Commodity inventory distribution management method and system based on Internet of Things

Abstract

The invention relates to the field of commodity inventory distribution, and discloses a commodity inventory distribution management method and system based on the Internet of Things, and the method comprises the following steps: analyzing the preference degree of a commodity suitable user for a commodity, obtaining the initial demand of the commodity, and obtaining the initial demand of the commodity based on the initial demand of the commodity; carrying out supply quantity prediction analysis on the time-limited selling commodities and the continuous selling commodities to obtain the total quantity of the commodities; the commodity inventory change degree and the human traffic of different commodity distribution points are analyzed, and commodity supply amount distribution is carried out in combination with the total commodity amount; and comprehensively analyzing the commodity distribution point distribution map and the transportation cost and the route length of all the transportation routes to obtain an optimal commodity transportation route, and finally determining a final commodity loading scheme of the commodity transportation vehicle based on the supply state of the commodity and the property of the commodity. According to the invention, the commodity supply demand of each commodity distribution point can be obtained, the transportation condition of the commodity is reasonably planned, the benefit of the commodity is maximized, and the distribution efficiency of the commodity is improved at the same time.

Description

Technical Field

[0001] This invention relates to the field of commodity inventory distribution, and in particular to a commodity inventory distribution management method and system based on the Internet of Things. Background Technology

[0002] After production, goods accumulate a large inventory in warehouses, requiring transportation and sale to other distribution points. Different distribution points may sell different quantities of goods; for example, supermarkets with high foot traffic typically sell more than small shops. Supplying large supermarkets requires greater quantities, necessitating inventory distribution to increase sales and achieve higher economic benefits. Inventory distribution begins with transportation, assessing factors such as transportation costs, time, and distance to determine the optimal route and method. This ensures goods remain intact during transport and are delivered to distribution points quickly and efficiently, preventing inefficient routes, warehousing, and logistics management that could lead to high transportation costs and negatively impact profitability. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides a commodity inventory distribution management method and system based on the Internet of Things.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention provides a commodity inventory distribution management method based on the Internet of Things, comprising the following steps:

[0006] Obtain the degree of preference of the target users for the product, analyze the degree of preference of the target users for the product, and obtain the preliminary demand for the product based on the analysis results;

[0007] Based on the sales period of the goods, the goods are classified, and the supply of the classified goods is predicted and analyzed based on the initial demand of the goods to obtain the total quantity of goods.

[0008] The study analyzes the changes in commodity inventory and foot traffic at different commodity distribution points, and allocates commodity supply to different commodity distribution points based on the analysis results.

[0009] Construct a distribution map of commodity distribution points and obtain the transportation costs and route lengths of all transportation routes. Conduct a comprehensive analysis of the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal route for commodity transportation.

[0010] The supply status and nature of the goods are analyzed, and the final loading plan for the goods transport vehicle is determined based on the analysis results.

[0011] Furthermore, in a preferred embodiment of the present invention, the step of obtaining the degree of preference of applicable users for the product, analyzing the degree of preference of applicable users for the product, and obtaining the preliminary demand for the product based on the analysis results specifically includes:

[0012] The properties of the product are obtained, and based on these properties, applicable user analysis and prediction are performed in a big data network to obtain the applicable users of the product.

[0013] Create a market research questionnaire about the product, push the questionnaire to the devices of users who are interested in the product through a big data network, and collect the survey data of different users who are interested in the product, which is defined as product research data.

[0014] Based on the product survey data, the degree of preference of different product users for the product is obtained, and a standard degree of preference is preset. If the degree of preference of the product users for the product is greater than the standard degree of preference, the corresponding product users are marked as a type of user.

[0015] If the user's preference for the product is less than the standard preference level, the corresponding user will be marked as a second-class user.

[0016] We analyze the proportions of Category 1 and Category 2 users among all users applicable to the product, and then input these proportions into a convolutional neural network to make preliminary predictions of product demand, thus obtaining the preliminary demand for the product.

[0017] Furthermore, in a preferred embodiment of the present invention, the step of classifying goods based on their sales period and performing supply forecasting analysis on the classified goods based on the initial demand to obtain the total quantity of goods specifically involves:

[0018] Determine if a product has a sales period. If so, define the product as a limited-time sale product; otherwise, define the product as a continuously sellable product.

[0019] If the product is a limited-time sale item, then retrieve the current inventory of the limited-time sale item from the product warehouse;

[0020] Compare the initial demand for the limited-time sale item with the current inventory. If the initial demand for the limited-time sale item is greater than the current inventory, then the current inventory of the limited-time sale item is taken as the supply of the limited-time sale item and defined as the first item supply.

