Commodity sales supply intelligent management method and system based on Internet of Things

Abstract

The invention discloses a commodity sales and supply intelligent management method and system based on the Internet of Things, and relates to the field of sales and supply management. According to the method, primary optimization and secondary optimization are carried out on the placement positions of the goods shelves in the warehouse from the two aspects of the overall sheltered area of the goods shelves placed in the warehouse and the space utilization rate of the goods placed on the goods shelves, a second final goods shelf coordinate point matrix is finally obtained, and the goods shelves are placed according to the coordinates; according to the method, commodities with high selling frequency can be placed on more conspicuous goods shelves, the selling effect is better when the commodities are finally sold, in addition, two coordinate collection points are set at the bottom of the goods shelf corresponding to each selected goods shelf type in the selected goods shelf type set, and the goods shelf can be sold more accurately based on the two collection points of each goods shelf subsequently. And the position of the goods shelf in the current warehouse is determined and optimized, and the position is quantified, so that subsequent iterative updating is facilitated.

Description

Technical Field

[0001] The present invention belongs to the field of sales and supply management, and in particular, relates to an intelligent management method and system for commodity sales and supply based on the Internet of Things. Background Art

[0002] A Chinese patent with announcement number CN113269457B discloses an integrated management system and method for commodity sales and supply based on big data. Distributors send historical sales to a management terminal, which analyzes the distributor's historical sales and outputs supply instructions to suppliers. Suppliers supply goods to distributors according to the supply instructions. The management terminal analyzes the distributor's historical sales big data, predicts the supply date, and provides unified supply to distributors.

[0003] At present, when goods are supplied for sale, the goods usually need to be placed on shelves for consumers or customers to view; if the shelves in the warehouse are not placed reasonably, most of the goods placed on the shelves will be blocked, which will affect the visit of consumers or customers and further affect the sales of these goods; in addition, due to the differences in the types of shelves, the unreasonable placement of shelves in the warehouse will also affect the low space utilization rate of the goods on the shelves, which is not conducive to the sales of the goods. Summary of the invention

[0004] In view of the problems in the related art, the present invention proposes an intelligent management method and system for commodity sales and supply based on the Internet of Things to overcome the above-mentioned technical problems existing in the existing related technology.

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

[0006] The present invention is an intelligent management method for commodity sales and supply based on the Internet of Things, comprising the following steps:

[0007] S1. Collect the characteristic data of the current goods to be stored, the selected shelves and the current warehouse, and obtain the characteristic data matrix of the goods to be stored, the characteristic data matrix of the selected shelves and the characteristic data set of the current warehouse;

[0008] S2. Construct a three-dimensional coordinate system of the current warehouse based on the current warehouse feature data set; classify each commodity in the commodity feature data matrix to be stored according to the sales frequency to obtain the current classified commodity matrix to be stored;

[0009] S3, collecting the coordinate points of each shelf in the current warehouse corresponding to the selected shelf feature data matrix in cooperation with the three-dimensional coordinate system of the current warehouse, and obtaining an initial shelf coordinate point matrix; obtaining the blocked area of ​​each shelf placed in the current warehouse according to the initial shelf coordinate point matrix, and obtaining an initial blocked area; optimizing the initial shelf coordinate point matrix once according to the initial blocked area, and obtaining a first final shelf coordinate point matrix;

[0010] S4, obtaining the unobstructed area data of each shelf placed in the current warehouse according to the first final shelf coordinate point matrix, and obtaining an unobstructed area data set; calculating the space utilization rate of the goods placed on each shelf according to the unobstructed area data set and the current classified commodity matrix to be stored, and obtaining initial space utilization rate data; performing secondary optimization on the first final shelf coordinate point matrix according to the initial space utilization rate data, and obtaining a second final shelf coordinate point matrix;

[0011] When selling goods, it is necessary to supply goods; goods are usually placed on shelves in warehouses; because different goods, shelves and warehouses have different characteristics, these characteristics determine the different ways of placing shelves in warehouses and the different ways of placing goods on shelves; based on this, in this scheme, firstly, by collecting the characteristic data of the current goods to be stored, the selected shelves and the current warehouse, data support is provided for the subsequent placement of shelves in the current warehouse and the placement of goods on the shelves; therefore, by constructing the three-dimensional coordinate system of the current warehouse, a coordinate system support is provided for the subsequent acquisition of the placement coordinate position of each shelf; according to common sense, goods with a good historical sales frequency often need to be placed in a conspicuous and easy-to-access position because they need to be stored or picked up frequently and are viewed by customers more frequently; based on this, in this scheme, each product in the characteristic data matrix of the goods to be stored is classified according to the sales frequency, so as to provide a data basis for the subsequent placement of goods according to the sales frequency; before optimizing the placement position of the shelves in the current warehouse, first initialize the current warehouse The location of the shelves in the warehouse, because the larger the blocked area of ​​the shelves, the more likely it is that the goods placed on the shelves will be blocked, which will affect the final sales of the goods; based on this, in this solution, by calculating the blocked area of ​​the shelves in the warehouse, when the blocked area of ​​the shelves does not meet the requirements after the current location of the shelves in the warehouse is initialized, it is necessary to optimize the location of the shelves in the current warehouse so that the overall blocked area of ​​the shelves in the warehouse meets the requirements; in addition, this solution also considers the space utilization rate when the goods are placed on the shelves. The greater the space utilization rate, the more goods can be placed in the unit space, which is conducive to the sales of the goods; in addition, due to the different characteristics of the goods and the different characteristics of the shelves, the space utilization rates of the same goods placed on different shelves are also different; based on this, when the overall blocked area of ​​the shelves in the warehouse meets the requirements, if the space utilization rate of the goods placed at the same time also meets the requirements, there is no need to optimize the shelf positions in the warehouse; otherwise, the shelf positions in the warehouse need to be optimized to meet the requirements of space utilization.

