Inventory management method and device for supply chain collaboration

Abstract

The invention provides an inventory management method and device oriented to supply chain collaboration, is applied to the technical field of supply chain management, identifies characteristics and storage requirements of different fruits by obtaining category information, establishes a quality attenuation evaluation model, scientifically quantifies a fruit quality change process, and improves the quality of the fruits. Calculating a quality attenuation value to accurately evaluate the current and predicted quality states of the fruits; backfield storage space information is obtained, and the actual inventory bearing capacity is known; the space distribution proportion is calculated, the fruit storage space utilization is optimized, and then the replenishment time point is determined according to the space distribution proportion of the fruits and the sales time period information, so that the sales demand and the inventory state are accurately matched, a scientific replenishment strategy can be formulated according to the market demand and the backfield inventory storage space, the shop cost is reduced to the minimum, and the market competitiveness is improved. And the utilization rate of the backfield inventory storage space is maximized.

Description

Technical Field

[0001] The present application relates to the technical field of supply chain management, and in particular to an inventory management method and device for supply chain collaboration. Background Art

[0002] As consumers' demand for fresh and healthy food continues to increase, this has brought new challenges to fruit supply. Specifically, stores in different regions face complex sales patterns, such as different peak sales hours in busy business districts and residential areas. The peak sales of stores in business districts are mainly concentrated during lunch breaks, while stores in residential areas have peak sales after dinner. This multi-regional and multi-time sales model requires the inventory management system to be highly flexible and adaptable.

[0003] The diversity of fruit categories further increases the complexity of inventory management. Small fruits such as grapes and strawberries have a short shelf life and their quality decays quickly, so they need to be sorted and processed within 1-2 hours before the peak sales. Large fruits such as bananas and apples have a longer shelf life, but the time required for subsequent ripening needs to be determined in advance. Tropical fruits such as mangoes and pitaya need to be graded, stored and used according to their maturity. This diverse fruit characteristic requires the inventory management system to be able to formulate personalized storage and replenishment strategies for different categories.

[0004] In this application scenario, suppliers deliver fruits to regional warehouses in the early morning every day, and then the warehouses carry out secondary distribution according to store orders. However, due to traffic and weather factors, the delivery time of some stores in business districts is limited on weekdays, especially during the morning and evening rush hours and in bad weather. This complex distribution environment requires the inventory management system to dynamically adjust the replenishment strategy to cope with possible delivery delays or interruptions. The main challenge faced by each store is to ensure the freshness and taste of the fruit within the limited back-end space, while avoiding sales affected by insufficient stock or loss caused by excessive stock. The existing inventory management method is difficult to effectively cope with this complex multi-regional, multi-period sales peak and limited delivery time situation, and it is impossible to establish a dynamic hierarchical storage and replenishment strategy for each store based on the quality decay characteristics, ripening laws and storage conditions of different types of fruits. As a result, the quality of the fruit is difficult to guarantee, and it is impossible to meet consumers' high requirements for freshness. In addition, the inventory management efficiency is low, and it is impossible to respond to changes in market demand in a timely manner, and the loss rate is high, resulting in economic losses and waste of resources.

[0005] Therefore, the existing technology lacks an intelligent inventory management method that can comprehensively consider multiple factors such as fruit quality decay, sales forecasts, storage space and distribution restrictions to achieve accurate evaluation and prediction of fruit quality, and thus cannot formulate a scientific replenishment strategy in line with market demand and back-end inventory storage space, minimize store costs, and maximize the utilization of back-end inventory storage space.

[0006] In view of the above problems, the existing technology needs to be improved urgently. Summary of the invention

[0007] In view of the above-mentioned shortcomings of the prior art, the present application provides an inventory management method and device for supply chain collaboration, which is applied to the field of supply chain management technology and has the advantages of improving the accuracy of fruit inventory management, reducing the loss rate, and optimizing the utilization of back-end space.

[0008] In a first aspect, the present application proposes an inventory management method for supply chain collaboration, the method comprising: S1: Obtain information on fruit categories, storage environment parameters, and sales periods of each store; S2: establishing a fruit quality decay assessment model according to the category information and the storage environment parameter information; S3: Calculating the quality decay value of each type of fruit according to the fruit quality decay assessment model; S4: Obtaining the back-end storage space information of each store; S5: Calculating the space allocation ratio of each type of fruit according to the quality attenuation value of the fruit and the back-end storage space information; S6: Determine the replenishment time point for each category of fruit according to the sales period information and the space allocation ratio, and generate a replenishment instruction according to the replenishment time point.

[0009] This application proposes an inventory management method for supply chain collaboration. By obtaining category information to identify the characteristics and storage requirements of different fruits, a quality decay evaluation model is established to scientifically quantify the fruit quality change process, and the quality decay value is calculated to accurately evaluate the current and predicted quality status of the fruit; the back-end storage space information is obtained to understand the actual inventory carrying capacity; the space allocation ratio is calculated to optimize the use of fruit storage space, and then the replenishment time point is determined according to the fruit space allocation ratio and sales period information, so as to accurately match sales demand and inventory status. By constructing a systematic fruit quality decay evaluation and inventory management method, accurate management of different categories of fruits is achieved. This method solves the problem that fruit quality is difficult to accurately control in traditional inventory management by establishing a scientific quality decay evaluation model, dynamically calculating fruit quality, and combining back-end storage space and sales period information, intelligently allocating inventory space and formulating replenishment strategies. It has the beneficial effect of being able to formulate scientific replenishment strategies in line with market demand and back-end inventory storage space, minimizing store costs, and maximizing the utilization of back-end inventory storage space.

[0010] Further, step S2 includes: S21: Obtaining the basic attenuation coefficient and periodic fluctuation parameter of each category of fruit in the category information; S22: Acquire temperature parameters and humidity parameters in the storage environment parameter information; S23: establishing a basic quality attenuation model according to the basic attenuation coefficient and the periodic fluctuation parameter; S24: Calculating an environmental impact factor according to the temperature parameter and the humidity parameter; S25: performing correlation operation on the basic quality decay model and the environmental impact factors to obtain the fruit quality decay assessment model.

[0011] This application proposes an inventory management method for supply chain collaboration, which solves the problem of how to accurately evaluate the decay of fruit quality by constructing a fruit quality decay evaluation model in steps. First, by obtaining the basic decay characteristics and environmental parameters of the fruit, a basic model that takes into account the inherent characteristics of the fruit is established. Then, by introducing environmental influencing factors, the influence of external conditions is taken into consideration. Finally, through association operations, the basic model and environmental factors are combined to form a comprehensive evaluation model. This method not only takes into account the characteristics of the fruit itself, but also takes into account the influence of the storage environment, so that changes in fruit quality can be predicted more accurately. This provides reliable data support for subsequent inventory management, replenishment decisions and quality control, and helps to improve the overall efficiency and product quality of the fruit supply chain.

[0012] Further, step S25 includes: S251: Acquire the quality attenuation reference value of the basic quality attenuation model, and the correction coefficient and standard deviation parameter of the environmental impact factor; S252: performing correction calculation on the quality attenuation reference value according to the correction coefficient and the standard deviation parameter to obtain a corrected quality attenuation value; S253: Performing weighted calculation on the corrected quality decay value and the basic quality decay model to obtain the fruit quality decay assessment model.

[0013] This application proposes an inventory management method for supply chain collaboration. By accurately correcting the quality decay baseline value, this technical solution can effectively improve the accuracy of the fruit quality decay assessment model. Specifically, by introducing correction coefficients and standard deviation parameters, the deviation and uncertainty in the original data can be eliminated, and the corrected quality decay value can be weighted with the basic quality decay model to obtain a more accurate and reliable fruit quality decay assessment model. This method can not only more accurately predict changes in fruit quality, but also provide more reliable data support for subsequent inventory management and replenishment decisions.

