Intelligent matching method for distribution rural power grid protocol inventory
By building an inventory matching model, combining historical demand data and inventory deviation rate, optimizing inventory volume and distribution paths, the problem of mismatch between protocol inventory and actual demand is solved, and efficient inventory management and low-cost distribution in the supply chain are achieved.
Patent Information
- Application Number
- CN202411378062.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2025-06-06
AI Technical Summary
In the prior art, the agreement inventory does not match the actual demand, resulting in low cost efficiency of supply chain, complex inventory management, high transportation costs and increased risk of power and material loss.
By obtaining the historical demand data of the project unit, predicting demand data; obtaining the inventory and consumption of suppliers, and calculating supply inventory data; combining the predicted demand data and inventory deviation rate, a inventory matching model is built based on greedy algorithms and machine learning algorithms, optimizing inventory and distribution paths, improving resource utilization and reducing distribution costs.
It achieves accurate matching of inventory and demand, optimizes inventory management and distribution efficiency of the supply chain, reduces costs and risks, and improves resource utilization.
Smart Images
Figure CN120106726A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of inventory optimization and matching, and more specifically, to a method for intelligent matching of inventory in a distribution network protocol for farmers. Background Art
[0002] The agreement inventory procurement method will rely on the State Grid Corporation's e-commerce platform. The provincial power company will classify and summarize the required materials based on the material demand forecast of the material demand unit in a certain period of time in the future, apply unified material coding and technical specifications, determine the supplier through bidding or other procurement methods, and sign a framework procurement agreement with them; after the specific material demand application is generated, the supplier will be directly assigned according to the agreement, thereby shortening the procurement and supply cycle and gaining time for project construction; the procurement application for the agreement inventory is divided into two stages: demand forecast and actual demand. The demand forecast is only used as the basis for signing the framework agreement. After the agreement inventory is tendered, each demand unit establishes procurement demand based on the project in the ERP system. After review, the provincial company uniformly assigns suppliers and signs supply contracts.
[0003] Deficiencies of existing technologies: In the prior art, the mismatch between the agreed inventory and the actual demand will lead to many problems. Mismatched demand data and supply inventory will affect the cost efficiency of the supply chain. Excessive inventory requires additional storage and management costs, which will also increase the cost of capital occupation. Insufficient inventory may lead to urgent orders and emergency transportation, increasing transportation costs and handling fees. The power material supply chain often involves a large geographical area, including large distances between warehouses and project units. Long-distance distribution not only increases transportation costs, but may also lead to delays and risks of power material loss. Therefore, by optimizing the inventory ratio and distribution efficiency in the supply chain, the resource utilization of the distribution network for farmers can be improved, and the distribution cost of the distribution network for farmers can be reduced.
[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention
[0005] In order to overcome the above defects of the prior art, an embodiment of the present invention provides an intelligent matching method for inventory in a supply network agreement for agricultural products, and solves the problems raised in the above background technology through the intelligent matching method for inventory in a supply network agreement for agricultural products.
[0006] To achieve the above object, the present invention provides the following technical solutions: The intelligent matching method of the inventory of the distribution network for farmers includes: obtaining the historical demand data of the project unit for power materials, performing data analysis based on the historical demand data, and obtaining the predicted demand data; obtaining the inventory of the supplier and the consumption of the project unit, obtaining the supply inventory data according to the difference between the inventory and the consumption, and comparing it with the predicted demand data to obtain the inventory deviation rate; obtaining the location of the demand node and the supply node, and obtaining the distribution optimization data based on the greedy algorithm in combination with the predicted demand data; combining the inventory deviation rate with the distribution optimization data, building an inventory matching model based on the machine learning algorithm, and optimizing the distribution network for farmers according to the inventory matching model.
[0007] In a preferred embodiment, the specific method for obtaining the predicted demand data is as follows: collect historical demand data of each project unit within a preset period, add the historical demand data of the demanders to obtain total demand data, and calculate the arithmetic mean of the total demand data within multiple periods to obtain predicted demand data.
[0008] In a preferred embodiment, the specific method for obtaining the supply inventory data is as follows: collect the basic production data of the supply chain within a time period, including the total time and output per unit time, and calculate the total output; obtain the initial inventory quantity and consumption, add the initial inventory quantity and the total output to obtain the inventory quantity, and subtract the inventory quantity from the consumption to obtain the supply inventory data.