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

[0013] S11. Set multiple commodity supply shelf feature types, commodity feature types, and warehouse feature types to obtain a supply shelf feature type set. Product feature type set and warehouse feature type sets a 1i 、a 2i 、a 3iThey respectively represent the set i-th commodity supply shelf feature type, commodity feature type and warehouse feature type, and a1′, a′2 and a3′ respectively represent the total number of the set commodity supply shelf feature type, commodity feature type and warehouse feature type;

[0014] S12: Set the current goods to be stored, the available shelf type and the current warehouse to obtain the current goods to be stored set. And select shelf type set They represent the i-th item to be stored and the i-th shelf type currently available. Respectively represent the total number of goods currently to be stored and the types of shelves available;

[0015] According to the commodity feature type set and the warehouse feature type set, feature data of each commodity to be stored in the current commodity set and feature data of each type of shelf in the selected shelf type set are collected to obtain a commodity feature data matrix b1 and a selected shelf feature data matrix b2; respectively, as follows:

[0016]

[0017] Among them, b 1ij , b 2ij Respectively represent the j-th characteristic data of the i-th commodity currently to be stored and the j-th characteristic data of the i-th shelf type currently available;

[0018] Collect the feature data of the current warehouse according to the warehouse feature type set to obtain the current warehouse feature data set b 3i Represents the feature data of the i-th type of the current warehouse;

[0019] The supply shelf feature types include the number of layers, the load-bearing capacity of each layer, the length, width and height of each layer, etc.; the product feature types include weight, length, width, height, shape, whether it can be stored and whether it can be squeezed, etc.; the warehouse feature types include internal volume, etc.; the selected shelf types include beam shelves, through shelves, cantilever shelves, mezzanine shelves, gravity shelves, mobile shelves, rotating shelves, mold racks, steel structure platforms and shuttle racks, etc.

[0020] Preferably, S2 comprises the following steps:

[0021] S21, constructing a three-dimensional coordinate system of the current warehouse according to the current warehouse feature data set; setting a statistical period, obtaining the sales frequency of each current commodity to be stored in the current commodity set according to the historical sales data of the current store within the statistical period, and obtaining a current sales frequency set;

[0022] Set the sales frequency level set and the corresponding sales frequency range set b i ′1, b i ′2 respectively represent the frequency lower limit data and frequency upper limit data of the set i-th selling frequency level, Indicates the total number of sales frequency levels that are set;

[0023] S22: dividing the current commodities to be stored in the current commodity set to be stored according to the selling frequency range set and the current selling frequency set to obtain a current classified commodity matrix to be stored as follows,

[0024]

[0025] in, represents the jth current inventory item corresponding to the i-th sales frequency level in the current inventory item set, c i Indicates the total number of current commodities to be stored corresponding to the i-th selling frequency level in the current commodity set to be stored;

[0026] The sales frequency levels include low frequency level, medium frequency level and high frequency level.

[0027] Preferably, S3 comprises the following steps:

[0028] S31, in the selected shelf type set, two coordinate collection points are set at the bottom of each shelf corresponding to the selected shelf type, to obtain a shelf coordinate collection point matrix as follows,

[0029]

[0030] in, They respectively represent two coordinate collection points set at the bottom of the shelf corresponding to the i-th selected shelf type in the selected shelf type set;

[0031] S32: Set the number of shelves corresponding to each shelf type in the selected shelf type set in the current warehouse when storing and selling goods, and obtain an initial shelf quantity data set Indicates the number of shelves corresponding to the i-th shelf type in the shelf type set placed in the current warehouse as initially set;

[0032] Cooperate with the three-dimensional coordinate system of the current warehouse and collect the point matrix according to the shelf coordinates And the initial shelf quantity dataset Get each shelf coordinate point corresponding to each shelf type in the shelf type set, and get the initial shelf coordinate point matrix c'; as follows,

[0033]

[0034] Among them, c i ' j1 、c i ' j2 They represent the first and second coordinate points at the bottom of the jth shelf corresponding to the i-th shelf type in the shelf type set placed in the current warehouse; c i ' j1 =(c i ' j11 ,c i ' j12 ,c i ' j13 ), c i ' j2 =(c i ' j21 ,c i ' j22 ,c i ' j23 ), c i ' j11 、c i ' j12 、c i ' j13 Respectively represent c i ' j1 One-dimensional coordinate data, two-dimensional coordinate data and three-dimensional coordinate data; c i ' j21 、c i ' j22 、c i ' j23 Respectively represent c i ' j2 One-dimensional coordinate data, two-dimensional coordinate data and three-dimensional coordinate data;

[0035] S33, cooperate with the selected shelf feature data matrix b2 and according to the initial shelf coordinate point matrix c′, shelf type set and initial shelf quantity data set Each shelf of each type is placed in the current warehouse; after the placement is completed, all shelves inside the warehouse are photographed by a camera at the warehouse entrance to obtain a first photographed shelf image data set; the area blocked by the shelves inside the current warehouse is obtained according to the photographed shelf image data set, and recorded as the initial blocked area;

[0036] S34, optimizing the initial shelf coordinate point matrix c' according to the initial blocked area to obtain a first final shelf coordinate point matrix;

[0037] Since the position of a shelf in a warehouse can be determined by the three-dimensional coordinates of two points on the shelf, two coordinate collection points are set at the bottom of each shelf corresponding to the selected shelf type in the selected shelf type set, and the position of the shelf in the current warehouse is determined and optimized based on the two collection points of each shelf. Since the number of shelves of each type must be more than one when placing shelves, the number of shelves corresponding to each shelf type in the selected shelf type set is set in the current warehouse when storing and selling goods, which further provides data support for the subsequent placement of shelves. When customers arrive at the warehouse entrance, the more goods directly presented to the customers, the higher the probability of selling the goods. Therefore, a camera is used at the warehouse entrance to shoot all the shelves inside the warehouse, which provides data support for the subsequent calculation of the blocked area of ​​the shelves.