[0014] Furthermore, in step S2, the fruit quality attenuation assessment model is: ,in, ;in, Indicates the corrected quality attenuation value of the fruit at time t, represents the fruit quality attenuation reference value, k represents the fruit basic attenuation coefficient, α represents the periodic fluctuation amplitude of fruit quality, ω represents the periodic frequency of fruit quality, φ represents the phase difference of fruit quality, wherein the periodic fluctuation parameters include α, ω and φ; E(T,H) represents the environmental influencing factor, T represents the storage environment temperature value, H represents the storage environment humidity value, Indicates the standard storage temperature value, Represents the standard storage humidity value, where the temperature parameters include T and , humidity parameters include H and ; and Indicates the correction coefficient of storage temperature and storage humidity. and Indicates the standard deviation parameter of the ambient temperature and humidity values.

[0015] This application proposes an inventory management method for supply chain collaboration. By organically combining the inherent attenuation characteristics of fruits, periodic fluctuation laws and environmental influencing factors, the model can quantify the fruit quality attenuation process more comprehensively and accurately. The model not only takes into account the basic attenuation coefficient and periodic fluctuation parameters of the fruit itself, but also introduces corrections to environmental parameters such as temperature and humidity, making the quality attenuation assessment more dynamic and accurate. This multi-dimensional, parameterized modeling method provides scientific technical support for fruit supply chain inventory management, and can help companies better allocate inventory, formulate replenishment strategies and control quality.

[0016] Further, step S252 includes: S2521: Acquire time series data of the quality attenuation reference value; S2522: Generate an environmental impact correction matrix according to the correction coefficient and the standard deviation parameter; S2523: performing matrix multiplication operation on the time series data and the environmental impact correction matrix; S2524: Normalize the calculation result to obtain the corrected quality attenuation value.

[0017] Further, step S5 includes: According to the quality attenuation value of the fruit, the quality attenuation value of each type of fruit under the current storage condition is obtained, and according to the backstage storage space information, the total space capacity and the occupied space capacity of the backstage are obtained; S51: Obtain the number of types of the fruit and the estimated sales demand of each type of the fruit; S52: Establish a comprehensive benefit objective function for each type of fruit based on the quality attenuation value of the fruit, the total space capacity of the backstage, the occupied space capacity, the number of fruit categories, and the estimated sales demand for each type of fruit: ; Among them, the comprehensive benefit objective function satisfies the constraints: , , ; Where Z represents the maximum value of the comprehensive benefit target, represents the quality attenuation value of the i-th type of fruit, represents the allocation space ratio of the i-th type of fruit, represents the expected sales demand for the i-th type of fruit; represents the minimum space allocation ratio for the i-th type of fruit, C represents the total space capacity of the backcourt, and O represents the occupied space capacity; , , They represent the weight factors of quality decay value, expected sales demand and allocation space ratio, n represents the number of fruit categories, and i represents the ordinal number of the fruit category; S53: Solving the spatial allocation ratio of each type of fruit according to the comprehensive benefit objective function.

[0018] Further, step S6 includes: S61: Acquire historical sales data and sales peak period data in the sales period information; S62: Calculating sales forecast values ​​of various types of fruits according to the historical sales data; S63: Calculate the safety inventory threshold of each category of fruit according to the sales forecast value and the space allocation ratio; S64: Establishing a replenishment time evaluation matrix based on the safety stock threshold and the sales peak period data; S65: Calculate the optimal replenishment time point for each category of fruit according to the replenishment time evaluation matrix.

[0019] Furthermore, the method further comprises: S7: Acquire real-time sensor data corresponding to the storage environment parameter information; S8: Calculating an environmental change value according to a difference between the real-time sensing data and the stored environmental parameter information; S9: When the environmental change value exceeds a preset range, generating a parameter adjustment instruction; S10: According to the parameter adjustment instruction, the parameters in the fruit quality decay assessment model are updated.

[0020] Further, step S8 includes: S81: Acquire temperature data and humidity data in the real-time sensing data; S82: Acquire preset temperature data and preset humidity data in the storage environment parameter information; S83: generating a difference matrix according to a first difference between the temperature data and the preset temperature data, and a second difference between the humidity data and the preset humidity data; S84: Calculate the environment change value according to the change trends of the first difference and the second difference in the difference matrix.

[0021] In a second aspect, the present application proposes an inventory management device for supply chain collaboration, the device comprising: The first acquisition module: obtains the category information, storage environment parameter information and sales period information of each store's fruits; Model building module: building a fruit quality attenuation assessment model based on the category information and the storage environment parameter information; The first calculation module is used to calculate the quality attenuation value of each type of fruit according to the fruit quality attenuation assessment model; The second acquisition module: obtains the back-end storage space information of each store; The second calculation module calculates the space allocation ratio of each category of fruit according to the quality attenuation value of the fruit and the back-end storage space information; Inventory scheduling module: determines the replenishment time point of each category of fruit according to the sales period information and the space allocation ratio, and generates replenishment instructions according to the replenishment time point.

[0022] Beneficial effects: The present application proposes an inventory management method and device for supply chain collaboration. By acquiring category information, the characteristics and storage requirements of different fruits are identified, and a quality decay evaluation model is established to scientifically quantify the fruit quality change process, and the quality decay value is calculated to accurately evaluate the current and predicted quality status of the fruit; the back-end storage space information is obtained to understand the actual inventory carrying capacity; the space allocation ratio is calculated to optimize the use of the fruit storage space, and then the replenishment time point is determined according to the space allocation ratio of the fruit and the sales period information, so as to accurately match the sales demand and the inventory status. By constructing a systematic fruit quality decay evaluation and inventory management method, accurate management of different categories of fruits is achieved. The method solves the problem that the fruit quality is difficult to accurately control in traditional inventory management by establishing a scientific quality decay evaluation model, dynamically calculating the fruit quality, and combining the back-end storage space and sales period information, intelligently allocating inventory space and formulating replenishment strategies. It has the beneficial effect of being able to formulate a scientific replenishment strategy in line with market demand and back-end inventory storage space, minimizing store costs, and maximizing the utilization of back-end inventory storage space. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart of an inventory management method for supply chain collaboration proposed in this application.

[0024] Figure 2 This is a structural diagram of an inventory management device for supply chain collaboration proposed in this application.

[0025] Description of reference numerals: 201, first acquisition module; 202, model building module; 203, first calculation module; 204, second acquisition module; 205, second calculation module; 206, inventory scheduling module. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application usually described and marked in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first, second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] As consumers’ demand for fresh and healthy food continues to increase, traditional inventory management methods face severe challenges. Specifically, these challenges are mainly reflected in the following aspects: First, there are significant differences in the peak sales hours of stores in different regions, making it difficult to formulate a unified replenishment strategy; second, different types of fruits require differentiated storage and replenishment plans due to their different shelf life, quality decay rate and ripening rules; finally, the back-of-store space is limited, and it is necessary to find a balance between ensuring the freshness of the fruit and meeting the timely sales needs. These factors together constitute a complex multivariate problem that traditional inventory management methods cannot effectively deal with.

