Logistics digital management system based on AI large model

By using AI models in the logistics digital management system, integrating historical data to analyze order quantity changes, calculating influencing factors and supplementary information, the shortcomings in order quantity prediction and resource allocation of existing systems are solved, and logistics efficiency is improved.

CN119047979AInactive Publication Date: 2024-11-29CHINA NATIONAL PACKAGING IOT TECHNOLOGY CO LTD

Patent Information

Application Number
CN202411533400.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-31
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing digital logistics management system is difficult to accurately predict changes in order volume, especially under the influence of seasonal changes, holidays, promotional activities and other factors, which leads to unreasonable resource allocation and affects logistics efficiency.

Method used

Using a logistics digital management system based on AI large model, through comprehensive comparative analysis units, larger comprehensive analysis units and reduced comprehensive analysis units, historical data are integrated, order quantity changes are analyzed, influencing factors are calculated, predicted, and based on inventory quantity Related to the order quantity, generate supplementary information to ensure reasonable allocation of resources.

Benefits of technology

Accurate prediction and targeted analysis of changes in order volume are achieved, and the sudden change is quickly responded to the situation, ensuring smooth logistics operations and improving logistics efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047979A_ABST
    Figure CN119047979A_ABST
Patent Text Reader

Abstract

The invention discloses a logistics digital management system based on an AI large model, relates to the technical field of electronic data processing, and solves the technical problems of unreasonable resource allocation and influence on logistics efficiency caused by lack of a targeted analysis and processing mechanism for different order quantity change conditions. According to the invention, logistics historical data can be integrated, the comprehensive comparison and analysis unit classifies and analyzes the data, analyzes order quantity changes according to a time sequence, provides a comprehensive and accurate basis for logistics decision making, considers different factors to calculate influence factors, accurately predicts the order quantity, and carries out targeted analysis on the order quantity changes, so that the logistics decision making efficiency is improved. Different processing strategies are formulated according to the order quantity increasing and decreasing conditions, when the order quantity changes suddenly, quick response can be made, the supplement speed can be calculated or the supplement information can be generated, smooth logistics operation is ensured, and the logistics efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electronic data processing, and in particular to a logistics digital management system based on an AI big model. Background Art

[0002] In the digital age, advanced technologies such as AI big models have provided new opportunities for the transformation and upgrading of the logistics industry. Using digital technology to comprehensively manage logistics, improve logistics efficiency, reduce costs, and improve service quality has become an inevitable trend in the development of the logistics industry.

[0003] According to the publication number CN117787838B, a logistics digital management system and method based on an AI large model are disclosed, which specifically include: first, preprocessing the original logistics data, converting the preprocessed logistics data into a high-dimensional feature space, and analyzing the time series correlation of the data features to extract information that affects the decision; then, constructing a time-aware multi-layer recurrent network model, and obtaining decision information through time-aware gating units, multi-layer recurrent structures, multi-feature fusion and weighting mechanisms.

[0004] Some existing digital logistics management systems are unable to accurately predict changes in logistics order volumes when in use, especially when affected by external factors such as seasonal changes, holidays, and promotional activities. Sudden changes in order volumes are difficult to grasp, and there is a lack of targeted analysis and processing mechanisms for changes in different order volumes, which leads to irrational resource allocation and affects logistics efficiency. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a logistics digital management system based on the AI ​​big model, which solves the problem of lack of targeted analysis and processing mechanism for changes in different order quantities, resulting in unreasonable resource allocation and affecting logistics efficiency.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] The logistics digital management system based on AI big model includes:

[0008] The comprehensive comparison and analysis unit is used to analyze the logistics changes in the same period according to the historical data transmitted by the logistics information collection unit, generate an increase change result and a decrease change result, and then transmit the increase change result to the increase comprehensive analysis unit, and transmit the decrease change result to the decrease comprehensive analysis unit;

[0009] A comprehensive analysis unit for increasing the value, which is used to analyze the obtained increase change results, calculate the predicted quantity for the same period, and compare the predicted quantity with the real-time inventory quantity to generate an inventory increase signal and a normal monitoring signal, calculate the replenishment quantity for the inventory increase signal, and generate supplementary information in combination with the historical data for the same period, and transmit the supplementary information and the normal monitoring signal to the management information output unit;

[0010] The reduction comprehensive analysis unit is used to analyze the obtained reduction change results by comparing the relationship between the real-time inventory quantity and the order quantity, while generating supplementary information based on the order quantity in the historical data, and transmitting the supplementary information to the management information output unit.