[0009] In a preferred embodiment, the specific method for obtaining the inventory deviation rate is as follows: based on the supply inventory data and the forecast demand data, the difference between the supplier's supply inventory data and the forecast demand data is calculated, and the calculated difference is divided by the forecast demand data to obtain the inventory deviation rate.
[0010] In a preferred embodiment, the specific steps of optimizing the agricultural distribution network according to the inventory matching model are as follows: optimize the ratio of the difference between inventory and consumption to the predicted demand data through the inventory deviation rate in the inventory matching model. When the inventory deviation rate is a positive number, the supply inventory data is greater than the predicted demand data, and the production volume needs to be reduced; when the inventory deviation rate is a negative number, the supply inventory data is less than the predicted demand data, and the production volume needs to be increased; when the inventory deviation rate is zero, the supply inventory data is equal to the predicted demand data, and there is no need to change the production volume; optimize the distribution distance between the supply node and the demand node and the packaging matching degree between the transport container and the actual volume of the power materials through the distribution optimization data in the inventory matching model.
[0011] In a preferred embodiment, the distribution optimization data includes the total distribution distance and the packaging matching degree; the specific method for obtaining the total distribution distance is as follows: obtain the shortest distance from the supply node to each demand node, and then use a greedy algorithm based on the local optimal principle to sum up the shortest distances to calculate the total distribution distance.
[0012] In a preferred embodiment, the specific method for obtaining the packaging matching degree is as follows: obtaining the actual volume of the power material and the volume of the transport container, and dividing the actual volume of the power material and the volume of the transport container to calculate the packaging matching degree. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 This is a structural schematic diagram of the intelligent matching method for the agricultural network protocol inventory of the present invention. DETAILED DESCRIPTION
[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0015] Embodiment 1, Figure 1 A structural schematic diagram of the intelligent matching method for the inventory of the agricultural distribution network protocol of the present invention is given; S10, obtaining historical demand data of the project unit for electric power materials, performing data analysis based on the historical demand data, and obtaining predicted demand data; The specific method for obtaining the forecast demand data is as follows: First collect Historical demand data for power materials by project units within a time period , the historical demand data includes The demand data of each node is calculated The arithmetic mean of the historical demand data is the predicted demand data; The specific calculation formula for forecasting demand data is as follows:
[0016] In the formula, is the forecast demand data, is the historical demand data, where , and is a positive integer; Obtaining the project unit's forecast demand data for power materials plays an important role in supply chain management, mainly in the following aspects: Optimize inventory management: Forecast demand data helps optimize the inventory management strategy of power materials. Based on the forecast data, suppliers can reasonably adjust inventory levels to avoid increasing storage costs due to excessive inventory or not meeting project unit demand due to insufficient inventory. Through accurate forecasting, inventory levels can be more adaptable to fluctuations in project unit demand. Reduce supply chain risks: Forecasting demand data can help suppliers reduce risks in supply chain management. By predicting project unit demand, suppliers can adjust supply plans and procurement strategies in a timely manner to reduce economic losses and business risks caused by demand fluctuations. Improve production efficiency: With accurate forecast demand data, suppliers can plan and utilize production resources more effectively, improve production efficiency, thereby reducing production costs and improving economic benefits; Enhance project unit satisfaction: Forecasting demand data helps to better understand the project unit's demand for power materials, thereby providing power materials that better meet the needs of the project unit. Through personalized positioning and design, the project unit's satisfaction can be enhanced; The specific calculation formula for historical demand data is as follows:
[0017] In the formula, is the historical demand data, is the demand data of each node, where , and is a positive integer; Obtaining historical demand data of project units plays an important role in the management and optimization of the industry, which is mainly reflected in the following aspects: Demand forecasting: Historical demand data can help predict future demand trends and changes for project units. By analyzing data, order volumes, and feedback from the past few years, seasonal changes and preferences for power materials can be discovered. These data can provide a basis for supply chain production planning, inventory management, and promotion strategies, thereby meeting demand more accurately. Optimize inventory management: Historical demand data is an important basis for optimizing inventory management. Understanding the fluctuations in demand in different seasons or time periods can help the supply chain make reasonable adjustments between demand peaks and troughs, thus avoiding increased storage costs due to excessive inventory backlogs or unmet unit demand for items due to insufficient inventory. Improve supply chain efficiency: By analyzing historical demand data, we can optimize the logistics and