[0029] To illustrate this technical problem in detail, in some specific embodiments, a convenience store chain store in a busy business district has a peak sales period during the lunch break on weekdays (11:30-13:30). The back-end storage space of the store is only 10 square meters, and at least 10 different types of fruits need to be stored at the same time, including strawberries and grapes with a short shelf life, and bananas and mangoes that need to be judged in advance. In order to facilitate customers to enter and exit the store to purchase products, the store receives delivery in two time periods every day: 7:00-9:00 in the morning and 20:00-22:00 in the evening. In this case, store managers are faced with the problem of how to formulate the best replenishment strategy for fruits with different shelf lives and ripening cycles within the limited storage space and fixed delivery time window to ensure sufficient supply of fresh fruits during the peak sales period at noon. Specifically, managers need to consider multiple factors such as the quality decay rate of each fruit, the current inventory level, the expected sales volume, and the uncertainty of the delivery time, which far exceeds the processing capacity of traditional inventory management methods.

[0030] If this technical problem cannot be effectively solved, a series of serious consequences will occur. First, the quality of the fruit is difficult to guarantee, and some fruits may be past their best consumption period during peak sales, affecting customer experience and brand reputation. Secondly, inefficient inventory management may lead to insufficient inventory of popular categories, resulting in loss of sales opportunities; or inventory backlogs, increased loss rates and operating costs. Finally, since it is impossible to accurately predict the optimal time to replenish fruits of various categories, it may cause a waste of human resources and increase operating costs. Therefore, there is an urgent need for a new fruit inventory management method that can comprehensively consider multiple factors and dynamically adjust inventory strategies to solve this complex technical problem.

[0031] This application conducts in-depth analysis and exploration of the inventory management challenges faced by the chain convenience store group's ready-made and sold fruit platter business. Considering the differences in peak sales hours of stores in different regions, an inventory management method that can adapt to diversified sales models is needed. In addition, due to the different shelf life, quality decay rate and ripening rules of various types of fruits, differentiated storage and replenishment strategies are required. In addition, the back-of-store space is limited, and a balance needs to be found between ensuring the freshness of the fruit and meeting the timely sales needs.

[0032] In order to solve the above problems, the following solutions are usually adopted in the prior art: 1. Use IoT technology to monitor the inventory status of each store in real time, and automatically trigger replenishment when the inventory falls below a certain threshold. However, this method may lead to frequent replenishment and increase transportation costs.

[0033] 2. Set up a large warehouse in the regional center to centrally manage inventory and deliver according to the needs of each store. This method may affect the freshness of the fruit due to the increased delivery distance.

[0034] From the above analysis, the solutions in the prior art all have certain limitations and it is difficult to comprehensively solve the problem of fruit inventory management. Therefore, this application proposes an inventory management method and device for supply chain collaboration.

[0035] Please refer to Figure 1 In the first aspect, the present application proposes an inventory management method for supply chain collaboration, the method comprising: S1: Obtain information on fruit categories, storage environment parameters, and sales periods of each store; S2: Establish a fruit quality decay assessment model based on category information and storage environment parameter information; S3: Calculate the quality decay value of each type of fruit according to the fruit quality decay assessment model; S4: Obtaining the back-end storage space information of each store; S5: Calculate the space allocation ratio of each type of fruit according to the quality attenuation value of the fruit and the back-end storage space information; S6: Determine the replenishment time point for each category of fruit based on the sales period information and the space allocation ratio, and generate a replenishment instruction based on the replenishment time point.

[0036] Category information refers to basic information such as the types and characteristics of fruits, which can be stored and managed in the form of a database or table.

[0037] Storage environment parameter information refers to environmental factors that affect fruit quality, such as temperature, humidity, etc., which can be obtained by real-time collection by sensors or manual entry.

[0038] Sales period information refers to time data such as the peak sales period and off-season of each store, which can be obtained by analyzing historical sales records or real-time monitoring of sales.

[0039] The fruit quality decay assessment model refers to a mathematical model used to predict the change of fruit quality over time, which can be constructed using an exponential decay function or other suitable mathematical models.

[0040] The quality decay value refers to the degree of decline in fruit quality, which can be specifically expressed by the numerical value obtained by the calculation model.

[0041] Back-of-the-field storage space information refers to the size and layout of the space available for storing fruit in the store, which can be obtained through on-site measurements or by referring to the store floor plan.

[0042] The space allocation ratio refers to the distribution plan of different types of fruits in limited storage space, which can be calculated through optimization algorithms.

[0043] The replenishment time point refers to the best time to replenish fruits, which can be determined based on sales forecasts and inventory status.

[0044] In some specific implementations, the specific implementation process of this application is as follows: First, the system obtains fruit category information from each store through store terminal devices, including basic information such as the names and shelf life of common fruits such as apples, bananas, and grapes. At the same time, the system collects storage environment parameters in real time through temperature and humidity sensors installed in the back field, such as maintaining the temperature at 4°C ± 1°C and the relative humidity at 85% ± 5%. The sales period information is obtained by analyzing the sales data of the past 30 days, recording the sales volume of each hour period.

[0045] Next, the system builds a fruit quality decay assessment model based on the acquired information. Taking apples as an example, its quality decay model can be expressed as: ,in Indicates the corrected quality attenuation value of the fruit at time t, It represents the baseline value of fruit quality decay, k is the basic decay coefficient of the fruit (such as 0.05 / day), and E(T,H) represents the environmental impact factor.

[0046] The system then uses the established model to calculate the quality decay value of each type of fruit. For example, for apples stored for three days, in the current environment of 4°C and 85% humidity, the quality decay value may be 5%.

[0047] The system also obtains the back-end storage space information of each store. For example, the total capacity of the back-end refrigerated area of ​​a certain store is 10 cubic meters, and 7.5 cubic meters are currently occupied.

[0048] Based on this information, the system calculates the spatial allocation ratio of each type of fruit. Through the optimization algorithm, the system may come up with the following allocation plan: 30% for apples, 25% for bananas, 20% for grapes, and 25% for other fruits.

[0049] Finally, based on the sales period information (such as the store's peak sales at 12:00-14:00 and 18:00-20:00) and the space allocation ratio, the system determines the replenishment time of each category of fruit. For example, the system may generate the following replenishment instructions: apples are replenished at 10:00 and 16:00 every day, bananas are replenished at 9:30 and 15:30, and grapes are replenished at 11:00 and 17:00.

[0050] In this way, the application achieves precise management of fruit inventory, which not only ensures fruit quality, but also optimizes space utilization and reduces inventory costs. At the same time, it can respond to sales demand in a timely manner, greatly improving the management efficiency of the fruit supply chain.

[0051] Further, step S2 includes: S21: Obtain the basic attenuation coefficient and periodic fluctuation parameter of each category of fruit in the category information; S22: Acquire temperature parameters and humidity parameters in the storage environment parameter information; S23: Establish a basic quality attenuation model based on the basic attenuation coefficient and periodic fluctuation parameters; S24: Calculate the environmental impact factor according to the temperature parameter and the humidity parameter; S25: Correlate the basic quality decay model with environmental influencing factors to obtain a fruit quality decay assessment model.

[0052] In the implementation process of collaborative inventory management in the fruit supply chain, the existing technology is difficult to accurately evaluate the quality decay process of different types of fruits, and cannot effectively consider the comprehensive impact of the inherent characteristics of fruits and external environmental factors on quality. In response to this technical problem, this application proposes a technical solution to establish a fruit quality decay assessment model.

[0053] This technical solution systematically acquires and analyzes the intrinsic and external factors of fruits to construct a comprehensive quality decay assessment model to obtain the basic decay coefficient and periodic fluctuation parameters in the fruit category information. This parameter can be implemented in a variety of ways. For example, the quality change curves of different fruit categories under standard conditions can be measured experimentally to extract the basic decay coefficient k, periodic fluctuation amplitude α, periodic frequency ω and phase difference φ. There may be significant differences in the parameters of different fruit categories. For example, the decay rate of grapes may be significantly faster than that of apples.