[0011] Moreover, it also includes a logistics information collection unit and a management information output unit;

[0012] A logistics information collection unit, used to transmit the acquired historical data to the comprehensive comparison and analysis unit;

[0013] The management information output unit is used to display the acquired supplementary information and normal monitoring signals to the corresponding operators.

[0014] Moreover, the comprehensive comparison and analysis unit generates the increase change result and the decrease change result in a specific manner as follows:

[0015] All historical data within time T is obtained, and the historical data is classified based on the time period to obtain the historical data of the same period. Then, one group of historical data of the same period is used as the analysis target for analysis, and the order volume of the analysis target is obtained. The order volume changes in adjacent time periods are analyzed in chronological order, and the corresponding order volume change results are generated, wherein the order volume change results include: increase change results and decrease change results.

[0016] Moreover, the specific method of analyzing the enlargement change result by the enlargement comprehensive analysis unit is as follows:

[0017] Get the current time point, and at the same time get the historical data of the same period as the current time point, and calculate the impact factor based on the current time point, then get the corresponding order quantity in the historical data of the same period, and record it as the standard value, and at the same time, comprehensively calculate the standard value and the impact factor to get the predicted quantity, and the specific calculation method is: predicted quantity = standard value × impact factor, then compare the predicted quantity with the real-time inventory, and generate an inventory increase signal and a normal monitoring signal.

[0018] Moreover, the specific manner in which the enlarged comprehensive analysis unit compares the predicted quantity with the real-time inventory quantity is:

[0019] If the predicted quantity is greater than the inventory quantity, an inventory increase signal is generated and the inventory increase signal is analyzed. If the predicted quantity is less than the inventory quantity, a normal monitoring signal is generated and transmitted to the management information output unit.

[0020] Moreover, the specific method of analyzing the inventory increase signal by the said comprehensive analysis unit is as follows:

[0021] The difference between the predicted quantity and the real-time inventory is recorded as the replenishment quantity. At the same time, the corresponding replenishment time is calculated based on the replenishment quantity, and the replenishment time is calculated as follows:

[0022] Get historical data for the same period, and get the corresponding order quantity based on the historical data for the same period, then calculate the unit consumption, and the specific calculation method is: unit consumption = order quantity ÷ number of days. At the same time, get the real-time inventory, and calculate the remaining consumption time based on the real-time inventory, and the specific calculation method is: remaining consumption time = real-time inventory ÷ unit consumption. At the same time, get the order quantity mutation situation corresponding to the current time point, and the order quantity mutation situation includes: there is a mutation and there is no mutation, and analyze the order quantity mutation situation separately.

[0023] Moreover, the specific method of analyzing the sudden change of order volume by the comprehensive analysis unit is as follows:

[0024] If there is no sudden change in order quantity, the replenishment speed is calculated, and the specific calculation method is: replenishment speed = replenishment quantity ÷ replenishment time. At the same time, the time point corresponding to the remaining consumption time is taken as the starting point, and replenishment is performed evenly based on the replenishment speed as the standard, and replenishment information is generated, and then the replenishment information is transmitted to the management information output unit;

[0025] If there is a sudden change in the order volume, the time point corresponding to the remaining time is obtained, and supplementary information is generated based on the supplementary volume, and the supplementary information is transmitted to the management information output unit.

[0026] Moreover, the specific manner in which the reduction comprehensive analysis unit analyzes the reduction change result is:

[0027] The real-time inventory quantity is obtained, and the real-time inventory quantity is compared with the order quantity. If the real-time inventory quantity is greater than the order quantity, it means that the real-time inventory quantity meets the corresponding demand, and a satisfaction analysis signal is generated. On the contrary, if the real-time inventory quantity is less than the order quantity, it means that the real-time inventory quantity does not meet the corresponding demand, and a dissatisfaction analysis signal is generated. Then, the satisfaction analysis signal and the dissatisfaction analysis signal are analyzed separately.