[0021] If the initial demand for a limited-time sale item is less than the current inventory, the historical demand for the limited-time sale item will be retrieved based on historical data, and the historical demand for the item with the highest similarity to the limited-time sale item will be retrieved through a big data network.

[0022] By combining the historical demand for limited-time sale items with the historical demand for items most similar in nature to limited-time sale items, a first predictive analysis result is obtained. Based on the first predictive analysis result, a second commodity supply quantity is obtained.

[0023] If the product is a continuously sold product, the historical demand for continuously sold products is obtained, and the supply of continuously sold products is determined based on the historical demand for continuously sold products, which is defined as the supply of the third product.

[0024] By combining the supply quantities of the first, second, and third commodities, the total quantity of commodities is obtained.

[0025] Furthermore, in a preferred embodiment of the present invention, the analysis of changes in commodity inventory and foot traffic at different commodity distribution points, and the allocation of commodity supply to different commodity distribution points based on the analysis results, specifically includes:

[0026] Identify product distribution points and, based on historical data, obtain the average foot traffic around the product distribution points, and preset the standard foot traffic.

[0027] If the average foot traffic around a product distribution point is greater than the standard foot traffic, the corresponding product distribution point will be designated as the first product distribution point; if the average foot traffic around a product distribution point is less than the standard foot traffic, the corresponding product distribution point will be designated as the second product distribution point.

[0028] Obtain the historical inventory change rate of all product distribution points, and classify and optimize the first and second product distribution points based on the historical inventory change rate of product distribution points to obtain popular product distribution points and ordinary product distribution points;

[0029] Get the supply status of the product and the percentage of popular product distribution points among all product distribution points. If the percentage of popular product distribution points among all product distribution points is greater than a preset value, the supply status of the product is defined as the first supply status of the product. If the percentage of popular product distribution points among all product distribution points is less than a preset value, the supply status of the product is defined as the second supply status of the product.

[0030] If the supply status of the goods is in the first supply status, then the total amount of goods will be supplied evenly to different popular goods distribution points so that the supply of goods at different popular goods distribution points is the same.

[0031] If the supply status of the goods is in the second supply status, the total amount of goods will be supplied to all distribution points. The supply of goods will be allocated among different distribution points based on the historical inventory change rate of the distribution points, so that all distribution points have goods to sell.

[0032] Furthermore, in a preferred embodiment of the present invention, the step of constructing a distribution map of commodity distribution points and obtaining the transportation costs and route lengths of all transportation routes, and then comprehensively analyzing the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal route for commodity transportation, specifically involves:

[0033] Obtain the coordinate information of different product distribution points, and import the coordinate information of the different product distribution points into map software to construct a product distribution point distribution map;

[0034] In the distribution map of the product distribution points, the Dijkstra algorithm is introduced to calculate the shortest path length between different product distribution points. Based on the shortest path length between different product distribution points, similar product distribution points are generated. The similar product distribution points contain several product distribution points, and the shortest path height between any two product distribution points in the similar product distribution points is less than a preset value.

[0035] Obtain the coordinate information of the commodity warehouse, and based on the coordinate information of the commodity warehouse and the distribution map of commodity distribution points, obtain all routes from the commodity warehouse to different commodity distribution points of the same type of commodity distribution points, and define them as a type of transportation route;

[0036] The transportation cost and route length of all routes in a class of transportation routes are obtained. A genetic algorithm is then introduced to iteratively calculate the transportation cost and route length of all routes in the class of transportation routes, as well as the shortest path length between different distribution points of the same type of goods, to obtain the optimal route for goods transportation.

[0037] Furthermore, in a preferred embodiment of the present invention, the analysis of the supply status and properties of the goods, and the determination of the final goods loading plan for the goods transport vehicle based on the analysis results, specifically includes:

[0038] Based on the supply status of the goods, obtain the supply volume of goods at different distribution points, and based on the supply volume of goods at different distribution points, obtain the total supply volume of goods at distribution points of the same type of goods;

[0039] The total supply and nature of goods at similar distribution points are imported into a big data network for retrieval, generating various goods loading schemes.

[0040] Obtain the specifications of the goods transport vehicle, and based on the specifications of the goods transport vehicle, obtain all feasible loading schemes for the goods transport vehicle;

[0041] Calculate the similarity between the feasible loading schemes of the goods transport vehicle and various goods loading schemes. Define the goods loading schemes whose similarity to the feasible loading schemes of a class of goods transport vehicles is greater than a preset value as usable goods loading schemes.