[0038] Preferably, the S34 comprises the following steps:

[0039] S341, setting a threshold of the blocked area;

[0040] S342: When the initial blocked area is smaller than the blocked area threshold, there is no need to optimize the initial shelf coordinate point matrix, and the initial shelf coordinate point matrix is ​​used as the first final shelf coordinate point matrix;

[0041] Otherwise, the initial shelf coordinate point matrix is ​​optimized once until the initial blocked area is smaller than the blocked area threshold, thereby obtaining a first final shelf coordinate point matrix;

[0042] By presetting the blocked area threshold, a basis is provided for determining whether the currently acquired blocked area data meets the requirements.

[0043] Preferably, optimizing the initial shelf coordinate point matrix in S342 includes the following steps:

[0044] S3421, build the first tuna population d 1k represents the kth tuna in the first tuna population, d1′ represents the size of the first tuna population; the maximum number of iterations of the first tuna population is set to The current number of iterations is are respectively recorded as the first maximum number of iterations and the first current number of iterations; the search space dimension of the first tuna population is

[0045] S3422, randomly select a number of groups of three-dimensional coordinate points in the three-dimensional coordinate system of the current warehouse in conjunction with the initial shelf coordinate point matrix c′ as the first tuna population The initial position of each tuna in the first initial position matrix set is obtained. represents the initial position matrix of the kth tuna in the first tuna population; as follows,

[0046]

[0047] in, Respectively represent the component sets in the dimensions of the first coordinate point and the second coordinate point of the bottom of the jth shelf corresponding to the i-th shelf type in the shelf type set placed in the current warehouse of the initial position matrix of the k-th tuna in the first tuna population;

[0048] Respectively The component values ​​in the one-dimensional coordinate data, two-dimensional coordinate data, and three-dimensional coordinate data dimensions, Respectively Component values ​​in one-dimensional coordinate data, two-dimensional coordinate data, and three-dimensional coordinate data dimensions;

[0049] S3423, constructing the first tuna population The fitness function e1 is as follows:

[0050]

[0051] In the formula, e′ represents the area of ​​the shelves currently blocked in the warehouse;

[0052] S3424, start iteration, before iteration, set the first current iteration number Set to 1; the first tuna population is used in the first iteration The fitness function e1 is used to calculate the fitness value of the initial position matrix of each tuna in the first initial position matrix set to obtain a first fitness value set; the maximum fitness value in the first fitness value set and the corresponding initial position matrix of the tuna are used as the first global optimal fitness and the first global optimal position respectively; the initial position matrix of each tuna in the first initial position matrix set is updated according to the first global optimal fitness and the first global optimal position; after the update is completed, the first current iteration number is Add 1 and enter the next iteration;

[0053] The first tuna population is used in each other iteration The fitness function e1 calculates the fitness value of the position matrix of each tuna updated in the previous round of iterations to obtain a second fitness value; the maximum fitness value in the second fitness value set and the corresponding initial position matrix of the tuna are respectively used as the second global optimal fitness and the second global optimal position; the position matrix of each tuna updated in the previous round of iterations is updated again according to the second global optimal fitness and the second global optimal position; after the update is completed, the first current iteration number is Add 1 and enter the next iteration;

[0054] S3425, when When , stop the iteration and get the first final global optimal position, otherwise, continue to iterate until until the time; taking the first final global optimal position as the first final shelf coordinate point matrix;

[0055] The tuna optimization algorithm has a fast convergence speed in single-objective optimization problems, can quickly approach the optimal solution, and can achieve high solution accuracy in most cases, ensuring the quality of the optimization results; by simulating the foraging behavior of tuna, it can maintain diversity in the search process, which helps the algorithm to jump out of the local optimal solution and improve the probability of finding the global optimal solution; based on the above advantages of the tuna optimization algorithm, the tuna optimization algorithm is used in this scheme to iteratively update the position of each shelf in the current warehouse for multiple times, and the total occluded area of ​​all shelves in the current warehouse is used as the fitness function. Therefore, as the iteration proceeds, the total occluded area of ​​all shelves in the current warehouse will become smaller and smaller, and finally meet the requirements.