[0028] Moreover, the specific manner in which the comprehensive analysis unit analyzes the satisfying analysis signal and the non-satisfying analysis signal respectively is:

[0029] The specific method of analyzing the satisfied analysis signal is as follows: calculating the difference between the real-time inventory quantity and the order quantity as the remaining inventory quantity, obtaining the order quantity of the next period adjacent to the current period, and then calculating the replenishment quantity of the next adjacent period based on the remaining inventory quantity, generating replenishment information, and transmitting the replenishment information to the management information output unit;

[0030] The specific method of analyzing the unsatisfied analysis signal is: calculating the difference between the real-time inventory quantity and the order quantity as the replenishment quantity, then generating replenishment information according to the replenishment quantity, and transmitting the replenishment information to the management information output unit.

[0031] The present invention provides a logistics digital management system based on AI big model. Compared with the prior art, it has the following beneficial effects:

[0032] The present invention can integrate logistics historical data through the logistics information collection unit, and the comprehensive comparison and analysis unit can classify and analyze the data, analyze the change of order volume in chronological order, and provide a comprehensive and accurate basis for logistics decision-making. The increase comprehensive analysis unit and the decrease comprehensive analysis unit are used to consider seasonal changes, holidays, promotional activities and other factors, calculate the influencing factors, and accurately predict the order volume. Through targeted analysis of the change of order volume, different processing strategies are formulated for the increase and decrease of order volume. When the order volume suddenly changes, it can respond quickly, calculate the replenishment speed or generate supplementary information, ensure the smooth operation of logistics operations, and improve logistics efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a block diagram of the system principle of the present invention;

[0034] Figure 2 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0035] 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.

[0036] For example, see Figure 1 and Figure 2 The present application provides a logistics digital management system based on an AI big model, including a logistics information collection unit, a comprehensive comparison and analysis unit, an enlarged comprehensive analysis unit, a reduced comprehensive analysis unit, and a management information output unit. Figure 1 It can be known that the above functional units are electrically connected in a unidirectional manner.

[0037] Logistics information collection unit, which is used to acquire historical data and transmit the historical data to the comprehensive comparison and analysis unit.

[0038] Comprehensive comparative analysis unit, which is used to analyze the changes in logistics in the same period based on the acquired historical data, and the specific analysis method is:

[0039] All historical data within time T are obtained, and the specific value of time T is set by the operator. For example, if the value of time T is one year, the historical data obtained is the historical data within one year. At the same time, the historical data is classified based on the time period, and the value of the time period here is set by the operator, which can be one month or two months, to obtain the historical data of the same period, and then one group of historical data of the same period is used as the analysis target for analysis, and the order volume of the analysis target is obtained at the same time, and the order volume changes of adjacent time periods are analyzed in chronological order, and the chronological order here is represented by sorting in the order of time periods. For example, if the value of the time period is one month, the months are sorted from small to large. For example, the current time point is June, and the order volume of July is further compared. If the order volume of July is greater than that of June, an increase change result is generated. If the order volume of July is less than that of June, a decrease change result is generated, and the corresponding order volume change result is generated at the same time, wherein the order volume change result includes: an increase change result and a decrease change result, and so on, the remaining historical data of the same period are analyzed;

[0040] In a specific example, for example, if the operator sets the time T to two years and the time period value to two months. The system first obtains the historical data within these two years, and then divides it into multiple two-month time period data. Then select one group of two months of historical data for analysis, assuming that the time periods corresponding to this group of data are January-February 2024 and March-April 2024. Obtain the order volume within these two time periods and analyze them in chronological order (i.e., analyze January-February 2024 first, and then analyze March-April 2024). If the order volume in the latter time period (March-April 2024) is higher than the order volume in the previous time period (January-February 2024), then the generated order volume change result is an increase change result; otherwise, it is a decrease change result.

[0041] Then the increase change result is transmitted to the increase comprehensive analysis unit, and the decrease change result is transmitted to the decrease comprehensive analysis unit.