[0054] The temperature and humidity parameters in the storage environment parameter information are monitored in real time by sensors. The temperature parameters include the current storage temperature value T and the standard storage temperature value , humidity parameters include the current storage humidity value H and the standard storage humidity value .

[0055] By obtaining the above parameters, the environmental impact factor E(T,H) that affects the environment can be directly calculated.

[0056] When establishing a basic quality decay model, it is necessary to consider the nonlinear changes in fruit quality over time. The model can more accurately describe the dynamic changes in fruit quality by combining an exponential decay function with periodic fluctuations. The periodic fluctuation parameter introduces a sine function to simulate the periodic changes in fruit quality at different growth stages.

[0057] The calculation of environmental impact factors is to describe the effects of temperature and humidity on fruit quality through Gaussian functions. When the actual temperature and humidity deviate from the standard values, the environmental impact factors will significantly adjust the quality decay rate. This modeling method can quantify the nonlinear effects of the external environment on fruit quality.

[0058] The basic quality decay model is associated with the environmental factors to form the final fruit quality decay assessment model. The association operation makes the environmental factors become the adjustment coefficients of the basic model through multiplication. This method can comprehensively consider the inherent characteristics of fruits and external environmental factors and improve the accuracy of quality decay prediction.

[0059] In some specific implementations, apples are taken as an example. Assume that the basic attenuation coefficient k of apples is 0.05 / day, the periodic fluctuation amplitude α is 0.1, the periodic frequency ω is 2π / 7, and the phase difference φ is 0. Under a standard environment of 20°C and 60% relative humidity, by establishing a quality attenuation model, the quality change trend of apples under different storage conditions can be accurately predicted. When the actual temperature rises to 25°C or the humidity changes to 70%, the model can automatically adjust the quality attenuation rate to provide more accurate prediction results.

[0060] Compared with the existing technology, the method of this application breaks through the limitations of the traditional single linear decay model, introduces periodic fluctuations and environmental influencing factors, and significantly improves the accuracy and adaptability of fruit quality decay assessment. Through systematic modeling, it can provide more reliable technical support for fruit supply chain management.

[0061] Further, step S25 includes: S251: Obtain the quality attenuation benchmark value of the basic quality attenuation model, as well as the correction coefficient and standard deviation parameter of the environmental impact factor; S252: Correcting and calculating the quality attenuation reference value according to the correction coefficient and the standard deviation parameter to obtain a corrected quality attenuation value; S253: Perform weighted calculation on the corrected quality decay value and the basic quality decay model to obtain a fruit quality decay assessment model.

[0062] Among them, in some of the above-mentioned embodiments, during the implementation of the present application, there is still a problem of how to accurately correct the fruit quality attenuation baseline value to obtain a more accurate fruit quality attenuation assessment model.

[0063] In this regard, the present application further proposes obtaining a quality attenuation benchmark value of a basic quality attenuation model, as well as a correction coefficient and standard deviation parameter of an environmental impact factor; performing correction calculation on the quality attenuation benchmark value according to the correction coefficient and standard deviation parameter to obtain a corrected quality attenuation value; performing weighted calculation on the corrected quality attenuation value and the basic quality attenuation model to obtain a fruit quality attenuation assessment model.

[0064] This application accurately corrects the quality decay benchmark value by calculating the correction coefficient and standard deviation parameters, thereby improving the accuracy of the fruit quality decay assessment model. Specifically, the quality decay benchmark value of the basic quality decay model is first obtained, which provides the original data basis for subsequent corrections. At the same time, the correction coefficient and standard deviation parameters of the environmental impact factor are obtained, which provide the key basis for the correction calculation.

[0065] Next, the quality attenuation benchmark value is corrected and calculated based on the correction coefficient and standard deviation parameter. The purpose of this step is to eliminate the possible deviation and uncertainty in the original data. The correction coefficient can adjust the overall trend of the quality attenuation benchmark value, while the standard deviation parameter can reflect the discrete degree of the data, so that the corrected quality attenuation value is closer to the actual situation.

[0066] Finally, the corrected quality decay value is weighted and calculated with the basic quality decay model to obtain the final fruit quality decay assessment model. This step integrates the corrected data with the original model, retaining the basic characteristics of the basic model and introducing the accurately corrected quality decay value, thereby improving the accuracy and adaptability of the model.

[0067] The technical solution of the present application can be implemented in a variety of ways. For example, when obtaining the quality attenuation benchmark value, historical data analysis, experimental measurement or expert experience value and other methods can be used. The correction coefficient and standard deviation parameter of the environmental impact factor can be determined by statistical analysis or machine learning algorithm.

[0068] In the correction calculation process, different methods can be used, such as linear correction, nonlinear correction or correction based on probability distribution. For example, weighted average, exponential smoothing or Bayesian inference techniques can be used to comprehensively consider the influence of the correction coefficient and standard deviation parameters.

[0069] There are also multiple options for weighted calculation methods, such as simple arithmetic mean, geometric mean, or more complex optimization algorithms. These different implementation methods can be selected and adjusted according to specific application scenarios and data characteristics.

[0070] Through the above steps, the technical solution of this application can effectively improve the accuracy of the fruit quality decay assessment model. Compared with the method that only relies on the basic quality decay model, the solution of this application can better adapt to the changes in fruit quality under different environmental conditions, thereby providing more reliable data support for subsequent inventory management and replenishment decisions.

[0071] In some specific implementations, first, the quality decay benchmark value of the basic quality decay model is obtained. For example, for a certain fruit, its quality decay benchmark value Probably 100 (assuming 100 represents the best quality).

[0072] Next, obtain the correction coefficient and standard deviation parameter of the environmental impact factor. Assume that the correction coefficient of the storage ambient temperature value is is 0.95, the standard deviation parameter The correction factor for storage humidity is 2℃. is 0.98, the standard deviation parameter It is 5%.

[0073] Then, perform correction calculation. Assume that the current storage environment temperature value T is 22°C and the standard storage temperature value is The current storage environment humidity value H is 65%, the standard storage humidity value is 60%. Using the formula Calculate environmental impact factors.

[0074] Substitute the values: E(T,H) = 0.9025.

[0075] In some simple calculation models, the above calculation steps calculate the environmental impact factor based on the correction coefficient and standard deviation parameter of the environmental impact factor, and then multiply the environmental impact factor by the quality attenuation reference value to obtain the corrected quality attenuation value: 100 × 0.9025 = 90.25. In some preferred calculation models, an exponential attenuation term can also be introduced and the periodic fluctuation term Multiply it by the environmental impact factor and the quality attenuation baseline value to obtain a more accurate corrected quality attenuation value.

[0076] Finally, the corrected quality attenuation value is weighted with the basic quality attenuation model. Assuming that the quality attenuation value predicted by the basic model is 95 and the weighting coefficient is 0.6, the final quality attenuation value is: 90.25 × 0.6 + 95 ×0.4 = 92.15.

[0077] This result comprehensively considers the impact of environmental factors and the prediction of the basic model, providing a more accurate assessment of fruit quality decay. Traditional fruit quality decay assessment models usually only consider basic time factors, or simply introduce environmental parameters, which makes it difficult to accurately reflect quality changes in complex environments. The present application can more accurately quantify the impact of environmental factors by introducing correction coefficients and standard deviation parameters. In addition, the method of the present application fuses the corrected quality decay value and the basic model through weighted calculation, which not only retains the advantages of the basic model, but also improves the adaptability and accuracy of the model. This method can not only more accurately predict changes in fruit quality, but also provide more reliable data support for subsequent inventory management and replenishment decisions, thereby effectively reducing the fruit loss rate and improving inventory management efficiency.