[0042] Calculate the number of goods transport vehicles required under different available goods loading schemes, and define the available goods loading scheme with the fewest required goods transport vehicles as the final goods loading scheme;

[0043] If there are several available goods loading schemes that require the fewest and the same number of goods transport vehicles, then the loading speed of the available goods loading schemes is predicted, and the available goods loading scheme with the fastest loading speed is defined as the final goods loading scheme.

[0044] A second aspect of the present invention also provides a commodity inventory distribution management system based on the Internet of Things (IoT). The commodity inventory distribution management system includes a memory and a processor. The memory stores a commodity inventory distribution management method. When the processor executes the commodity inventory distribution management method, it performs the following steps:

[0045] Obtain the degree of preference of the target users for the product, analyze the degree of preference of the target users for the product, and obtain the preliminary demand for the product based on the analysis results;

[0046] Based on the sales period of the goods, the goods are classified, and the supply of the classified goods is predicted and analyzed based on the initial demand of the goods to obtain the total quantity of goods.

[0047] The study analyzes the changes in commodity inventory and foot traffic at different commodity distribution points, and allocates commodity supply to different commodity distribution points based on the analysis results.

[0048] Construct a distribution map of commodity distribution points and obtain the transportation costs and route lengths of all transportation routes. Conduct a comprehensive analysis of the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal route for commodity transportation.

[0049] The supply status and nature of the goods are analyzed, and the final loading plan for the goods transport vehicle is determined based on the analysis results.

[0050] This invention addresses the technical deficiencies in the existing technology and offers the following beneficial effects: It analyzes the preferences of target users for a product, obtains the initial demand for the product, and based on this initial demand, performs supply forecasting analysis for limited-time and continuous sales products to obtain the total product volume; it analyzes the changes in product inventory and foot traffic at different distribution points, and allocates the product supply based on the total product volume; it comprehensively analyzes the distribution map of product distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal transportation route; and finally, based on the supply status and properties of the product, it determines the final product loading plan for the transport vehicles. This invention can obtain the product supply demand at each distribution point and rationally plan the transportation of the product, maximizing product profits. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0052] Figure 1 A flowchart of an IoT-based merchandise inventory distribution management method is shown;

[0053] Figure 2 A flowchart illustrating the method for obtaining the optimal route for goods transportation and the final goods loading plan is shown.

[0054] Figure 3 This paper presents a program view of an Internet of Things (IoT) based merchandise inventory distribution management system. Detailed Implementation

[0055] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0056] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0057] Figure 1 A flowchart illustrating an IoT-based merchandise inventory distribution management method is provided, including the following steps:

[0058] S102: Obtain the degree of preference of the applicable users for the product, analyze the degree of preference of the applicable users for the product, and obtain the preliminary demand for the product based on the analysis results;

[0059] S104: Based on the sales period of the goods, classify the goods, and based on the initial demand of the goods, conduct supply forecast analysis on the classified goods to obtain the total quantity of goods;

[0060] S106: Analyze the changes in commodity inventory and foot traffic at different commodity distribution points, and allocate commodity supply to different commodity distribution points based on the analysis results;

[0061] S108: Construct a distribution map of commodity distribution points, obtain the transportation cost and route length of all transportation routes, and conduct a comprehensive analysis of the distribution map of commodity distribution points, the transportation cost and route length of all transportation routes to obtain the optimal route for commodity transportation;

[0062] S110: Analyze the supply status and nature of the goods, and determine the final goods loading plan for the goods transport vehicle based on the analysis results.

[0063] Furthermore, in a preferred embodiment of the present invention, the step of obtaining the degree of preference of applicable users for the product, analyzing the degree of preference of applicable users for the product, and obtaining the preliminary demand for the product based on the analysis results specifically includes:

[0064] The properties of the product are obtained, and based on these properties, applicable user analysis and prediction are performed in a big data network to obtain the applicable users of the product.

[0065] Create a market research questionnaire about the product, push the questionnaire to the devices of users who are interested in the product through a big data network, and collect the survey data of different users who are interested in the product, which is defined as product research data.

[0066] Based on the product survey data, the degree of preference of different product users for the product is obtained, and a standard degree of preference is preset. If the degree of preference of the product users for the product is greater than the standard degree of preference, the corresponding product users are marked as a type of user.

[0067] If the user's preference for the product is less than the standard preference level, the corresponding user will be marked as a second-class user.

[0068] We analyze the proportions of Category 1 and Category 2 users among all users applicable to the product, and then input these proportions into a convolutional neural network to make preliminary predictions of product demand, thus obtaining the preliminary demand for the product.

