Intelligent cabin networked multi-cabin collaborative scheduling management system and method thereof

Abstract

The invention discloses an intelligent cabin networked multi-cabin cooperative scheduling management system and a method thereof, and relates to the technical field of camping intelligent cabins, and the method comprises the following steps: collecting various parameter information generated in the operation process of a central scheduling system, including system load management information and supply chain robustness information, and after the collection, carrying out cooperative scheduling on the system load management information and the supply chain robustness information; and processing the system load management information and the supply chain robustness information. According to the invention, the load distribution index and the supply chain breakpoint index of the central scheduling system are collected in real time, and the data evaluation index is generated, so that the operation state of the system is accurately analyzed. A high-risk state is judged by setting a threshold value, and when a data evaluation index exceeds a reference threshold value, the system immediately generates a high-risk early warning signal to prompt a potential fault or abnormality. According to the method, the response speed of the system to the abnormity is increased, supply chain unbalance or logistics interruption caused by delay is avoided, particularly under the condition of large demand fluctuation, cargo overstock or shortage can be effectively prevented, and stable operation of the supply chain is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of camping smart cabins, and in particular to a smart cabin networked multi-cabin collaborative scheduling management system and method thereof. Background Art

[0002] The smart cabin network multi-warehouse collaborative scheduling management method is based on technologies such as the Internet of Things, big data, and artificial intelligence. It realizes efficient collaboration and intelligent scheduling among multiple warehouses through a network platform. Through IoT sensors and automated equipment, the smart cabin system can collect real-time inventory status, environmental data (such as temperature, humidity, etc.), transportation equipment status, and order demand data of each warehouse. These data are transmitted to the central scheduling system through the network to form a real-time, all-round warehouse operation view. The central scheduling system uses big data analysis and artificial intelligence algorithms to optimize the scheduling of storage resources. According to the geographical location of the warehouse, the current load, and order requirements, it reasonably arranges the storage, distribution, and transportation routes of goods. At the same time, it dynamically adjusts resource allocation to ensure efficient collaborative operation of multiple warehouses and respond to emergencies, thereby achieving overall optimization of the supply chain.

[0003] In addition, the smart cabin network multi-warehouse collaborative scheduling management method uses technologies such as IoT devices, sensors, cloud computing and artificial intelligence to improve the automation and intelligence level of the system. Through the system's automated collaborative scheduling, seamless connection between warehousing and transportation can be achieved, while ensuring the efficient operation of all links in the logistics chain and reducing the need for manual intervention. This method is particularly suitable for companies with complex logistics needs, and can improve the response speed of the overall supply chain, reduce logistics costs, and optimize resource utilization.

[0004] The prior art has the following deficiencies:

[0005] However, when the central dispatch system encounters abnormal hidden dangers during operation and the system fails to perceive them in time, it may lead to a series of increasingly serious consequences, especially in the field of logistics and supply chain management, and the problem will gradually expand over time. Since the system cannot effectively monitor and dynamically optimize scheduling, the allocation of warehousing resources will become seriously unbalanced. Some warehouses may have excessive backlogs or supply shortages due to untimely updates of inventory data. For example, warehouses in high-demand areas may be out of stock due to failure to allocate goods in time, while warehouses in low-demand areas may have excess inventory due to continuous receipt of goods. This resource imbalance not only makes it impossible to meet orders in a timely manner, but also significantly increases warehousing costs and further reduces operational efficiency.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a smart cabin networked multi-warehouse collaborative scheduling management system and method thereof to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution, comprising the following steps:

[0009] Collect various parameter information generated during the operation of the central dispatching system, including system load management information and supply chain robustness information, and process the system load management information and supply chain robustness information after collection;

[0010] After processing the system load management information and the supply chain robustness information, a data analysis model is established for the system load management information and the supply chain robustness information to generate a data evaluation index;

[0011] Compare the data evaluation index generated during the operation of the central dispatching system with the pre-set data evaluation index reference threshold, generate high-risk abnormal signals or low-risk abnormal signals, and issue early warning prompts for high-risk abnormal signals;

[0012] When a high-risk abnormal signal is generated and an early warning is issued during the operation of the central dispatching system, a number of data evaluation indexes are collected, and a data set is established based on the collected data evaluation indexes. A comprehensive analysis is performed on the data evaluation indexes in the data set to comprehensively judge the operating status of the central dispatching system.

[0013] Preferably, the obtained system load management information and supply chain robustness information include a load distribution index and a supply chain breakpoint index, respectively, and the load distribution index and the supply chain breakpoint index are calibrated as I L , (T) and S(t).