[0078] Furthermore, in step S2, the fruit quality attenuation assessment model is: ,in, ;in, Indicates the corrected quality attenuation value of the fruit at time t, represents the fruit quality attenuation reference value, k represents the fruit basic attenuation coefficient, α represents the periodic fluctuation amplitude of fruit quality, ω represents the periodic frequency of fruit quality, φ represents the phase difference of fruit quality, wherein the periodic fluctuation parameters include α, ω and φ; E(T,H) represents the environmental influencing factor, T represents the storage environment temperature value, H represents the storage environment humidity value, Indicates the standard storage temperature value, Represents the standard storage humidity value, where the temperature parameters include T and , humidity parameters include H and ; and Indicates the correction coefficient of storage temperature and storage humidity. and Indicates the standard deviation parameter of the ambient temperature and humidity values.

[0079] Among them, in terms of basic attenuation characteristics, an exponential attenuation term is introduced , accurately describing the inherent decay law of fruits. By adjusting the basic decay coefficient k, the basic decay rate of different fruit categories can be simulated. For example, for perishable fruits such as strawberries, the k value can be set to a larger value to reflect its rapid decay characteristics; while for storable fruits such as apples, the k value is relatively small.

[0080] Periodic fluctuations The dynamic change characteristics of fruit quality are introduced. By adjusting the periodic fluctuation amplitude α, periodic frequency ω and phase difference φ, the periodic fluctuations of fruit quality during storage can be simulated, so that the model can capture the complex process of fruit quality, which is not a simple linear decay, but a fluctuation and fine-tuning. Among them, by introducing the phase difference φ, it is indicated that the periodic fluctuation of fruit quality decay does not necessarily start from time t=0, but can be input by the technician to start at a specific time point, which can be t=0, so that the fruit can obtain periodic fluctuation parameters from different time points under different storage conditions, making the application of the fruit quality decay assessment model more flexible and improving the accuracy of the fruit quality decay assessment model.

[0081] The environmental impact factor E(T,H) accurately quantifies the impact of temperature and humidity on fruit quality through a Gaussian function. This factor not only takes into account the absolute values ​​of temperature and humidity, but also introduces a standard deviation parameter, which enables the model to be sensitive to small changes in environmental parameters. For example, when the temperature slightly deviates from the optimal storage temperature, the model can accurately calculate the degree of impact on fruit quality.

[0082] In practical applications, the model can dynamically adjust model parameters according to the characteristics of different fruit categories. For tropical fruits such as mangoes, a more sensitive temperature correction coefficient can be set; for temperate fruits such as apples, the weight of humidity influence can be adjusted. This flexible parameterization design makes the model highly adaptable and universal.

[0083] By introducing this multi-dimensional, parameterized quality decay assessment model, the precise inventory management of the fruit supply chain can be achieved. This model can not only provide a more dynamic and accurate quality assessment, but also provide technical support for enterprises to formulate scientific inventory allocation and replenishment strategies.

[0084] Further, step S252 includes: S2521: Obtaining time series data of quality attenuation benchmark values; S2522: Generate an environmental impact correction matrix based on the correction coefficient and standard deviation parameters; S2523: Perform matrix multiplication operation on the time series data and the environmental impact correction matrix; S2524: Normalize the calculation result to obtain a corrected quality attenuation value.

[0085] Among them, in some of the above-mentioned embodiments, during the implementation of the present application, there is still a technical problem of how to solve the correction calculation of the quality attenuation baseline value by the environmental impact factors in the fruit quality attenuation assessment model.

[0086] In this regard, the technical solution of the present application realizes the dynamic correction of the benchmark value of fruit quality decay by introducing time series data and environmental impact correction matrix. First, the time series data of the quality decay benchmark value is obtained to provide a basis for the correction calculation. Then, according to the correction coefficient and standard deviation parameter of the environmental impact factor, the environmental impact correction matrix is ​​generated. This step quantifies the impact of environmental factors. Next, the benchmark data is combined with the environmental impact through matrix multiplication to obtain a preliminary correction result. Finally, the calculation results are normalized to ensure that the corrected quality decay value has a unified scale and comparability. This method not only takes into account the impact of time factors on quality decay, but also incorporates the dynamic changes of environmental factors, thereby improving the accuracy and adaptability of fruit quality decay assessment.

[0087] In a specific embodiment, the quality degradation of a batch of apples needs to be evaluated. First, the time series data of the quality degradation baseline value of the batch of apples in the past 7 days is obtained, with a data point once a day, for a total of 7 data points. These data may be obtained by non-destructive testing equipment (such as a near-infrared spectrometer).

[0088] Next, we determined the correction coefficients and standard deviation parameters for the storage temperature and humidity values ​​based on the actual storage environment. Assume that the correction coefficient for the storage temperature value is 1.1 and the standard deviation is 0.05; the correction coefficient for the storage humidity value is 0.95 and the standard deviation is 0.03. Based on these parameters, a 7x7 environmental impact correction matrix is ​​generated.

[0089] Then, the 7-day time series data (represented as a 1x7 matrix) is matrix multiplied with the 7x7 environmental impact correction matrix.

[0090] Finally, the 1x7 result matrix is ​​normalized. The maximum and minimum normalization method can be used to map all values ​​between 0 and 1. In this way, the final corrected quality decay values ​​are obtained, which can be directly used for subsequent inventory management decisions.

[0091] This method can more accurately reflect the impact of environmental changes on apple quality. For example, if the temperature of the storage environment suddenly rises on the third day, a corresponding change will be observed in the corrected quality decay value, so that the inventory strategy can be adjusted in time to avoid quality loss caused by environmental changes.

[0092] Compared with the prior art, the technical solution of the present application has significant advantages. Traditional methods usually only consider the impact of time factors on fruit quality, or use simple linear correction methods to consider environmental factors. These methods are difficult to accurately reflect the dynamic impact of complex environmental changes on fruit quality. However, by introducing environmental impact correction matrices and matrix multiplication operations, the present application can more accurately capture the impact of environmental changes on quality attenuation, thereby providing more reliable quality assessment results. This precise assessment provides better decision support for inventory management, helps reduce fruit losses, and improves economic benefits.

[0093] Further, step S5 includes: According to the quality decay value of the fruit, the quality decay value of each type of fruit under the current storage condition is obtained, and according to the back-end storage space information, the total space capacity and the occupied space capacity of the back-end are obtained; S51: Obtain the number of fruit categories and the estimated sales demand of each type of fruit; S52: Based on the quality attenuation value of the fruit, the total space capacity of the back field, the occupied space capacity, the number of fruit categories and the expected sales demand of each type of fruit, establish the comprehensive benefit objective function of each type of fruit: ; Among them, the comprehensive benefit objective function satisfies the constraints: , , ; Where Z represents the maximum value of the comprehensive benefit target, represents the quality attenuation value of the i-th type of fruit, represents the allocation space ratio of the i-th type of fruit, represents the expected sales demand for the i-th type of fruit; represents the minimum space allocation ratio for the i-th type of fruit, C represents the total space capacity of the backcourt, and O represents the occupied space capacity; , , They represent the weight factors of quality decay value, expected sales demand and allocation space ratio, n represents the number of fruit categories, and i represents the ordinal number of the fruit category; S53: Solve the spatial allocation ratio of each type of fruit based on the comprehensive benefit objective function.