distribution processes in the supply chain, understand the demand and distribution of project units in different time periods, optimize the transportation routes and distribution plans of goods, reduce transportation time and costs, and improve the punctuality and efficiency of distribution; Support decision-making: Historical demand data provides strong support for supply chain decision-making. Based on data analysis, more accurate promotion strategies, supply plans and procurement strategies can be formulated. These decisions can not only reduce risks, but also improve resource utilization efficiency and enhance suppliers' ability to adapt to changes in demand. S20, obtaining the inventory of the supplier and the consumption of the project unit, obtaining the supply inventory data according to the difference between the inventory and the consumption, and comparing with the forecast demand data to obtain the inventory deviation rate; The specific method for obtaining the supply inventory data is as follows: First, collect the basic production data of the supply chain in the same time period, including total time and unit time output, and calculate the total output; obtain the initial inventory quantity and consumption, add the initial inventory quantity and total output to get the inventory quantity, and combine it with the consumption to generate the supply inventory data; The specific calculation formula for supply inventory data is as follows:
[0018] In the formula, is the supply inventory data, is the initial inventory quantity, is the total output, is the consumption;
[0019] In the formula, is the total output, is the output per unit time, is the total time; The specific method for obtaining the inventory deviation rate is as follows: First, the difference between the supply inventory data and the forecast demand data of the supply chain is calculated, and the inventory deviation rate is obtained by dividing the difference with the forecast demand data; The specific calculation formula for inventory deviation rate is as follows:
[0020] In the formula, is the inventory deviation rate, is the supply inventory data, It is the forecast demand data; The calculation of this inventory deviation rate can help decision makers and supply chain managers evaluate and understand the current supply situation of the supply chain. The following is the role of analyzing the inventory deviation rate in the supply chain supply situation: Evaluate the supply-demand balance: The inventory deviation rate can be used to understand the degree of difference between actual supply and expected demand; Optimize production and supply plans: Based on the inventory deviation rate, decision makers can adjust production plans and supply strategies to better meet demand and avoid risks and losses caused by supply-demand imbalance; Forecasting and strategy formulation: Accurate inventory deviation rates can provide a basis for demand forecasting and strategy formulation to more effectively respond to demand fluctuations and changes; S30, obtaining the locations of the demand nodes and the supply nodes, and obtaining the distribution optimization data based on the greedy algorithm in combination with the predicted demand data; The delivery optimization data includes the total delivery distance and the packaging matching degree, wherein the specific calculation formula of the delivery optimization data is as follows:
[0021] In the formula, It is the delivery optimization data. is the total delivery distance, It is the packing matching degree; The total delivery distance The specific method of obtaining is as follows: First, the shortest distance from the supply node to each demand node is obtained, and then the greedy algorithm is used based on the local optimal principle to sum up the shortest distances and calculate the total delivery distance; Total delivery distance The specific calculation formula is as follows:
[0022] In the formula, is the shortest distance from the supply node to each demand node; The implementation process of the greedy algorithm is as follows: The shortest distance from the supply node to each demand node is selected according to the greedy strategy. Based on the principle that the local optimal solution can lead to the global optimal solution, the shortest distances are summed to calculate the total delivery distance. Obtaining the total delivery distance of the supply chain is one of the important indicators for evaluating and optimizing supply chain efficiency. It has the following important functions for supply chain management: Cost control and efficiency optimization: The total delivery distance directly affects the transportation cost. By reducing the delivery distance, the transportation cost can be reduced and the overall efficiency and competitiveness of the supply chain can be improved. Optimizing the delivery distance means more effective planning of logistics routes and transportation modes, reducing empty mileage and energy consumption, and thus reducing delivery costs; Reduce environmental impact: Shorter delivery distances can reduce carbon dioxide emissions and other environmental impacts during transportation, which is in line with modern society's requirements for sustainable development and environmental protection, and helps the supply chain achieve a more environmentally friendly and sustainable operating model; Risk management: Long-distance delivery may face more risks, such as transportation delays, cargo damage or loss. By controlling the total delivery distance, these potential risks can be reduced and the reliability and stability of the supply chain can be improved; The packaging matching The specific method of obtaining is as follows: Obtain the actual volume of the power materials and the volume of the transport container, and divide the actual volume of the power materials by the volume of the transport container to calculate the packaging matching degree; The specific calculation formula for the packaging matching degree is as follows:
[0023] In the formula, is the packing matching degree, is the actual volume of the electrical material, is the volume of the shipping container.