[0056] Preferably, S4 comprises the following steps:

[0057] S41, placing each type of each shelf in the current warehouse according to the final shelf coordinate point matrix; after the placement is completed, photographing all the shelves inside the warehouse with a camera at the warehouse entrance to obtain a second photographed shelf image data set; obtaining the unobstructed area data of each shelf in the current warehouse according to the second photographed shelf image data set to obtain an unobstructed area data set e i ′ represents the i-th shelf in the current warehouse, Indicates the total number of shelves placed inside the current warehouse;

[0058] S42, matching the current classified commodity matrix to be stored And the unobstructed area dataset The products are placed on shelves with larger unobstructed area data according to the sales frequency level from high to low; after the placement is completed, the overall space utilization rate of all shelves in the current warehouse is calculated to obtain initial space utilization rate data;

[0059] S43, performing secondary optimization on the first final shelf coordinate point matrix according to the initial space utilization rate data to obtain a second final shelf coordinate point matrix;

[0060] S44, placing the shelves in the current warehouse according to the second final shelf coordinate point matrix, and then placing the goods on the shelves with larger unobstructed area data according to the sales frequency level from high to low; after the placement is completed, the goods are sold;

[0061] By placing products with higher sales frequency on shelves with larger unobstructed areas, products with higher sales frequency become more conspicuous, which helps increase sales volume.

[0062] Preferably, the S43 comprises the following steps:

[0063] S431, setting a space utilization threshold;

[0064] S432: when the initial space utilization data is less than the space utilization threshold, performing secondary optimization on the first final shelf coordinate point matrix until the initial space utilization data is greater than or equal to the space utilization threshold, thereby obtaining a second final shelf coordinate point matrix;

[0065] Otherwise, there is no need to perform secondary optimization on the first final shelf coordinate point matrix, and the first final shelf coordinate point matrix is ​​used as the second final shelf coordinate point matrix;

[0066] By presetting the space utilization threshold, a basis is provided for subsequent determination of whether the space utilization of the commodities currently placed on the shelf meets the requirements, so as to further optimize the first final shelf coordinate point matrix.

[0067] An intelligent management system for commodity sales and supply based on the Internet of Things, comprising a feature type setting module, a current feature data acquisition module, a coordinate system construction module, a commodity classification module, a shelf placement initial coordinate data acquisition module, an initial blocked area data acquisition module, a primary optimization module, an unblocked area data acquisition module, an initial space utilization rate calculation module and a secondary optimization module;

[0068] The feature type setting module is used to set a plurality of commodity supply shelf feature types, commodity feature types and warehouse feature types, and obtain a supply shelf type set, a commodity feature type set and a warehouse feature type set;

[0069] The current feature data collection module is used to collect feature data of the current goods to be stored, the selected shelves and the current warehouse according to the supply shelf type set, the commodity feature type set and the warehouse feature type set, and obtain a feature data matrix of the goods to be stored, a feature data matrix of the selected shelves and a feature data set of the current warehouse;

[0070] The coordinate system construction module is used to construct a three-dimensional coordinate system of the current warehouse according to the current warehouse feature data set;

[0071] The commodity classification module is used to classify each commodity in the commodity feature data matrix to be stored according to the sales frequency, and obtain the current classified commodity matrix to be stored;

[0072] The shelf placement initial coordinate data acquisition module is used to cooperate with the three-dimensional coordinate system of the current warehouse to collect the coordinate points of each shelf in the current warehouse corresponding to the selected shelf feature data matrix to obtain the initial shelf coordinate point matrix;

[0073] The initial blocked area data acquisition module is used to acquire the blocked area of ​​each shelf placed in the current warehouse according to the initial shelf coordinate point matrix to obtain the initial blocked area;

[0074] The primary optimization module is used to optimize the initial shelf coordinate point matrix according to the initial blocked area to obtain a first final shelf coordinate point matrix;

[0075] The unobstructed area data acquisition module is used to acquire the unobstructed area data of each shelf placed in the current warehouse according to the first final shelf coordinate point matrix to obtain an unobstructed area data set;

[0076] The initial space utilization calculation module is used to calculate the space utilization of the goods placed on each shelf according to the unobstructed area data set and the current classified goods matrix to be stored, and obtain the initial space utilization data;

[0077] The secondary optimization module is used to perform secondary optimization on the first final shelf coordinate point matrix according to the initial space utilization data to obtain the second final shelf coordinate point matrix.

[0078] The present invention has the following beneficial effects:

[0079] 1. In the present invention, the placement of the shelves in the warehouse is optimized once and twice from two aspects: the overall blocked area of ​​the shelves inside the warehouse and the space utilization rate of the goods placed on the shelves. The second final shelf coordinate point matrix is ​​finally obtained. The shelves are placed according to these coordinates, so that the goods with higher sales frequency can be placed on more conspicuous shelves, and the space utilization rate of the placement is also higher, so that the sales effect is better when the goods are finally sold.

[0080] 2. In the present invention, two coordinate collection points are set at the bottom of each shelf corresponding to the selected shelf type in the selected shelf type set, and then the position of each shelf in the current warehouse is determined and optimized based on the two collection points, and the position is quantified to facilitate subsequent iterative updates.

[0081] 3. In the present invention, the position of each shelf in the current warehouse is iteratively updated multiple times by using the tuna optimization algorithm, and the total blocked area of ​​all shelves in the current warehouse is used as the fitness function. Therefore, as the iteration proceeds, the total blocked area of ​​all shelves in the current warehouse will become smaller and smaller, and finally meet the requirements; then the first final shelf coordinate point matrix is ​​further updated, and the overall blocked area of ​​the shelves in the current warehouse and the space utilization rate of the goods are used as the fitness function. Therefore, as the iteration proceeds, the overall blocked area of ​​the shelves in the current warehouse will become smaller and smaller, and the space utilization rate of the goods will become larger and larger, and finally meet the requirements, so that the final product sales effect is better.

[0082] 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

[0083] 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.

[0084] Figure 1 The present invention is a flowchart of an intelligent management method for commodity sales and supply based on the Internet of Things. DETAILED DESCRIPTION

[0085] 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.

[0086] 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.