[0094] Among them, in some of the above-mentioned embodiments, during the implementation of the present application, there is still a problem of how to reasonably allocate storage space for various types of fruits in a limited back-end space.

[0095] In this regard, the present application solves the problem of reasonable allocation of back-end space by establishing a comprehensive benefit objective function. The comprehensive benefit objective function takes into account three key factors: fruit quality attenuation, expected sales demand, and space utilization, and introduces weight factors to balance the importance of these factors. By setting reasonable constraints, the feasibility and rationality of the allocation plan are ensured. Finally, by solving the objective function, the optimal space allocation ratio for each type of fruit is obtained. This method can not only maximize space utilization, but also be flexibly adjusted according to the characteristics of different fruits and market demand, thereby improving overall inventory management efficiency, reducing fruit loss, and meeting consumer demand for fresh fruits. Among them, the expected sales demand for each type of fruit can be obtained based on historical sales data.

[0096] Further, step S6 includes: S61: Acquire historical sales data and sales peak period data in the sales period information; S62: Calculate sales forecast values ​​of various types of fruits based on historical sales data; S63: Calculate the safety stock threshold of each category of fruit based on the sales forecast value and the space allocation ratio; S64: Establish a replenishment time evaluation matrix based on safety stock thresholds and sales peak period data; S65: Calculate the optimal replenishment time point for each category of fruit according to the replenishment time evaluation matrix.

[0097] Among them, in order to solve the technical problem of inaccurate replenishment time points for various categories of fruits in the inventory management of the fruit supply chain, this application proposes a technical solution for determining replenishment time in an inventory management method for supply chain collaboration. The core of this technical solution is to accurately calculate the optimal replenishment time points for various categories of fruits through multi-dimensional data analysis. The specific implementation includes the following key steps: First, obtain the historical sales data and sales peak period data in the sales period information. This step provides basic data for subsequent analysis, covering sales in different periods and regions. For example, it can distinguish the sales characteristics of stores in business districts and stores in residential areas, and capture different sales peak periods such as lunch break and after dinner.

[0098] Secondly, calculate the sales forecast value of each category of fruit based on historical sales data. This step predicts the possible sales volume of different categories of fruit in the future through statistical analysis of historical data. For example, sales forecast models can be established for small fruits such as grapes and strawberries and large fruits such as apples and bananas.

[0099] Thirdly, the safety stock threshold of each category of fruit is calculated based on the sales forecast and the space allocation ratio. This step not only considers the sales forecast, but also the actual situation of the back-end storage space to determine the reasonable inventory level. Different safety stock thresholds can be set for different categories of fruit, such as tropical fruits and temperate fruits.

[0100] Specifically, the calculation formula for the safety stock threshold can be: ,in, is the safety stock threshold of the i-th category of fruit; is the replenishment cycle; is the sales fluctuation coefficient of the i-th category of fruit, which is usually estimated by calculating the standard deviation or dispersion of daily sales.

[0101] Then, a replenishment time evaluation matrix is ​​established based on the safety stock threshold and sales peak period data. This matrix comprehensively considers multiple dimensions such as sales forecast, inventory level, sales peak, etc., providing a systematic analysis framework for accurately determining the replenishment time point.

[0102] Finally, the optimal replenishment time for each type of fruit is calculated based on the replenishment time evaluation matrix. By calculating and analyzing the matrix, the best replenishment time can be determined for each type of fruit, which can ensure freshness and avoid inventory backlogs.

[0103] Specifically, the replenishment time evaluation matrix The calculation process is: First, calculate the inventory consumption of each type of fruit: ,in, represents the inventory consumption of the i-th type of fruit in the j-th period, j=1,2... ...24; Represents the expected sales demand for the i-th type of fruit in the j-th period.

[0104] Then calculate the real-time inventory level, assuming that the initial inventory level is , then the real-time inventory of time period j is for: . Next, define the replenishment evaluation matrix ,in, Indicates the sales peak flag of the jth period, with a value of 1 indicating peak and a value of 0 indicating non-peak. Less than or equal to the safety stock threshold When the replenishment evaluation matrix depends on the sales peak indicator and inventory consumption ratio; when the off-peak period ( =0) or the real-time inventory is greater than the safety stock threshold, The value of is 0.

[0105] Last restocking time ,in represents the vth replenishment time of the i-th type of fruit, It represents the replenishment priority threshold, which is used to filter the low priority time periods, and D represents the replenishment time interval.

[0106] In actual application, this solution can complete replenishment 1-2 hours before the sales peak based on the characteristics of short-shelf-life fruits such as grapes and strawberries. For large fruits such as bananas and apples, the ripening time can be determined in advance and corresponding replenishment strategies can be formulated.

[0107] Compared with the existing technology, this solution has established a dynamic and sophisticated method for determining replenishment time, which can be adjusted in real time according to the characteristics of different types of fruits and market demand; through multi-dimensional data analysis, it overcomes the empiricism and lag of traditional inventory management methods, realizes the personalization and precision of inventory management, and can significantly improve inventory turnover efficiency.

[0108] In some specific embodiments, a convenience store chain group can set different replenishment time points for stores in different regions. For example, stores in business districts can replenish small fruits such as grapes and strawberries at 10 a.m. and 2 p.m.; stores in residential areas can replenish large fruits such as apples and bananas at 7 p.m. and 9 p.m. This refined management can effectively reduce inventory costs and improve the freshness of fruits.

[0109] Furthermore, the method also includes: S7: Acquire real-time sensor data corresponding to storage environment parameter information; S8: Calculate the environmental change value according to the difference between the real-time sensing data and the stored environmental parameter information; S9: When the environmental change value exceeds the preset range, a parameter adjustment instruction is generated; S10: According to the parameter adjustment instruction, the environmental impact factors in the fruit quality decay assessment model are updated.

[0110] Among them, in some of the above-mentioned embodiments, during the implementation of the present application, there is still a technical problem of how to solve the dynamic update of the parameters of the fruit quality attenuation assessment model.

[0111] In this regard, the present application obtains real-time sensor data and compares it with preset storage environment parameters to calculate the environmental change value. When the environmental change exceeds the preset range, a parameter adjustment instruction is generated, and the environmental impact factor of the fruit quality decay assessment model is updated accordingly. These steps enable the model to be dynamically adjusted according to actual environmental changes, thereby improving the accuracy of quality decay assessment.

[0112] This technical solution solves the problem of updating the parameters of the fruit quality decay assessment model through real-time monitoring and dynamic adjustment. By continuously acquiring real-time environmental data, the system can promptly detect changes in the storage environment. By calculating the environmental change value and comparing it with the preset range, the system can determine whether the model parameters need to be adjusted. When adjustment is required, the system will generate parameter adjustment instructions and update the model parameters accordingly. This dynamic adjustment mechanism enables the fruit quality decay assessment model to adapt to changes in the actual storage environment, improving the accuracy and practicality of the assessment.

[0113] The acquisition of real-time sensor data can be achieved in a variety of ways. For example, temperature sensors and humidity sensors can be installed in the storage environment, which can collect environmental data regularly or continuously. In addition, integrated environmental monitoring equipment can also be used to collect multiple parameters such as temperature, humidity, and light at the same time.

[0114] There are many algorithms that can be used to calculate the environmental change value. A simple method is to calculate the absolute difference between the real-time data and the preset parameters.

[0115] The generation of parameter adjustment instructions can be based on predetermined rules or machine learning algorithms. For example, a simple threshold rule can be set: if the environmental change value exceeds 10%, an adjustment instruction is generated. More advanced methods can use fuzzy logic or neural networks to more accurately determine when parameters need to be adjusted.