[0024] The packaging matching degree of the supply chain is very important in supply chain management and has a significant impact on improving operational efficiency. Its functions include the following aspects: Reduce space waste: Reasonable packaging matching can reduce space waste during transportation. By reasonably combining power materials of different sizes and shapes, the space of the transport container can be maximized and the transportation cost can be reduced; Improve transportation efficiency: Reasonable packaging and matching can improve transportation efficiency. By tightly combining power materials in the transport container and reducing unnecessary gaps, the frequency and number of times during transportation can be reduced, thereby saving time and energy consumption; Reduce transportation risks: Appropriate packaging and matching can reduce risks during transportation. Considering the stability and anti-extrusion ability of power materials when packaging can reduce damage and loss caused by friction or extrusion during transportation; Optimize warehousing and distribution processes: Reasonable packaging matching can simplify the warehousing and distribution processes. By unifying packaging standards and optimizing packing solutions, the complexity of warehousing management can be reduced, loading and unloading efficiency can be improved, and operational errors and costs can be reduced; S40, combining the inventory deviation rate with the distribution optimization data, building an inventory matching model based on the machine learning algorithm, and optimizing the distribution network according to the inventory matching model; The specific calculation formula of the inventory matching model is as follows:
[0025] In the formula, is the inventory deviation rate, is the supply inventory data, is the forecast demand data, It is the delivery optimization data. is the packing matching degree, is the total delivery distance; The ratio of the difference between inventory and consumption to the predicted demand data is optimized through the inventory deviation rate in the inventory matching model. When the inventory deviation rate is positive, the supply inventory data is greater than the predicted demand data, and the production volume needs to be reduced; when the inventory deviation rate is negative, the supply inventory data is less than the predicted demand data, and the production volume needs to be increased; when the inventory deviation rate is zero, the supply inventory data is equal to the predicted demand data, and the production volume does not need to be changed; the distribution distance between the supply node and the demand node and the packaging matching degree between the transport container and the actual volume of the power materials are optimized through the distribution optimization data in the inventory matching model; Explore the role of building an inventory matching model based on a machine learning algorithm, which uses inventory deviation rate and distribution optimization data to generate inventory matching coefficients. The role of this model can be reflected in the following aspects: 1. Inventory optimization and management The inventory matching model can more accurately match the difference between actual inventory and expected demand. Specifically: Real-time inventory management: The model can dynamically adjust inventory levels based on actual inventory deviation rates and distribution optimization data, and decide whether to adjust procurement volume or supply strategy to ensure that inventory is in an optimal state, neither too high to waste nor too low to cause insufficient supply; Reduce inventory costs: Through accurate inventory matching, it is possible to reduce capital occupation and inventory costs caused by excessive inventory, while avoiding the unmet demand of project units due to insufficient inventory; 2. Improve supply chain responsiveness Inventory matching models can improve supply chain flexibility and responsiveness: Timely supply adjustment: Based on the model, supply chain managers can adjust production plans and distribution strategies in a timely manner to respond to changes in demand. This flexibility can effectively reduce the impact of supply chain delays and fluctuations; Predictive maintenance: The model can not only respond to current demand, but also predict future inventory needs based on historical data and trends, so as to allocate resources and prepare in advance, improving the efficiency and stability of the supply chain; 3. Improve demand unit satisfaction By accurately matching inventory, suppliers can better meet the needs of project units, improve service quality and project unit satisfaction: On-time delivery: Optimized inventory matching can ensure timely delivery of materials, thereby enhancing the project unit's trust in suppliers; 4. Data-driven decision support Finally, the inventory matching model is built on machine learning algorithms and is not just a forecasting tool, but can also provide data-driven decision support: Intelligent decision-making: Through the model, managers can make more accurate and rational decisions to maximize benefits and resource utilization; Continuous optimization: Models can be continuously optimized and learned through feedback loops, improving prediction accuracy and decision-making effectiveness over time.