[0087] Embodiment 1

[0088] This embodiment is a method for intelligent management of commodity sales and supply based on the Internet of Things, comprising the following steps:

[0089] S1. Collect the characteristic data of the current goods to be stored, the selected shelves and the current warehouse, and obtain the characteristic data matrix of the goods to be stored, the characteristic data matrix of the selected shelves and the characteristic data set of the current warehouse;

[0090] The S1 comprises the following steps:

[0091] S11. Set multiple commodity supply shelf feature types, commodity feature types, and warehouse feature types to obtain a supply shelf feature type set. Product feature type set

[0092] and warehouse feature type sets a 1i 、a 2i 、a 3i They respectively represent the set i-th commodity supply shelf feature type, commodity feature type and warehouse feature type, and a1′, a′2 and a3′ respectively represent the total number of the set commodity supply shelf feature type, commodity feature type and warehouse feature type;

[0093] S12: Set the current goods to be stored, the available shelf type and the current warehouse to obtain the current goods to be stored set. And select shelf type set They represent the i-th item to be stored and the i-th shelf type currently available. Respectively represent the total number of goods currently to be stored and the types of shelves available;

[0094] According to the commodity feature type set and the warehouse feature type set, feature data of each commodity to be stored in the current commodity set and feature data of each type of shelf in the selected shelf type set are collected to obtain a commodity feature data matrix b1 and a selected shelf feature data matrix b2; respectively, as follows:

[0095]

[0096] Among them, b 1ij , b 2ij Respectively represent the j-th characteristic data of the i-th commodity currently to be stored and the j-th characteristic data of the i-th shelf type currently available;

[0097] Collect the feature data of the current warehouse according to the warehouse feature type set to obtain the current warehouse feature data set b 3i Represents the feature data of the i-th type of the current warehouse;

[0098] S2. Construct a three-dimensional coordinate system of the current warehouse based on the current warehouse feature data set; classify each commodity in the commodity feature data matrix to be stored according to the sales frequency to obtain the current classified commodity matrix to be stored;

[0099] The S2 comprises the following steps:

[0100] S21, constructing a three-dimensional coordinate system of the current warehouse according to the current warehouse feature data set; setting a statistical period, obtaining the sales frequency of each current commodity to be stored in the current commodity set according to the historical sales data of the current store within the statistical period, and obtaining a current sales frequency set;

[0101] Set the sales frequency level set and the corresponding sales frequency range set b i ′1, b i ′2 respectively represent the frequency lower limit data and frequency upper limit data of the set i-th selling frequency level, Indicates the total number of sales frequency levels that are set;

[0102] S22: dividing the current commodities to be stored in the current commodity set to be stored according to the selling frequency range set and the current selling frequency set to obtain a current classified commodity matrix to be stored as follows,

[0103]

[0104] in, represents the jth current inventory item corresponding to the i-th sales frequency level in the current inventory item set, c i Indicates the total number of current commodities to be stored corresponding to the i-th selling frequency level in the current commodity set to be stored;

[0105] S3, collecting the coordinate points of each shelf in the current warehouse corresponding to the selected shelf feature data matrix in cooperation with the three-dimensional coordinate system of the current warehouse, and obtaining an initial shelf coordinate point matrix; obtaining the blocked area of ​​each shelf placed in the current warehouse according to the initial shelf coordinate point matrix, and obtaining an initial blocked area; optimizing the initial shelf coordinate point matrix once according to the initial blocked area, and obtaining a first final shelf coordinate point matrix;

[0106] The S3 comprises the following steps:

[0107] S31, in the selected shelf type set, two coordinate collection points are set at the bottom of each shelf corresponding to the selected shelf type, to obtain a shelf coordinate collection point matrix as follows,

[0108]

[0109] in, They respectively represent two coordinate collection points set at the bottom of the shelf corresponding to the i-th selected shelf type in the selected shelf type set;

[0110] S32: Set the number of shelves corresponding to each shelf type in the selected shelf type set in the current warehouse when storing and selling goods, and obtain an initial shelf quantity data set Indicates the number of shelves corresponding to the i-th shelf type in the shelf type set placed in the current warehouse as initially set;

[0111] Cooperate with the three-dimensional coordinate system of the current warehouse and collect the point matrix according to the shelf coordinates And the initial shelf quantity dataset Get each shelf coordinate point corresponding to each shelf type in the shelf type set, and get the initial shelf coordinate point matrix c'; as follows,

[0112]

[0113] Among them, c i ' j1 、c i ' j2 They represent the first and second coordinate points at the bottom of the jth shelf corresponding to the i-th shelf type in the shelf type set placed in the current warehouse; c i ' j1 =(c i ' j11 ,c i ' j12 ,c i ' j13 ), c i ' j2 =(c i ' j21 ,c i ' j22 ,c i ' j23 ), c i ' j11 、c i ' j12 、c i ' j13 Respectively represent c i ' j1 One-dimensional coordinate data, two-dimensional coordinate data and three-dimensional coordinate data; c i ' j21 、ci ' j22 、c i ' j23 Respectively represent c i ' j2 One-dimensional coordinate data, two-dimensional coordinate data and three-dimensional coordinate data;

[0114] S33, cooperate with the selected shelf feature data matrix b2 and according to the initial shelf coordinate point matrix c′, shelf type set and initial shelf quantity data set Each shelf of each type is placed in the current warehouse; after the placement is completed, all shelves inside the warehouse are photographed by a camera at the warehouse entrance to obtain a first photographed shelf image data set; the area blocked by the shelves inside the current warehouse is obtained according to the photographed shelf image data set, and recorded as the initial blocked area;