[0014] Preferably, the load distribution index I L (T) The acquisition logic is as follows:

[0015] Collect the load data L of the central dispatching system in different time periods within T time i (t), T={t k}={t 1 , t 2 , t 3 ..., t n}, n represents the upper limit of time, and the available capacity C of each node is collected at the same time i (t) and the scheduling request R i (t), where L i (t) represents the load of node i at time t, C i (t) represents the available capacity of node i at time t, R i (t) represents the scheduling request amount of node i at time t;

[0016] To analyze the load anomaly, use the timing model to detect the abnormal load change rate of each node. The calculation expression is as follows: In the formula, ξ i (t) represents the abnormal load change rate, λ i (t) is the scheduling anomaly response coefficient of node i, which indicates the response sensitivity of scheduling anomaly. is the time derivative of the load, indicating the speed of change of the load;

[0017] Based on the load anomaly analysis, the load balancing value is calculated by combining the load and capacity ratio through a nonlinear function. The calculation expression is as follows: In the formula, B i (t) represents the load balancing value, θ is the response sensitivity coefficient of the scheduling system, which is used to adjust the change amplitude of the load balancing degree;

[0018] After calculating the load balance of each node, the time-weighted integration method is used to generate the load distribution index. The load balance of each node in the entire time window is comprehensively considered. The calculation expression is as follows: In the formula, I L (T) is the load sharing index, W i (t) is the weight factor of node i at time t, n represents the upper limit of time, which refers to the interval of the system from time t=0 to time t=n, and N represents the total number of nodes.

[0019] Preferably, the logic for obtaining the supply chain breakpoint index S(t) is as follows:

[0020] Real-time status monitoring is performed on each node in the supply chain at different time periods within T time, and key data parameters of each node are collected, including node load data L i (t), delay time D i (t), interruption frequency F i (t) and external risk factors N i (t); where L i (t) Node load data represents the load of node i at time t, delay time D i (t) represents the delay time of node i, and the interruption frequency F i (t) represents the frequency of interruption of node i per unit time, N j (t) represents the external risk faced by node i;

[0021] The node failure risk is evaluated through the nonlinear interaction of risk factors, considering the mutual influence between the delay, load and interruption frequency of each node. The calculation expression is as follows: In the formula, Hi (t) represents the fracture risk, i.e., the fracture risk of node i at time t, β 1 is the node load data L i The weight coefficient of (t), β 2 is the delay time D i The weight coefficient of (t), γ 1 is the interrupt frequency F i (t), δ is the weight coefficient of the external risk factor N i The weight coefficient of (t);

[0022] The breakage risks of all nodes in the entire supply chain are summarized to generate the overall supply chain breakpoint index. The calculation expression is as follows: In the formula, S(t) represents the supply chain breakpoint index, α represents the time decay rate, and e -αt represents the time decay function.

[0023] Preferably, the load distribution index I is obtained L After determining the supply chain breakpoint index S(t) and supply chain breakpoint index S(t), a data analysis model is established to generate the data evaluation index DE, based on the following formula:

[0024]

[0025] , where f 1 , f 2 They are load distribution index I L (T) and the preset coefficient of the supply chain breakpoint index S(t), and f 1 , f 2 Both are greater than 0.

[0026] Preferably, the data evaluation index generated during the operation of the central dispatching system is compared with a pre-set data evaluation index reference threshold. If the generated data evaluation index is greater than or equal to the pre-set data evaluation index reference threshold, indicating that an abnormal situation has occurred during the operation of the central dispatching system, a high-risk abnormal signal is generated, and an early warning is issued for the high-risk abnormal signal. If the generated data evaluation index is less than the pre-set data evaluation index reference threshold, indicating that the central dispatching system is operating normally and no abnormal situation has occurred, a low-risk abnormal signal is generated, and no early warning is issued for the low-risk abnormal signal.

[0027] Preferably, when a high-risk abnormal signal is generated and an early warning prompt is issued during the operation of the central dispatching system, a number of data evaluation indexes are collected, and the collected data evaluation indexes are used to establish a data set;

[0028] Find the average value DE of the data evaluation index in the data set 平均 and data evaluation index standard deviation DE 标准, and evaluate the data exponential mean DE 平均 and data evaluation index standard deviation DE 标准 The reference threshold DE of the pre-set data evaluation index average value is 参考平均 and data evaluation index standard deviation reference threshold DE 参考标准 The comparison results are as follows:

[0029] If DE 平均 ≥DE 参考平均 , indicating that the central dispatching system has an abnormality during operation, an early warning signal is generated to prompt relevant personnel to check the operating status of the central dispatching system;

[0030] like This indicates that the central dispatching system is unstable during operation. If the central dispatching system is running well or badly, an unstable signal will be generated, which will also prompt relevant personnel to check the operating status of the central dispatching system.

[0031] Ruoruo This indicates that the central dispatching system is operating stably, no abnormal situations occur, and a stable operation signal is generated.