[0069] It should be noted that since different people may have different levels of preference for different products, market research is necessary before selling the product to understand the different levels of user preferences and to determine the demand for the product based on these preferences. The target audience for each product also varies; for example, razors are suitable for adult men. Market research questionnaires are sent to suitable users to understand their level of preference for the product, and users are divided into two categories based on their level of preference. Category 1 users have a higher level of preference and are likely to purchase the product directly; Category 2 users have a lower level of preference and are unlikely to purchase the product directly. Based on the proportion of Category 1 and Category 2 users, the approximate demand for the product can be preliminarily predicted, i.e., the initial demand for the product. This invention can obtain the initial demand for a product by analyzing the level of preference of different target users.

[0070] Furthermore, in a preferred embodiment of the present invention, the step of classifying goods based on their sales period and performing supply forecasting analysis on the classified goods based on the initial demand to obtain the total quantity of goods specifically involves:

[0071] Determine if a product has a sales period. If so, define the product as a limited-time sale product; otherwise, define the product as a continuously sellable product.

[0072] If the product is a limited-time sale item, then retrieve the current inventory of the limited-time sale item from the product warehouse;

[0073] Compare the initial demand for the limited-time sale item with the current inventory. If the initial demand for the limited-time sale item is greater than the current inventory, then the current inventory of the limited-time sale item is taken as the supply of the limited-time sale item and defined as the first item supply.

[0074] If the initial demand for a limited-time sale item is less than the current inventory, the historical demand for the limited-time sale item will be retrieved based on historical data, and the historical demand for the item with the highest similarity to the limited-time sale item will be retrieved through a big data network.

[0075] By combining the historical demand for limited-time sale items with the historical demand for items most similar in nature to limited-time sale items, a first predictive analysis result is obtained. Based on the first predictive analysis result, a second commodity supply quantity is obtained.

[0076] If the product is a continuously sold product, the historical demand for continuously sold products is obtained, and the supply of continuously sold products is determined based on the historical demand for continuously sold products, which is defined as the supply of the third product.

[0077] By combining the supply quantities of the first, second, and third commodities, the total quantity of commodities is obtained.

[0078] It's important to note that different products have different sales periods. Some products are sold for a limited time due to promotions or limited raw materials, while others are always available. Therefore, products are categorized into limited-time and continuously sold items. User demand for limited-time and continuously sold items may differ. For example, for limited-time sold items, inventory levels need to be considered. If initial demand exceeds inventory, it indicates a supply shortage, and the current inventory level must be used as the supply. If initial demand exceeds inventory, it means the inventory meets initial user demand. In this case, historical sales data and the sales data of similar products need to be analyzed. Historical sales data and the sales data of similar products can be used as reference points, combined with the initial demand for a comprehensive analysis and prediction. For example, convolutional neural network models can be used to calculate the supply when the initial demand for a limited-time sold item exceeds the inventory. For continuously sold items, the supply is directly determined by historical demand. Finally, all factors are combined to obtain the total quantity of goods. This invention can obtain the total quantity of goods by analyzing the demand for limited-time and continuously sold goods.

[0079] Furthermore, in a preferred embodiment of the present invention, the analysis of changes in commodity inventory and foot traffic at different commodity distribution points, and the allocation of commodity supply to different commodity distribution points based on the analysis results, specifically includes:

[0080] Identify product distribution points and, based on historical data, obtain the average foot traffic around the product distribution points, and preset the standard foot traffic.

[0081] If the average foot traffic around a product distribution point is greater than the standard foot traffic, the corresponding product distribution point will be designated as the first product distribution point; if the average foot traffic around a product distribution point is less than the standard foot traffic, the corresponding product distribution point will be designated as the second product distribution point.

[0082] Obtain the historical inventory change rate of all product distribution points, and classify and optimize the first and second product distribution points based on the historical inventory change rate of product distribution points to obtain popular product distribution points and ordinary product distribution points;

[0083] Get the supply status of the product and the percentage of popular product distribution points among all product distribution points. If the percentage of popular product distribution points among all product distribution points is greater than a preset value, the supply status of the product is defined as the first supply status of the product. If the percentage of popular product distribution points among all product distribution points is less than a preset value, the supply status of the product is defined as the second supply status of the product.

[0084] If the supply status of the goods is in the first supply status, then the total amount of goods will be supplied evenly to different popular goods distribution points so that the supply of goods at different popular goods distribution points is the same.