[0026] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0027] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.
[0028] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0029] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0030] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0031] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. The intelligent matching method of the agricultural network agreement inventory is characterized by: The following steps are involved: Obtain the historical demand data of the project unit for power materials, perform data analysis based on the historical demand data, and obtain the predicted demand data; Obtain the supplier's inventory and the project unit's consumption, obtain the supply inventory data based on the difference between the inventory and consumption, and compare it with the forecast demand data to obtain the inventory deviation rate; Obtain the locations of demand nodes and supply nodes, and obtain distribution optimization data based on the greedy algorithm in combination with the predicted demand data; The inventory deviation rate is combined with distribution optimization data, and an inventory matching model is built based on the machine learning algorithm. The agricultural distribution network is optimized according to the inventory matching model.
2. According to claim 1, the method for intelligent matching of agricultural network agreement inventory is characterized in that: The specific method for obtaining the forecast demand data is as follows: Collect the historical demand data of each project unit within the preset period, add up the historical demand data of the demanders to get the total demand data, and calculate the arithmetic mean of the total demand data within multiple periods to get the predicted demand data.
3. According to claim 1, the method for intelligent matching of agricultural network protocol inventory is characterized in that: The specific method for obtaining the supply inventory data is as follows: Collect basic production data of the supply chain within a time period, including total time and output per unit time, and calculate the total output; Get the initial inventory quantity and consumption, add the initial inventory quantity and total production to get the inventory quantity, and subtract the inventory quantity from the consumption to get the supply inventory data.
4. According to claim 1, the method for intelligent matching of agricultural network protocol inventory is characterized in that: The specific method for obtaining the inventory deviation rate is as follows: Based on the supply inventory data and forecast demand data, the difference between the supplier's supply inventory data and forecast demand data is calculated, and the difference is divided by the forecast demand data to obtain the inventory deviation rate.
5. According to claim 4, the method for intelligent matching of agricultural network agreement inventory is characterized in that: The specific steps of optimizing the agricultural distribution network according to the inventory matching model are as follows: Optimize the ratio of the difference between inventory and consumption to forecast demand data through the inventory deviation rate in the inventory matching model; When the inventory deviation rate is positive, the supply inventory data is greater than the forecast demand data, reducing production; When the inventory deviation rate is negative, the supply inventory data is less than the forecast demand data, and the production volume is increased; When the inventory deviation rate is zero, the supply inventory data is equal to the forecast demand data, and the production volume does not change; The distribution optimization data in the inventory matching model is used to optimize the distribution distance between the supply node and the demand node and the packaging matching degree between the transportation container and the actual volume of the power materials.
6. According to claim 5, the method for intelligent matching of agricultural network agreement inventory is characterized in that: The delivery optimization data includes the total delivery distance and the packaging matching degree. The specific method for obtaining the total delivery distance is as follows: Obtain the shortest distance from the supply node to each demand node, and then use the greedy algorithm based on the local optimal principle to sum up the shortest distances and calculate the total delivery distance.
7. The method for intelligent matching of agricultural network protocol inventory according to claim 6 is characterized in that: The specific calculation formula of the inventory deviation rate is as follows: In the formula, is the inventory deviation rate, is the supply inventory data, It is the forecast demand data.
8. The method for intelligent matching of agricultural network agreement inventory according to claim 7 is characterized in that: The specific calculation formula of the distribution optimization data is as follows: In the formula, It is the delivery optimization data. is the total delivery distance, It is the packaging matching degree.
9. The method for intelligent matching of agricultural supply network protocol inventory according to claim 8 is characterized in that: The specific calculation formula of the inventory matching model is as follows: In the formula, is the inventory deviation rate, is the supply inventory data, is the forecast demand data, It is the delivery optimization data. is the packing matching degree, is the total delivery distance.
10. The method for intelligent matching of agricultural supply network protocol inventory according to claim 9 is characterized in that: The specific method for obtaining the packaging matching degree is as follows: Obtain the actual volume of the power materials and the volume of the transport container, and divide the actual volume of the power materials by the volume of the transport container to calculate the packaging matching degree; The specific calculation formula for the packaging matching degree is as follows: In the formula, is the packing matching degree, is the actual volume of the electrical material, is the volume of the shipping container.