[0115] S34, optimizing the initial shelf coordinate point matrix c' according to the initial blocked area to obtain a first final shelf coordinate point matrix;

[0116] The S34 comprises the following steps:

[0117] S341, setting a threshold of the blocked area;

[0118] S342: When the initial blocked area is smaller than the blocked area threshold, there is no need to optimize the initial shelf coordinate point matrix, and the initial shelf coordinate point matrix is ​​used as the first final shelf coordinate point matrix;

[0119] Otherwise, the initial shelf coordinate point matrix is ​​optimized once until the initial blocked area is smaller than the blocked area threshold, thereby obtaining a first final shelf coordinate point matrix;

[0120] The optimization of the initial shelf coordinate point matrix in S342 includes the following steps:

[0121] S3421, build the first tuna population d 1k represents the kth tuna in the first tuna population, d1′ represents the size of the first tuna population; the maximum number of iterations of the first tuna population is set to The current number of iterations is are respectively recorded as the first maximum number of iterations and the first current number of iterations; the search space dimension of the first tuna population is

[0122] S3422, randomly select a number of groups of three-dimensional coordinate points in the three-dimensional coordinate system of the current warehouse in conjunction with the initial shelf coordinate point matrix c′ as the first tuna population The initial position of each tuna in the first initial position matrix set is obtained. represents the initial position matrix of the kth tuna in the first tuna population; as follows,

[0123]

[0124] in, Respectively represent the component sets in the dimensions of the first coordinate point and the second coordinate point of the bottom of the jth shelf corresponding to the i-th shelf type in the shelf type set placed in the current warehouse of the initial position matrix of the k-th tuna in the first tuna population;

[0125] Respectively The component values ​​in the one-dimensional coordinate data, two-dimensional coordinate data, and three-dimensional coordinate data dimensions, Respectively Component values ​​in one-dimensional coordinate data, two-dimensional coordinate data, and three-dimensional coordinate data dimensions;

[0126] S3423, constructing the first tuna population The fitness function e1 is as follows:

[0127]

[0128] In the formula, e′ represents the area of ​​the shelves currently blocked in the warehouse;

[0129] S3424, start iteration, before iteration, set the first current iteration number Set to 1; the first tuna population is used in the first iteration The fitness function e1 is used to calculate the fitness value of the initial position matrix of each tuna in the first initial position matrix set to obtain a first fitness value set; the maximum fitness value in the first fitness value set and the corresponding initial position matrix of the tuna are used as the first global optimal fitness and the first global optimal position respectively; the initial position matrix of each tuna in the first initial position matrix set is updated according to the first global optimal fitness and the first global optimal position; after the update is completed, the first current iteration number is Add 1 and enter the next iteration;

[0130] The first tuna population is used in each other iteration The fitness function e1 calculates the fitness value of the position matrix of each tuna updated in the previous round of iterations to obtain a second fitness value; the maximum fitness value in the second fitness value set and the corresponding initial position matrix of the tuna are respectively used as the second global optimal fitness and the second global optimal position; the position matrix of each tuna updated in the previous round of iterations is updated again according to the second global optimal fitness and the second global optimal position; after the update is completed, the first current iteration number is Add 1 and enter the next iteration;

[0131] S3425, when When , stop the iteration and get the first final global optimal position, otherwise, continue to iterate until until the time; taking the first final global optimal position as the first final shelf coordinate point matrix;

[0132] S4, obtaining the unobstructed area data of each shelf placed in the current warehouse according to the first final shelf coordinate point matrix, and obtaining an unobstructed area data set; calculating the space utilization rate of the goods placed on each shelf according to the unobstructed area data set and the current classified commodity matrix to be stored, and obtaining initial space utilization rate data; performing secondary optimization on the first final shelf coordinate point matrix according to the initial space utilization rate data, and obtaining a second final shelf coordinate point matrix;

[0133] The S4 comprises the following steps:

[0134] S41, placing each type of each shelf in the current warehouse according to the final shelf coordinate point matrix; after the placement is completed, photographing all the shelves inside the warehouse with a camera at the warehouse entrance to obtain a second photographed shelf image data set; obtaining the unobstructed area data of each shelf in the current warehouse according to the second photographed shelf image data set to obtain an unobstructed area data set e i ′ represents the i-th shelf in the current warehouse, Indicates the total number of shelves placed inside the current warehouse;

[0135] S42, matching the current classified commodity matrix to be stored And the unobstructed area dataset The products are placed on shelves with larger unobstructed area data according to the sales frequency level from high to low; after the placement is completed, the overall space utilization rate of all shelves in the current warehouse is calculated to obtain initial space utilization rate data;

[0136] S43, performing secondary optimization on the first final shelf coordinate point matrix according to the initial space utilization rate data to obtain a second final shelf coordinate point matrix;

[0137] The S43 comprises the following steps:

[0138] S431, setting a space utilization threshold;

[0139] S432: when the initial space utilization data is less than the space utilization threshold, performing secondary optimization on the first final shelf coordinate point matrix until the initial space utilization data is greater than or equal to the space utilization threshold, thereby obtaining a second final shelf coordinate point matrix;

[0140] Otherwise, there is no need to perform secondary optimization on the first final shelf coordinate point matrix, and the first final shelf coordinate point matrix is ​​used as the second final shelf coordinate point matrix;

[0141] The secondary optimization of the first final shelf coordinate point matrix in S432 includes the following steps:

[0142] S4321. Establishment of the second tuna population d 2k represents the kth tuna in the second tuna population, d2′ represents the size of the second tuna population; the maximum number of iterations of the second tuna population is set to The current number of iterations is are respectively recorded as the second maximum number of iterations and the second current number of iterations; the search space dimension of the second tuna population is

[0143] S4322, randomly selecting a plurality of groups of three-dimensional coordinate points in the three-dimensional coordinate system of the current warehouse in conjunction with the first final shelf coordinate point matrix as the second tuna population The initial position of each tuna in the second initial position matrix set is obtained. represents the initial position matrix of the kth tuna in the second tuna population; as follows,

[0144]

[0145] in, Respectively represent the component sets in the dimensions of the first coordinate point and the second coordinate point of the bottom of the jth shelf corresponding to the i-th shelf type in the shelf type set placed in the current warehouse of the initial position matrix of the k-th tuna in the second tuna population; Respectively The component values ​​in the one-dimensional coordinate data, two-dimensional coordinate data, and three-dimensional coordinate data dimensions, Respectively Component values ​​in one-dimensional coordinate data, two-dimensional coordinate data, and three-dimensional coordinate data dimensions;

[0146] S4323, construct the second tuna population The fitness function e2 is as follows:

[0147]

[0148] In the formula, f represents the space utilization data;

[0149] S4324, start iteration, before iteration, set the second current iteration number Set to 1; the second tuna population is used in the first iteration The fitness function e2 is used to calculate the fitness value of the initial position matrix of each tuna in the second initial position matrix set to obtain a third fitness value set; the maximum fitness value in the third fitness value set and the corresponding initial position matrix of the tuna are used as the third global optimal fitness and the third global optimal position respectively; the initial position matrix of each tuna in the second initial position matrix set is updated according to the third global optimal fitness and the third global optimal position; after the update is completed, the second current iteration number is Add 1 and enter the next iteration;

[0150] The second tuna population is used in each additional iteration The fitness function e2 calculates the fitness value of the position matrix of each tuna updated in the previous round of iterations to obtain a fourth fitness value; the maximum fitness value in the fourth fitness value set and the corresponding initial position matrix of the tuna are respectively used as the fourth global optimal fitness and the fourth global optimal position; the position matrix of each tuna updated in the previous round of iterations is updated again according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, the second current iteration number Add 1 and enter the next iteration;

[0151] S4325, when When , stop the iteration and get the second final global optimal position, otherwise, continue to iterate until until the second final global optimal position is used as the second final shelf coordinate point matrix;

[0152] The first final shelf coordinate matrix is ​​further updated by using the tuna optimization algorithm, and the overall blocked area of ​​the shelves in the current warehouse and the space utilization rate of the goods are used as the fitness function. Therefore, as the iteration proceeds, the overall blocked area of ​​the shelves in the current warehouse will become smaller and smaller, and the space utilization rate of the goods will become larger and larger, and finally meet the requirements, so that the final product sales effect is better;

[0153] S44, placing the shelves in the current warehouse according to the second final shelf coordinate point matrix, and then placing the goods on the shelves with larger unobstructed area data according to the sales frequency level from high to low; after the placement is completed, selling the goods;.

[0154] Embodiment 2

[0155] This embodiment discloses an intelligent management system for commodity sales and supply based on the Internet of Things. The system can implement the method of the above embodiment, including:

[0156] 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.

[0157] 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. An intelligent management method for commodity sales and supply based on the Internet of Things, characterized in that: The following steps are involved: S1. Collect the characteristic data of the current goods to be stored, the selected shelves and the current warehouse, and obtain the characteristic data matrix of the goods to be stored, the characteristic data matrix of the selected shelves and the characteristic data set of the current warehouse; S2. Construct a three-dimensional coordinate system of the current warehouse based on the current warehouse feature data set; Classify each product in the product feature data matrix to be stored according to the sales frequency to obtain the current classified product matrix to be stored; S3, collecting the coordinate points of each shelf in the current warehouse corresponding to the selected shelf feature data matrix in cooperation with the three-dimensional coordinate system of the current warehouse, and obtaining an initial shelf coordinate point matrix; Obtain the blocked area of ​​each shelf placed in the current warehouse according to the initial shelf coordinate point matrix to obtain the initial blocked area; optimize the initial shelf coordinate point matrix according to the initial blocked area to obtain the first final shelf coordinate point matrix; S4, obtaining unobstructed area data of each shelf placed in the current warehouse according to the first final shelf coordinate point matrix, to obtain an unobstructed area data set; Calculate the space utilization of the goods placed on each shelf based on the unobstructed area data set and the current classified goods matrix to be stored, and obtain the initial space utilization data; The first final shelf coordinate point matrix is ​​optimized twice according to the initial space utilization data to obtain the second final shelf coordinate point matrix.

2. According to the method of intelligent management of commodity sales and supply based on the Internet of Things in claim 1, it is characterized in that: The S1 comprises the following steps: S11, setting a plurality of commodity supply shelf feature types, commodity feature types, and warehouse feature types, and obtaining a supply shelf feature type set, a commodity feature type set, and a warehouse feature type set; S12. Set the current goods to be stored, the available shelf types and the current warehouse to obtain the current goods set to be stored and the selected shelf type set; collect the feature data of each current goods to be stored in the current goods set and the feature data of each type of shelf in the selected shelf type set according to the goods feature type set and the warehouse feature type set to obtain the goods feature data matrix and the selected shelf feature data matrix; collect the feature data of the current warehouse according to the warehouse feature type set to obtain the current warehouse feature data set.