[0042] The enlargement comprehensive analysis unit is used to analyze the obtained enlargement change results, and the specific analysis method is as follows:

[0043] Get the current time point, and at the same time get the historical data of the same period as the current time point, and calculate the impact factor based on the current time point. The impact factor here represents the change in the order volume at the current time point, including increase and decrease, such as seasonal changes, holidays, and promotional activities. When calculating the impact factor, the AI ​​big model is used for analysis, and the specific analysis method is as follows:

[0044] First, obtain a suitable model framework, and in this application, the recurrent neural network framework is selected. Then, the preprocessed historical order data and external factor data are input into the model for training. A supervised learning method can be used, with the order volume as the target variable and the external factors as the input features. The parameters of the model are continuously adjusted through optimization algorithms (such as stochastic gradient descent) so that the model can accurately predict the order volume. At the same time, the mean square error (MSE), mean absolute error (MAE) and other indicators are calculated to optimize the model;

[0045] The current time point (including specific date, whether it is a holiday, whether there is a promotion, etc.) is input into the trained AI big model. The AI ​​big model predicts the order volume at the current time point based on the input information, compares the predicted order volume with the historical order volume in the same period, and calculates the impact factor. The impact factor can be expressed as the ratio of the current predicted order volume to the historical order volume in the same period. For example, if the historical order volume in the same period is 1,000 orders and the predicted order volume is 1,200 orders, then the impact factor is 1.2, indicating that the order volume may increase.

[0046] Then, the corresponding order volume in the historical data of the same period is obtained and recorded as the standard value. At the same time, the standard value and the influencing factor are comprehensively calculated to obtain the predicted volume. The specific calculation method is: predicted volume = standard value × influencing factor;

[0047] In a specific example, for example, assuming that the current time point is mid-October 2024, the historical data for the same period in mid-October last year is found from the historical data, and the corresponding order volume is 1,000 orders, which is the standard value. After analyzing the factors such as the decline in consumption after the National Day and the increase in demand for the autumn season change at the current time point, the comprehensive impact factor is 1.2 (indicating that the order volume may increase). Then the predicted volume = 1000 × 1.2 = 1,200 orders, that is, the expected order volume in mid-October this year may be 1,200 orders.

[0048] The calculated predicted quantity is compared with the real-time inventory quantity. If the predicted quantity is greater than the inventory quantity, it means that the current real-time inventory quantity does not meet the predicted quantity. At the same time, an inventory increase signal is generated and the inventory increase signal is analyzed. If the predicted quantity is less than the inventory quantity, it means that the current real-time inventory quantity meets the predicted quantity. At the same time, a normal monitoring signal is generated and transmitted to the management information output unit.

[0049] Then, the generated inventory increase signal is analyzed, and the difference between the predicted quantity and the real-time inventory quantity is calculated as the replenishment quantity. At the same time, the corresponding replenishment time is calculated according to the replenishment quantity, and the specific calculation method is as follows:

[0050] Get the historical data of the same period, and the historical data of the same period here means the period data corresponding to the current time point. For example, if the current period is March, further get the historical data of March in the historical data, and get the corresponding order quantity based on the historical data of the same period, then calculate the unit consumption, and the specific calculation method is: unit consumption = order quantity ÷ number of days, and the default number of days here is thirty days, and get the real-time inventory at the same time, and calculate the remaining consumption time based on the real-time inventory, and the specific calculation method is: remaining consumption time = real-time inventory ÷ unit consumption;

[0051] Then, the mutation of the order volume corresponding to the current time point is analyzed, and the mutation of the order volume here means the mutation caused by holidays and promotional activities. If there is no mutation of the order volume, the replenishment speed is calculated, and the specific calculation method is: replenishment speed = replenishment volume ÷ replenishment time, and the replenishment time is expressed as the time value of the same period minus the remaining consumption time. For example, if the remaining consumption time is 20 days and the corresponding time value of the same period is 30 days, the replenishment time is 10 days. At the same time, the time point corresponding to the remaining consumption time is taken as the starting point, and the replenishment is uniformly replenished based on the replenishment speed, and the replenishment information is generated, and then the replenishment information is transmitted to the management information output unit;

[0052] For example, suppose the current time is during a promotion. First, determine whether there is a sudden change in the order volume. If there is no sudden change, for example, the current remaining consumption time is 15 days, and the time value of the same period is 25 days, then the replenishment time is 10 days. Assuming the replenishment volume is 500 pieces of goods, the replenishment speed is 500÷10=50 pieces / day.

[0053] If there is a sudden change in the order volume, the time point corresponding to the remaining time is obtained, and supplementary information is generated based on the supplementary volume, and the supplementary information is transmitted to the management information output unit.