[0085] If the supply status of the goods is in the second supply status, the total amount of goods will be supplied to all distribution points. The supply of goods will be allocated among different distribution points based on the historical inventory change rate of the distribution points, so that all distribution points have goods to sell.

[0086] It should be noted that a product distribution point is a place where goods are sold. Due to various factors, the quantity of goods sold varies at different distribution points. In areas with high foot traffic, such as supermarkets, or at distribution points where inventory changes rapidly, a larger supply of goods is required. Conversely, in areas with lower foot traffic, such as convenience stores, or at distribution points where inventory changes slowly, a smaller supply of goods is required. Therefore, a comprehensive analysis of foot traffic and historical inventory change rates is conducted at each distribution point. Based on the analysis results, distribution points are categorized into popular and ordinary product distribution points. Since popular product distribution points have higher sales rates and volumes, it is necessary to determine their proportion among all distribution points. If this proportion exceeds a preset value, a first-tier supply state is established. Under this first-tier supply state, all goods are directly and evenly distributed among popular product distribution points to maximize product profits. If the proportion is less than a preset value, a second supply state for the goods is generated. In this second supply state, the supply of goods is allocated based on the historical inventory change rate of the distribution points, i.e., the historical sales situation of the goods at the distribution points. The higher the historical inventory change rate of the distribution points, the higher the supply of goods. Finally, goods are sold at the distribution points corresponding to both the first and second supply states.

[0087] Figure 2 A flowchart illustrating a method for obtaining the optimal route for goods transportation and the final goods loading plan is shown, including the following steps:

[0088] S202: Based on the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes, a comprehensive analysis is conducted to obtain the optimal route for commodity transportation;

[0089] S204: Analyze the supply status of goods and the specifications of goods transport vehicles to obtain various goods loading schemes, as well as all feasible goods loading schemes for goods transport vehicles;

[0090] S206: Calculate the similarity between all feasible loading schemes for the goods transport vehicle and various goods loading schemes, and obtain the final goods loading scheme based on the similarity score.

[0091] Furthermore, in a preferred embodiment of the present invention, the step of comprehensively analyzing the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal commodity transportation route specifically involves:

[0092] Obtain the coordinate information of different product distribution points, and import the coordinate information of the different product distribution points into map software to construct a product distribution point distribution map;

[0093] In the distribution map of the product distribution points, the Dijkstra algorithm is introduced to calculate the shortest path length between different product distribution points. Based on the shortest path length between different product distribution points, similar product distribution points are generated. The similar product distribution points contain several product distribution points, and the shortest path height between any two product distribution points in the similar product distribution points is less than a preset value.

[0094] Obtain the coordinate information of the commodity warehouse, and based on the coordinate information of the commodity warehouse and the distribution map of commodity distribution points, obtain all routes from the commodity warehouse to different commodity distribution points of the same type of commodity distribution points, and define them as a type of transportation route;

[0095] The transportation cost and route length of all routes in a class of transportation routes are obtained. A genetic algorithm is then introduced to iteratively calculate the transportation cost and route length of all routes in the class of transportation routes, as well as the shortest path length between different distribution points of the same type of goods, to obtain the optimal route for goods transportation.

[0096] It should be noted that goods need to be transported from the warehouse to distribution points. To ensure faster and lower-cost transportation, routes need to be planned to obtain the optimal routes for goods transportation. A distribution point distribution map is obtained, marking the specific locations of the distribution points and surrounding road conditions. The Dijkstra algorithm is an algorithm that can solve the single-source shortest path problem in a graph, calculating the shortest path length between different distribution points on the distribution map. Distribution points of the same type may include multiple distribution points. The shortest path lengths between different distribution points of the same type are all less than preset values. The goal is to ensure that the same batch of goods transport vehicles can deliver goods to multiple distribution points with the minimum transportation cost and shortest distance after a single transport, and that the goods at the distribution points of the same type all originate from the same batch of goods transport vehicles. When a goods transport vehicle departs from the same warehouse, it must first select any one of the distribution points for the same type of goods as its first destination. It must also consider the transportation costs and route lengths in subsequent transport to ensure the goods are transported with the lowest cost, shortest route, and highest efficiency. The transportation costs include various expenses such as fuel and labor costs, as well as time costs incurred en route. A genetic algorithm is an algorithm that can find the optimal or near-optimal solution to a problem. By combining all the above factors and performing iterative calculations, a genetic algorithm can obtain the optimal goods transport route from a set of transport routes. This invention can generate the optimal goods transport route by comprehensively analyzing the distribution map of goods distribution points, the transportation costs of all transport routes, and their lengths.