3. The method for intelligent management of commodity sales and supply based on the Internet of Things according to claim 2, characterized in that: The S2 comprises the following steps: S21, constructing a three-dimensional coordinate system of the current warehouse according to the current warehouse feature data set; setting a statistical period, obtaining the sales frequency of each current commodity to be stored in the current commodity set according to the historical sales data of the current store within the statistical period, and obtaining a current sales frequency set; setting a sales frequency level set and a corresponding sales frequency range set; S22. Divide the current commodities to be stored in the current commodity set to be stored according to the selling frequency range set and the current selling frequency set to obtain a current classified commodity matrix to be stored.

4. The method for intelligent management of commodity sales and supply based on the Internet of Things according to claim 3 is characterized in that: The S3 comprises the following steps: S31, setting two coordinate collection points at the bottom of each shelf corresponding to each selected shelf type in the selected shelf type set, to obtain a shelf coordinate collection point matrix; S32, setting the number of shelves corresponding to each shelf type in the selected shelf type set to be placed in the current warehouse when storing and selling goods, and obtaining an initial shelf quantity data set; Acquire each shelf coordinate point corresponding to each shelf type in the shelf type set in accordance with the three-dimensional coordinate system of the current warehouse and the shelf coordinate acquisition point matrix and the initial shelf quantity data set to obtain an initial shelf coordinate point matrix; S33, placing each type of shelf in the current warehouse according to the initial shelf coordinate point matrix, the shelf type set and the initial shelf quantity data set in conjunction with the selected shelf feature data matrix; after the placement is completed, photographing all the shelves inside the warehouse with a camera at the warehouse entrance to obtain a first photographed shelf image data set; obtaining the area blocked by the shelves inside the current warehouse according to the photographed shelf image data set, and recording it as the initial blocked area; S34. Optimize the initial shelf coordinate point matrix according to the initial blocked area to obtain a first final shelf coordinate point matrix.

5. The method for intelligent management of commodity sales and supply based on the Internet of Things according to claim 4, characterized in that: The S34 comprises the following steps: S341, setting a threshold of the blocked area; S342: When the initial blocked area is smaller than the blocked area threshold, there is no need to optimize the initial shelf coordinate point matrix, and the initial shelf coordinate point matrix is ​​used as the first final shelf coordinate point matrix; Otherwise, the initial shelf coordinate point matrix is ​​optimized once until the initial blocked area is smaller than the blocked area threshold, thereby obtaining the first final shelf coordinate point matrix.

6. The method for intelligent management of commodity sales and supply based on the Internet of Things according to claim 5, characterized in that: The optimization of the initial shelf coordinate point matrix in S342 includes the following steps: S3421, constructing a first tuna population; setting the maximum number of iterations of the first tuna population to The current number of iterations is They are respectively recorded as the first maximum number of iterations and the first current number of iterations; S3422, randomly selecting a number of groups of three-dimensional coordinate points in the three-dimensional coordinate system of the current warehouse in conjunction with the initial shelf coordinate point matrix as the initial position of each tuna in the first tuna population, to obtain a first initial position matrix set; S3423. Constructing a fitness function of the first tuna population; S3424, start iteration; in each round of iteration, use the fitness function of the first tuna population to calculate the fitness value of the position matrix of each tuna updated in the previous round of iteration, and update the position matrix of each tuna updated in the previous round of iteration again; S3425, when When , stop the iteration and get the first final global optimal position, otherwise, continue to iterate until until the time; the first final global optimal position is used as the first final shelf coordinate point matrix.

7. The method for intelligent management of commodity sales and supply based on the Internet of Things according to claim 6, characterized in that: The S4 comprises the following steps: S41, placing each shelf of each type in the current warehouse according to the final shelf coordinate point matrix; after the placement is completed, photographing all the shelves inside the warehouse with a camera at the warehouse entrance to obtain a second photographed shelf image data set; obtaining unobstructed area data of each shelf in the current warehouse according to the second photographed shelf image data set to obtain an unobstructed area data set; S42, placing the goods on the shelves with larger unobstructed area data according to the sales frequency level from high to low in combination with the current classified goods matrix to be stored and the unobstructed area data set; after the placement is completed, calculating the overall space utilization rate of all shelves in the current warehouse to obtain initial space utilization rate data; S43, performing secondary optimization on the first final shelf coordinate point matrix according to the initial space utilization rate data to obtain a second final shelf coordinate point matrix; S44, placing the shelves in the current warehouse according to the second final shelf coordinate point matrix, and then placing the goods on the shelves with larger unobstructed area data according to the sales frequency level from high to low; after the placement is completed, selling the goods.

8. The method for intelligent management of commodity sales and supply based on the Internet of Things according to claim 7, characterized in that: The S43 comprises the following steps: S431, setting a space utilization threshold; S432: when the initial space utilization data is less than the space utilization threshold, performing secondary optimization on the first final shelf coordinate point matrix until the initial space utilization data is greater than or equal to the space utilization threshold, thereby obtaining a second final shelf coordinate point matrix; Otherwise, there is no need to perform secondary optimization on the first final shelf coordinate point matrix, and the first final shelf coordinate point matrix is ​​used as the second final shelf coordinate point matrix.

9. The method for intelligent management of commodity sales and supply based on the Internet of Things according to claim 8, characterized in that: In S432, the first final shelf coordinate point matrix is ​​optimized twice using the tuna optimization algorithm.

10. A system for implementing the intelligent management method for commodity sales and supply based on the Internet of Things as described in any one of claims 1 to 9.

Images