[0116] The parameter update of the fruit quality decay assessment model can be done by gradual adjustment or batch update. The gradual adjustment can use the following formula: new parameter = old parameter + learning rate * (target value - predicted value). Batch update can collect data within a certain period of time, and then use optimization algorithms (such as gradient descent) to update multiple parameters at one time, thereby improving computational efficiency.

[0117] Compared with the prior art, the dynamic parameter adjustment mechanism proposed in this application can automatically and in real time adapt to environmental changes. This adaptive ability makes the assessment of fruit quality attenuation more accurate, thereby providing a more reliable basis for inventory management decisions. For example, in traditional systems, if the storage environment suddenly becomes humid, manual intervention may be required to adjust the model parameters, which is not only time-consuming and labor-intensive, but may also miss the best time for adjustment. The system of this application can respond immediately when environmental changes occur, automatically adjust relevant parameters, and ensure that the evaluation results are always consistent with the actual situation.

[0118] Further, step S8 includes: S81: Acquire temperature data and humidity data in real-time sensor data; S82: Acquire preset temperature data and preset humidity data in the storage environment parameter information; S83: generating a difference matrix according to a first difference between the temperature data and the preset temperature data, and a second difference between the humidity data and the preset humidity data; S84: Calculate the environment change value according to the change trends of the first difference and the second difference in the difference matrix.

[0119] Among them, in the implementation process of collaborative inventory management of fruit supply chain, it is difficult for the existing technology to realize real-time accurate monitoring and dynamic adjustment of fruit storage environment parameters. To address this problem, this application proposes a method for dynamic adjustment of environmental parameters based on real-time sensor data.

[0120] In specific implementation, the method can adopt the following technical paths: First, deploy temperature and humidity sensors in the fruit storage environment to collect current environmental data in real time. Secondly, pre-set the optimal storage temperature and humidity standard values ​​for different fruit categories. Then, by calculating the first difference between the real-time temperature data and the standard temperature data, and the second difference between the real-time humidity data and the standard humidity data, a two-dimensional difference matrix is ​​constructed. Furthermore, a trend analysis is performed on the difference matrix to determine the rate and direction of change of temperature and humidity, thereby calculating the environmental change value.

[0121] In actual applications, when the calculated environmental change value exceeds the preset threshold range, the system will automatically generate parameter adjustment instructions. These instructions may include starting the refrigeration adjustment system, adjusting the ventilation equipment, or changing the microenvironmental conditions of the storage area, thereby adjusting the environmental impact factors in the model. Through this real-time monitoring and dynamic adjustment mechanism, the speed of fruit quality decay can be effectively slowed down and the shelf life of the fruit can be extended.

[0122] In some specific implementations, for example, multi-point temperature and humidity sensors are installed in the back-end storage area of ​​a convenience store chain. For different types of fruits, such as strawberries, apples, and bananas, the optimal storage temperatures are set at 15-18°C, 0-4°C, and 12-14°C, and the relative humidity is set at 60-70%. When the sensor detects that the temperature in a certain area deviates from the standard by 2°C or the humidity changes by more than 10%, the system will automatically trigger the environmental adjustment process.

[0123] Compared with the traditional static inventory management method, the method of this application can realize accurate dynamic monitoring of the fruit storage environment. By acquiring temperature and humidity data in real time and responding quickly to environmental changes, the fruit quality decay process can be better controlled and the accuracy and efficiency of inventory management can be improved.

[0124] In a second aspect, the present application proposes an inventory management device for supply chain collaboration, the device comprising: The first acquisition module 201: acquiring the category information, storage environment parameter information and sales period information of each store's fruit; Model building module 202: building a fruit quality decay assessment model based on category information and storage environment parameter information; The first calculation module 203: calculates the quality decay value of each type of fruit according to the fruit quality decay evaluation model; The second acquisition module 204: acquiring the back-end storage space information of each store; The second calculation module 205 calculates the space allocation ratio of each type of fruit according to the quality attenuation value of the fruit and the back-end storage space information; Inventory scheduling module 206: determines the replenishment time point of each category of fruit according to the sales period information and the space allocation ratio, and generates replenishment instructions according to the replenishment time point.

[0125] The device realizes supply chain collaborative inventory management for fruits through multiple functional modules. The first acquisition module acquires 201 the category information, storage environment parameter information and sales period information of fruits in each store, providing basic data for subsequent processing. The model building module 202 uses this information to construct a fruit quality decay assessment model to provide a basis for accurately assessing the changes in fruit quality. The first calculation module 203 uses the model to calculate the quality decay value, which helps to accurately grasp the shelf life and quality status of the fruit.

[0126] The second acquisition module 204 acquires the back-end storage space information of each store to provide a basis for the reasonable allocation of inventory space. The second calculation module 205 combines the quality decay value and the space information to calculate the space allocation ratio of each category of fruit to achieve optimal use of storage space. The inventory scheduling module 206 determines the replenishment time point and generates instructions based on the sales period information and the space allocation ratio to achieve accurate inventory replenishment.

[0127] The device closely combines fruit quality decay assessment with inventory management. By establishing an accurate quality decay assessment model, it can dynamically assess the quality of different types of fruits. This provides a scientific basis for subsequent space allocation and replenishment decisions. For example, for small fruits with a short shelf life, the device may allocate a smaller storage space and arrange more frequent replenishment; while for large fruits with a longer shelf life, it may allocate a larger space and reduce the replenishment frequency.

[0128] In terms of space allocation, the second calculation module 205 not only considers the quality decay value, but also combines the back-end storage space information. This enables the device to perform personalized space optimization based on the actual situation of each store. For example, for stores with smaller back-end space, the device may prioritize space allocation for fruit categories with large sales volume and short shelf life to ensure high turnover and freshness.

[0129] The design of the inventory scheduling module 206 reflects the adaptability of the device to multi-regional and multi-time sales models. By analyzing the sales time information, the device can identify the peak sales periods of different stores. For example, for stores in commercial areas, the system may arrange to replenish before lunch break; while for stores in residential areas, it may arrange to replenish before dinner. This precise time management ensures that the fruit maintains the best quality during the peak sales period.

[0130] The device can also adjust the quality decay assessment model, space allocation strategy and replenishment time point in real time by continuously acquiring and analyzing various types of information. This dynamic adjustment mechanism enables the device to quickly respond to market changes, such as seasonal demand fluctuations or changes in sales patterns caused by emergencies.

[0131] In practical applications, the device can operate as follows: First, the first acquisition module 201 collects data from the store management system and the environmental monitoring device. For example, it may obtain information that a store has 10 kinds of fruits, including strawberries with a shelf life of 3 days and apples with a shelf life of 7 days, and the storage environment temperature is 4°C and the humidity is 85%.

[0132] Next, the model building module 202 constructs a quality decay assessment model based on this information. For strawberries, the model may set a higher basic decay coefficient, while for apples, it sets a lower coefficient. At the same time, the model also considers the impact of temperature and humidity on different fruits.

[0133] The first calculation module 203 uses this model to calculate the quality decay value of each fruit. For example, it may be concluded that the quality of strawberries decreases by 20% per day under current conditions, while the quality of apples decreases by 5% per day.

[0134] The second acquisition module 204 acquires the back-end storage space information of the store, such as a total area of ​​20 square meters, of which 15 square meters are occupied. The second calculation module 205 calculates the optimal space allocation ratio based on the quality attenuation value and the space information. A possible result is to allocate 2 square meters to strawberries and 3 square meters to apples.