[0097] Furthermore, in a preferred embodiment of the present invention, the step of calculating the similarity between all feasible cargo loading schemes of the cargo transport vehicle and various cargo loading schemes, and obtaining the final cargo loading scheme based on the similarity score, specifically involves:

[0098] Calculate the similarity between the feasible loading schemes of the goods transport vehicle and various goods loading schemes. Define the goods loading schemes whose similarity to the feasible loading schemes of a class of goods transport vehicles is greater than a preset value as usable goods loading schemes.

[0099] Calculate the number of goods transport vehicles required under different available goods loading schemes, and define the available goods loading scheme with the fewest required goods transport vehicles as the final goods loading scheme;

[0100] If there are several available goods loading schemes that require the fewest and the same number of goods transport vehicles, then the loading speed of the available goods loading schemes is predicted, and the available goods loading scheme with the fastest loading speed is defined as the final goods loading scheme.

[0101] It should be noted that the feasible loading scheme for the goods transport vehicle refers to the loading scheme that can be implemented in this type of goods transport vehicle. However, since various goods may vary in size and shape, there are multiple loading schemes. The similarity between the feasible loading scheme and various other loading schemes is calculated. A high similarity indicates that the loading scheme is feasible in the goods transport vehicle. After obtaining the available loading schemes, it is necessary to determine the number of goods transport vehicles required for different available loading schemes. Because the arrangement of goods differs under different loading schemes, the number of goods transport vehicles required may also differ. The fewer the number of goods transport vehicles, the lower the transportation cost. The loading scheme with the fewest goods transport vehicles is selected as the final loading scheme output. If multiple loading schemes use the same number of goods transport vehicles, the loading speed of the goods under different loading schemes is determined. The faster the loading speed, the higher the transportation efficiency. The available loading scheme with the fastest loading speed is defined as the final loading scheme and output. This invention can analyze different goods loading schemes, including their feasibility, the number of goods transport vehicles used, and the loading speed, to obtain the final loading scheme.

[0102] Furthermore, the aforementioned IoT-based commodity inventory distribution management method also includes the following steps:

[0103] Based on the final goods loading plan, goods are loaded onto the goods transport vehicle, and the goods transport vehicle loaded with goods is designated as a goods loading transport vehicle. Temperature sensors and vibration sensors are installed inside the goods loading transport vehicle.

[0104] The system controls the goods loading and transport vehicle to transport goods according to the optimal route. During the transportation process, the internal temperature of the goods loading and transport vehicle is obtained in real time through the temperature sensor, and the continuous vibration rate of the goods loading and transport vehicle is obtained in real time through the vibration sensor.

[0105] Determine if the internal temperature of the goods loading and transport vehicle is greater than the preset value. If not, control the goods loading and transport vehicle to continue transporting goods according to the optimal goods transportation route.

[0106] If so, the internal temperature of the goods loading and transport vehicle will be actively cooled to maintain the internal temperature of the goods loading and transport vehicle within the preset range.

[0107] The system determines the continuous vibration rate of the goods loading and transport vehicle. If the vibration rate of the goods loading and transport vehicle is greater than a preset value, the system obtains the speed range that makes the continuous vibration rate of the goods loading and transport vehicle less than the preset value, defines it as the safe speed range, and controls the speed of the goods loading and transport vehicle to be maintained within the safe speed range.

[0108] It is important to note that goods transport vehicles must ensure the integrity of the goods during transport. For example, fresh produce or fruits require low-temperature storage and transportation to prevent spoilage; excessively high temperatures will affect the quality of the goods. Certain fragile goods, such as porcelain lamps, may be damaged if the transport vehicle experiences excessive continuous vibration during transport. Therefore, it is necessary to obtain the internal temperature and continuous vibration rate of the transport vehicle and to address those that do not meet the requirements. Active cooling of the internal temperature of the transport vehicle includes using air conditioning or ventilation. While transport vehicles inevitably experience bumps along optimal routes, excessive speed increases the rate of bumps, i.e., the continuous vibration rate, which is detrimental to the preservation of the goods. Establishing a safe speed range, allowing the transport vehicle to operate within this range, effectively protects the integrity of the goods and improves economic efficiency.

[0109] like Figure 3 As shown, a second aspect of the present invention also provides a commodity inventory distribution management system based on the Internet of Things. The commodity inventory distribution management system includes a memory 31 and a processor 32. The memory 31 stores a commodity inventory distribution management method. When the commodity inventory distribution management method is executed by the processor 32, it implements the following steps:

[0110] Obtain the degree of preference of the target users for the product, analyze the degree of preference of the target users for the product, and obtain the preliminary demand for the product based on the analysis results;

[0111] Based on the sales period of the goods, the goods are classified, and the supply of the classified goods is predicted and analyzed based on the initial demand of the goods to obtain the total quantity of goods.