[0054] A management information output unit is used to display the acquired normal monitoring signals and supplementary information to the corresponding operator.

[0055] Embodiment 2, as Embodiment 2 of the present invention, is implemented on the basis of Embodiment 1, and differs from Embodiment 1 in that:

[0056] The reduction comprehensive analysis unit is used to analyze the obtained reduction change results, and the specific analysis method is:

[0057] Get the real-time inventory and compare it with the order quantity. The order quantity here refers to the order quantity in the same period as the current time point. If the real-time inventory is greater than the order quantity, it means that the real-time inventory meets the corresponding demand and generates a satisfaction analysis signal. On the contrary, if the real-time inventory is less than the order quantity, it means that the real-time inventory does not meet the corresponding demand and generates a dissatisfaction analysis signal. Then analyze the satisfaction analysis signal and the dissatisfaction analysis signal respectively.

[0058] The specific method of analyzing the satisfied analysis signal is as follows: calculating the difference between the real-time inventory quantity and the order quantity as the remaining inventory quantity, obtaining the order quantity of the next period adjacent to the current period, and then calculating the replenishment quantity of the next adjacent period based on the remaining inventory quantity, generating replenishment information, and transmitting the replenishment information to the management information output unit;

[0059] The specific method of analyzing the unsatisfied analysis signal is: calculating the difference between the real-time inventory quantity and the order quantity as the replenishment quantity, then generating replenishment information according to the replenishment quantity, and transmitting the replenishment information to the management information output unit.

[0060] In a specific example, for example, the remaining inventory is calculated to be 1000-800=200 pieces. Then, the order quantity for late October is assumed to be 900 pieces. Based on the remaining inventory of 200 pieces, it can be calculated that the replenishment quantity for late October may be 900-200=700 pieces. Supplementary information such as "the expected replenishment quantity in late October is 700 pieces, and the current remaining inventory is 200 pieces" is generated and transmitted to the management information output unit.

[0061] If the real-time inventory is 700 pieces, which is less than the order quantity of 800 pieces, an unsatisfied analysis signal is generated. At this time, the calculated replenishment quantity is 800-700=100 pieces. Generate replenishment information such as "urgently replenish 100 pieces of goods to meet current demand" and transmit it to the management information output unit.

[0062] A management information output unit is used to display the acquired supplementary information to the corresponding operator.

[0063] Embodiment 3, as the embodiment 3 of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2 for implementation.

[0064] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0065] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A digital logistics management system based on AI big model, characterized by: include: The comprehensive comparison and analysis unit is used to analyze the logistics changes in the same period according to the historical data transmitted by the logistics information collection unit, generate an increase change result and a decrease change result, and then transmit the increase change result to the increase comprehensive analysis unit, and transmit the decrease change result to the decrease comprehensive analysis unit; The comprehensive analysis unit is used to analyze the obtained increase change results, calculate the predicted quantity in the same period, and compare the predicted quantity with the real-time inventory quantity to generate an inventory increase signal and a normal monitoring signal. According to the inventory increase signal, the replenishment quantity is calculated, and the supplementary information is generated in combination with the historical data in the same period, and the supplementary information and the normal monitoring signal are transmitted to the management information output unit; The reduction comprehensive analysis unit is used to analyze the obtained reduction change results by comparing the relationship between the real-time inventory quantity and the order quantity, while generating supplementary information based on the order quantity in the historical data, and transmitting the supplementary information to the management information output unit.

2. The logistics digital management system based on AI big model according to claim 1 is characterized in that: It also includes a logistics information collection unit and a management information output unit; A logistics information collection unit, used to transmit the acquired historical data to the comprehensive comparison and analysis unit; The management information output unit is used to display the acquired supplementary information and normal monitoring signals to the corresponding operators.

3. The logistics digital management system based on AI big model according to claim 1 is characterized in that: The specific manner in which the comprehensive comparison and analysis unit generates the increase change result and the decrease change result is: Obtain historical data within time T, classify historical data of the same period by time period, select a group of historical data of the same period for analysis, obtain its order volume, analyze the change of order volume in adjacent time periods in chronological order, and generate the result of increase or decrease in order volume change.