[0135] Finally, the inventory scheduling module 206 determines the replenishment time point according to the sales period information and the space allocation ratio. If the store is located in a business district, the system may arrange to replenish strawberries at 10 am every day to meet the demand during the lunch break; and apples may be arranged to be replenished on Mondays and Thursdays.

[0136] Compared with the prior art, the device of the present application has significant advantages. Traditional inventory management systems usually adopt fixed replenishment cycles and inventory levels, which are difficult to cope with the challenges of rapid changes in fruit quality and diversified sales models. The device of the present application can significantly improve the freshness and sales efficiency of fruits, while reducing the loss rate, by dynamically evaluating fruit quality, optimizing space allocation, and accurately scheduling replenishment. For example, in actual applications, stores using the device may find that the loss rate of strawberries has been reduced from the original 15% to 5%, while the overall inventory turnover rate has increased by 20%.

[0137] In addition, the device of the present application has good adaptability and scalability. It can not only be applied to different types of stores (such as business district stores and community stores), but also easily add new fruit categories or adjust evaluation parameters as needed. This flexibility enables the device to continuously optimize performance and provide long-term support for the collaborative management of the fruit supply chain.

[0138] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0139] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0141] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0142] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of protection of the present application.

Claims

1. An inventory management method for supply chain collaboration, characterized in that: The method includes: S1: Obtain information on fruit categories, storage environment parameters, and sales periods of each store; S2: establishing a fruit quality attenuation assessment model according to the category information and the storage environment parameter information; S3: Calculating the quality decay value of each type of fruit according to the fruit quality decay assessment model; S4: Obtaining the back-end storage space information of each store; S5: Calculating the space allocation ratio of each type of fruit according to the quality attenuation value of the fruit and the back-end storage space information; S6: Determine the replenishment time point for each category of fruit according to the sales period information and the space allocation ratio, and generate a replenishment instruction according to the replenishment time point.

2. The inventory management method for supply chain collaboration according to claim 1, characterized in that: Step S2 includes: S21: Obtaining the basic attenuation coefficient and periodic fluctuation parameter of each category of fruit in the category information; S22: Acquire temperature parameters and humidity parameters in the storage environment parameter information; S23: establishing a basic quality attenuation model according to the basic attenuation coefficient and the periodic fluctuation parameter; S24: Calculating an environmental impact factor according to the temperature parameter and the humidity parameter; S25: performing correlation operation on the basic quality decay model and the environmental impact factors to obtain the fruit quality decay assessment model.

3. The inventory management method for supply chain collaboration according to claim 2, characterized in that: Step S25 includes: S251: Acquire the quality attenuation reference value of the basic quality attenuation model, and the correction coefficient and standard deviation parameter of the environmental impact factor; S252: performing correction calculation on the quality attenuation reference value according to the correction coefficient and the standard deviation parameter to obtain a corrected quality attenuation value; S253: Performing weighted calculation on the corrected quality decay value and the basic quality decay model to obtain the fruit quality decay assessment model.

4. The inventory management method for supply chain collaboration according to claim 3 is characterized in that: In step S2, the fruit quality attenuation assessment model is: ,in, ;in, Indicates the corrected quality decay value of the fruit at time t; represents the quality attenuation baseline value of the fruit, and k represents the basic attenuation coefficient of the fruit; α represents the periodic fluctuation amplitude of fruit quality; ω represents the periodic frequency of fruit quality; φ represents the phase difference of fruit quality, where the periodic fluctuation parameters include α, ω and φ; E(T,H) represents the environmental influencing factor; T represents the storage environment temperature value, and H represents the storage environment humidity value; Indicates the standard storage temperature value, Represents the standard storage humidity value, where the temperature parameters include T and , humidity parameters include H and ; and Indicates the correction coefficient of storage temperature and storage humidity. and Indicates the standard deviation parameter of the ambient temperature and humidity values.

5. The inventory management method for supply chain collaboration according to claim 3, characterized in that: Step S252 includes: S2521: Acquire time series data of the quality attenuation reference value; S2522: Generate an environmental impact correction matrix according to the correction coefficient and the standard deviation parameter; S2523: performing matrix multiplication operation on the time series data and the environmental impact correction matrix; S2524: Normalize the calculation result to obtain the corrected quality attenuation value.

6. The inventory management method for supply chain collaboration according to claim 1, characterized in that: Step S5 includes: According to the quality attenuation value of the fruit, the quality attenuation value of each type of fruit under the current storage condition is obtained, and according to the backstage storage space information, the total space capacity and the occupied space capacity of the backstage are obtained; S51: Obtain the number of types of the fruit and the estimated sales demand of each type of the fruit; S52: Establish a comprehensive benefit objective function for each type of fruit based on the quality attenuation value of the fruit, the total space capacity of the backstage, the occupied space capacity, the number of fruit categories, and the estimated sales demand for each type of fruit: ; Among them, the comprehensive benefit objective function satisfies the constraints: , , ; Among them, Z represents the maximum value of the comprehensive benefit target; represents the quality attenuation value of the i-th type of fruit; represents the proportion of the allocated space for the i-th type of fruit; represents the expected sales demand for the i-th type of fruit; represents the minimum allocation space ratio of the i-th type of fruit; C represents the total backfield space capacity, and O represents the occupied space capacity; , , They represent the weight factors of quality decay value, expected sales demand and allocation space ratio, n represents the number of fruit categories, and i represents the ordinal number of the fruit category; S53: Solving the allocation space ratio of each type of fruit according to the comprehensive benefit objective function.

7. The inventory management method for supply chain collaboration according to claim 1, characterized in that: Step S6 includes: S61: Acquire historical sales data and sales peak period data in the sales period information; S62: Calculating sales forecast values ​​of various types of fruits according to the historical sales data; S63: Calculate the safety inventory threshold of each category of fruit according to the sales forecast value and the space allocation ratio; S64: Establishing a replenishment time evaluation matrix based on the safety stock threshold and the sales peak period data; S65: Calculate the optimal replenishment time point for each category of fruit according to the replenishment time evaluation matrix.

8. The inventory management method for supply chain collaboration according to claim 1, characterized in that: The method further comprises: S7: Acquire real-time sensor data corresponding to the storage environment parameter information; S8: Calculating an environmental change value according to a difference between the real-time sensing data and the stored environmental parameter information; S9: When the environmental change value exceeds a preset range, generating a parameter adjustment instruction; S10: According to the parameter adjustment instruction, the parameters in the fruit quality decay assessment model are updated.

9. The inventory management method for supply chain collaboration according to claim 8, characterized in that: Step S8 includes: S81: Acquire temperature data and humidity data in the real-time sensing data; S82: Acquire preset temperature data and preset humidity data in the storage environment parameter information; S83: generating a difference matrix according to a first difference between the temperature data and the preset temperature data, and a second difference between the humidity data and the preset humidity data; S84: Calculate the environment change value according to the change trends of the first difference and the second difference in the difference matrix.

10. An inventory management device for supply chain collaboration, characterized in that: The device comprises: The first acquisition module: obtains the category information, storage environment parameter information and sales period information of each store's fruits; Model building module: building a fruit quality attenuation assessment model based on the category information and the storage environment parameter information; The first calculation module is used to calculate the quality attenuation value of each type of fruit according to the fruit quality attenuation assessment model; The second acquisition module: obtains the back-end storage space information of each store; The second calculation module calculates the space allocation ratio of each category of fruit according to the quality attenuation value of the fruit and the back-end storage space information; Inventory scheduling module: determines the replenishment time point of each category of fruit according to the sales period information and the space allocation ratio, and generates replenishment instructions according to the replenishment time point.

Images