[0112] The study analyzes the changes in commodity inventory and foot traffic at different commodity distribution points, and allocates commodity supply to different commodity distribution points based on the analysis results.

[0113] Construct a distribution map of commodity distribution points and obtain the transportation costs and route lengths of all transportation routes. Conduct a comprehensive analysis of the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal route for commodity transportation.

[0114] The supply status and nature of the goods are analyzed, and the final loading plan for the goods transport vehicle is determined based on the analysis results.

[0115] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A commodity inventory distribution management method based on the Internet of Things, characterized in that, Includes the following steps: Obtain the degree of preference of the target users for the product, analyze the degree of preference of the target users for the product, and obtain the preliminary demand for the product based on the analysis results; Based on the sales period of the goods, the goods are classified, and the supply of the classified goods is predicted and analyzed based on the initial demand of the goods to obtain the total quantity of goods. The study analyzes the changes in commodity inventory and foot traffic at different commodity distribution points, and allocates commodity supply to different commodity distribution points based on the analysis results. Construct a distribution map of commodity distribution points and obtain the transportation costs and route lengths of all transportation routes. Conduct a comprehensive analysis of the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal route for commodity transportation. The supply status and nature of the goods are analyzed, and the final loading plan for the goods transport vehicle is determined based on the analysis results.

2. The commodity inventory distribution management method based on the Internet of Things as described in claim 1, characterized in that, The process involves obtaining the degree of user preference for the product, analyzing this preference, and determining the initial demand for the product based on the analysis results. Specifically: The properties of the product are obtained, and based on these properties, applicable user analysis and prediction are performed in a big data network to obtain the applicable users of the product. Create a market research questionnaire about the product, push the questionnaire to the devices of users who are interested in the product through a big data network, and collect the survey data of different users who are interested in the product, which is defined as product research data. Based on the product survey data, the degree of preference of different product users for the product is obtained, and a standard degree of preference is preset. If the degree of preference of the product users for the product is greater than the standard degree of preference, the corresponding product users are marked as a type of user. If the user's preference for the product is less than the standard preference level, the corresponding user will be marked as a second-class user. We analyze the proportions of Category 1 and Category 2 users among all users applicable to the product, and then input these proportions into a convolutional neural network to make preliminary predictions of product demand, thus obtaining the preliminary demand for the product.

3. The commodity inventory distribution management method based on the Internet of Things as described in claim 1, characterized in that, The process involves classifying goods based on their sales period and then performing supply forecasting analysis on the classified goods based on the initial demand to obtain the total quantity of goods. Specifically: Determine if a product has a sales period. If so, define the product as a limited-time sale product; otherwise, define the product as a continuously sellable product. If the product is a limited-time sale item, then retrieve the current inventory of the limited-time sale item from the product warehouse; Compare the initial demand for the limited-time sale item with the current inventory. If the initial demand for the limited-time sale item is greater than the current inventory, then the current inventory of the limited-time sale item is taken as the supply of the limited-time sale item and defined as the first item supply. If the initial demand for a limited-time sale item is less than the current inventory, the historical demand for the limited-time sale item will be retrieved based on historical data, and the historical demand for the item with the highest similarity to the limited-time sale item will be retrieved through a big data network. By combining the historical demand for limited-time sale items with the historical demand for items most similar in nature to limited-time sale items, a first predictive analysis result is obtained. Based on the first predictive analysis result, a second commodity supply quantity is obtained. If the product is a continuously sold product, the historical demand for continuously sold products is obtained, and the supply of continuously sold products is determined based on the historical demand for continuously sold products, which is defined as the supply of the third product. By combining the supply quantities of the first, second, and third commodities, the total supply of commodities is obtained.