4. The logistics digital management system based on AI big model according to claim 1 is characterized in that: The specific method of analyzing the enlargement change result by the enlargement comprehensive analysis unit is as follows: Get the current time point, find the historical data of the same period as the current time point from the historical data, calculate the impact factor based on the current time point, get the order quantity corresponding to the historical data of the same period as the standard value, calculate the predicted quantity through predicted quantity = standard value × impact factor, and then compare the predicted quantity with the real-time inventory to generate an inventory increase signal or a normal monitoring signal.

5. The logistics digital management system based on AI big model according to claim 4 is characterized in that: The specific method of comparing the predicted quantity with the real-time inventory quantity by the enlarged comprehensive analysis unit is: If the predicted quantity is greater than the inventory quantity, an inventory increase signal is generated and the inventory increase signal is analyzed. If the predicted quantity is less than the inventory quantity, a normal monitoring signal is generated and transmitted to the management information output unit.

6. The logistics digital management system based on AI big model according to claim 5 is characterized in that: The specific method of analyzing the inventory increase signal by the comprehensive analysis unit is as follows: The difference between the predicted quantity and the real-time inventory is recorded as the replenishment quantity. At the same time, the corresponding replenishment time is calculated based on the replenishment quantity, and the replenishment time is calculated as follows: Get historical data for the same period, and get the corresponding order quantity based on the historical data for the same period, then calculate the unit consumption, and the calculation method is: unit consumption = order quantity ÷ number of days. At the same time, get the real-time inventory, and calculate the remaining consumption time based on the real-time inventory, and the calculation method is: remaining consumption time = real-time inventory ÷ unit consumption. At the same time, get the order quantity mutation situation corresponding to the current time point, and the order quantity mutation situation includes: there is a mutation and there is no mutation, and analyze the order quantity mutation situation separately.

7. The logistics digital management system based on AI big model according to claim 6 is characterized in that: The specific method for the comprehensive analysis unit to analyze the sudden change of order volume is as follows: If there is no sudden change in order quantity, the replenishment speed is calculated, and the specific calculation method is: replenishment speed = replenishment quantity ÷ replenishment time. At the same time, the time point corresponding to the remaining consumption time is taken as the starting point, and replenishment is performed evenly based on the replenishment speed as the standard, and replenishment information is generated, and then the replenishment information is transmitted to the management information output unit; If there is a sudden change in the order volume, the time point corresponding to the remaining time is obtained, and supplementary information is generated based on the supplementary volume, and the supplementary information is transmitted to the management information output unit.

8. The logistics digital management system based on AI big model according to claim 1 is characterized in that: The specific method in which the reduction comprehensive analysis unit analyzes the reduction change result is: The real-time inventory quantity is obtained, and the real-time inventory quantity is compared with the order quantity. If the real-time inventory quantity is greater than the order quantity, it means that the real-time inventory quantity meets the corresponding demand, and a satisfaction analysis signal is generated. On the contrary, if the real-time inventory quantity is less than the order quantity, it means that the real-time inventory quantity does not meet the corresponding demand, and a dissatisfaction analysis signal is generated. Then, the satisfaction analysis signal and the dissatisfaction analysis signal are analyzed separately.

9. The logistics digital management system based on AI big model according to claim 8 is characterized in that: The specific manner in which the comprehensive analysis unit analyzes the satisfying analysis signal and the non-satisfying analysis signal respectively is as follows: Satisfy the analysis signal: Calculate the difference between the real-time inventory and the order quantity as the remaining inventory, obtain the order quantity for the next period, calculate the replenishment quantity for the next period based on the remaining inventory, generate replenishment information and transmit it to the management information output unit; Unsatisfied analysis signal: Calculate the difference between the real-time inventory quantity and the order quantity as the replenishment quantity, and generate replenishment information based on the replenishment quantity and transmit it to the management information output unit.

Citation Information

Patent Citations

  • Logistics digital management system and method based on AI big model

    CN117787838B

  • Internet of things trade inventory management method and device

    CN114418484A

  • E-commerce order information intelligent processing system based on big data

    CN117934124A

  • System and Method for Taking Inventory and Ordering

    US20160092828A1

  • Method and system for automatic replenishment of retail enterprise store, and computer-readable storage medium

    US20220374827A1

Cited By

  • Goods circulation and transportation planning management system and method based on block chain

    CN119849810A