4. The commodity inventory distribution management method based on the Internet of Things as described in claim 1, characterized in that, The analysis of inventory changes and foot traffic at different distribution points, and the allocation of product supply to different distribution points based on the analysis results, specifically involves: Identify product distribution points and, based on historical data, obtain the average foot traffic around the product distribution points, and preset the standard foot traffic. If the average foot traffic around a product distribution point is greater than the standard foot traffic, the corresponding product distribution point will be designated as the first product distribution point; if the average foot traffic around a product distribution point is less than the standard foot traffic, the corresponding product distribution point will be designated as the second product distribution point. Obtain the historical inventory change rate of all product distribution points, and classify and optimize the first and second product distribution points based on the historical inventory change rate of product distribution points to obtain popular product distribution points and ordinary product distribution points; Get the supply status of the product and the percentage of popular product distribution points among all product distribution points. If the percentage of popular product distribution points among all product distribution points is greater than a preset value, the supply status of the product is defined as the first supply status of the product. If the percentage of popular product distribution points among all product distribution points is less than a preset value, the supply status of the product is defined as the second supply status of the product. If the supply status of the goods is in the first supply status, then the total amount of goods will be supplied evenly to different popular goods distribution points so that the supply of goods at different popular goods distribution points is the same. If the supply status of the goods is in the second supply status, the total amount of goods will be supplied to all distribution points. The supply of goods will be allocated among different distribution points based on the historical inventory change rate of the distribution points, so that all distribution points have goods to sell.

5. The commodity inventory distribution management method based on the Internet of Things as described in claim 1, characterized in that, The process involves constructing a distribution map of product distribution points, obtaining the transportation costs and route lengths of all transportation routes, and conducting a comprehensive analysis of the distribution map, transportation costs, and route lengths to determine the optimal transportation route for the goods. Specifically: Obtain the coordinate information of different product distribution points, and import the coordinate information of the different product distribution points into map software to construct a product distribution point distribution map; In the distribution map of the product distribution points, the Dijkstra algorithm is introduced to calculate the shortest path length between different product distribution points. Based on the shortest path length between different product distribution points, similar product distribution points are generated. The similar product distribution points contain several product distribution points, and the shortest path height between any two product distribution points in the similar product distribution points is less than a preset value. Obtain the coordinate information of the commodity warehouse, and based on the coordinate information of the commodity warehouse and the distribution map of commodity distribution points, obtain all routes from the commodity warehouse to different commodity distribution points of the same type of commodity distribution points, and define them as a type of transportation route; The transportation cost and route length of all routes in a class of transportation routes are obtained. A genetic algorithm is then introduced to iteratively calculate the transportation cost and route length of all routes in the class of transportation routes, as well as the shortest path length between different distribution points of the same type of goods, to obtain the optimal route for goods transportation.

6. The commodity inventory distribution management method based on the Internet of Things as described in claim 1, characterized in that, The analysis of the supply status and nature of the goods, and the determination of the final goods loading plan for the goods transport vehicle based on the analysis results, specifically includes: Based on the supply status of the goods, obtain the supply volume of goods at different distribution points, and based on the supply volume of goods at different distribution points, obtain the total supply volume of goods at distribution points of the same type of goods; The total supply and nature of goods at similar distribution points are imported into a big data network for retrieval, generating various goods loading schemes. Obtain the specifications of the goods transport vehicle, and based on the specifications of the goods transport vehicle, obtain all feasible loading schemes for the goods transport vehicle; Calculate the similarity between the feasible loading schemes of the goods transport vehicle and various goods loading schemes. Define the goods loading schemes whose similarity to the feasible loading schemes of a class of goods transport vehicles is greater than a preset value as usable goods loading schemes. Calculate the number of goods transport vehicles required under different available goods loading schemes, and define the available goods loading scheme with the fewest required goods transport vehicles as the final goods loading scheme; If there are several available goods loading schemes that require the fewest and the same number of goods transport vehicles, then the loading speed of the available goods loading schemes is predicted, and the available goods loading scheme with the fastest loading speed is defined as the final goods loading scheme.

7. A commodity inventory and distribution management system based on the Internet of Things, characterized in that, The commodity inventory distribution management system includes a memory and a processor. The memory stores a commodity inventory distribution management method. When the commodity inventory distribution management method is executed by the processor, it performs the following steps: Obtain the degree of preference of the target users for the product, analyze the degree of preference of the target users for the product, and obtain the preliminary demand for the product based on the analysis results; Based on the sales period of the goods, the goods are classified, and the supply of the classified goods is predicted and analyzed based on the initial demand of the goods to obtain the total quantity of goods. The study analyzes the changes in commodity inventory and foot traffic at different commodity distribution points, and allocates commodity supply to different commodity distribution points based on the analysis results. Construct a distribution map of commodity distribution points and obtain the transportation costs and route lengths of all transportation routes. Conduct a comprehensive analysis of the distribution map of commodity distribution points, the transportation costs and route lengths of all transportation routes to obtain the optimal route for commodity transportation. The supply status and nature of the goods are analyzed, and the final loading plan for the goods transport vehicle is determined based on the analysis results.

Images