[0032] The smart cabin network multi-warehouse collaborative dispatching management method is characterized by comprising a data acquisition module, an abnormality analysis module, a comparison module, a comprehensive analysis module and an early warning module;

[0033] The data collection module collects various parameter information generated during the operation of the central dispatching system, including system load management information and supply chain robustness information. After collection, the load management information and supply chain robustness information are processed and passed to the abnormal analysis module;

[0034] The abnormal analysis module analyzes the processed system load management information and supply chain robustness information, generates a data evaluation index, and transmits the data evaluation index to the comparison module;

[0035] The comparison module compares the data evaluation index generated during the operation of the central dispatching system with the pre-set data evaluation index reference threshold, generates a high-risk abnormal signal or a low-risk abnormal signal, and transmits the abnormal signal to the comprehensive analysis module;

[0036] The comprehensive analysis module collects several data evaluation indexes and establishes a data set based on the collected data evaluation indexes when a high-risk abnormal signal is generated and an early warning is issued during the operation of the central dispatching system. The comprehensive analysis module conducts a comprehensive analysis on the data evaluation indexes in the data set, comprehensively judges the operating status of the central dispatching system, and issues an early warning signal through the early warning module.

[0037] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0038] The present invention collects the load distribution index and supply chain breakpoint index during the operation of the central dispatching system, and generates a data evaluation index based on these parameters, so as to analyze the operating status of the system in real time. The preset threshold is used to determine whether the system is in a high-risk state, thereby achieving accurate early warning. When the data evaluation index exceeds the preset reference threshold, the system immediately generates a high-risk abnormal signal and issues an early warning prompt. This real-time and accuracy improves the system's ability to perceive potential faults or anomalies, avoids supply chain imbalances and logistics interruptions caused by delayed responses, and can effectively prevent cargo backlogs or shortages, especially when cargo demand fluctuates greatly, and ensure the stable operation of the supply chain.

[0039] After the high-risk abnormal signal is generated, the present invention further judges the stability of the system by comprehensively analyzing multiple groups of data evaluation indexes and comparing the average value and standard deviation with the preset reference value. This intelligent analysis can not only identify abnormal situations, but also detect unstable signals in time when the system state fluctuates to prevent potential system failures. Through this mechanism, the system can effectively carry out dynamic adjustment and optimization, ensuring that the central dispatching system has stronger adaptability when facing complex and changing environments, improving the reasonable allocation and dispatching efficiency of storage resources, reducing operating costs, and avoiding losses caused by system failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 This is a method flow chart of the smart cabin networked multi-warehouse collaborative scheduling management method of the present invention.

[0042] Figure 2 This is a module schematic diagram of the smart cabin networked multi-warehouse collaborative scheduling management system of the present invention. DETAILED DESCRIPTION

[0043] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0044] The present invention provides Figure 1 The illustrated smart cabin network multi-warehouse collaborative scheduling management method includes the following steps:

[0045] Collect various parameter information generated during the operation of the central dispatching system, including system load management information and supply chain robustness information, and process the system load management information and supply chain robustness information after collection;

[0046] The system load management information and supply chain robustness information obtained include load distribution index and supply chain breakpoint index, respectively. The load distribution index and supply chain breakpoint index are calibrated as I L (T) and S(t).

[0047] The load distribution index is an indicator used to measure the load balance of each resource node in the system (such as warehouses, transportation equipment, etc.). It reflects the differences in resource utilization among different nodes and indicates whether the load in the system is reasonably distributed.

[0048] Changes in the load distribution index during the operation of the central dispatching system may indeed cause the system to make incorrect judgments about storage resources and cause some warehouses to face the risk of excessive backlogs or supply shortages due to untimely inventory data updates. This is because the load distribution index reflects the resource usage of each warehouse and transportation node. When the index fluctuates violently, the system may not be able to perceive the imbalance in resource utilization in time. For example, if the load of a warehouse suddenly increases and is not handled in time, the dispatching system may continue to allocate goods to the warehouse, causing it to operate overloaded and generate backlogs. At the same time, other warehouses may be mistakenly believed to have sufficient resources due to abnormal indexes, thereby reducing the allocation of goods and causing insufficient inventory. In addition, changes in the load distribution index may also cause data lag or inaccuracy, especially when the system has not yet fully responded to the changes. Untimely updates of inventory data will exacerbate this imbalance, causing the system to make scheduling decisions based on outdated or incomplete information, further amplifying resource allocation errors. This misjudgment will have a significant impact on the overall supply chain efficiency, leading to logistics delays, increased storage costs, and weakening flexible response to market demand.

[0049] Load sharing index I L (T) The acquisition logic is as follows:

[0050] Collect the load data L of the central dispatching system in different time periods within T time i (t), T={t k}={t 1 , t 2 , t 3 ..., t n}, n represents the upper limit of time, and the available capacity C of each node is collected at the same time i (t) and the scheduling request R i (t), where L i(t) represents the load of node i at time t, C i (t) represents the available capacity of node i at time t, R i (t) represents the scheduling request amount of node i at time t;

[0051] It should be noted that load data refers to the resource usage and processing capacity of each node (such as warehouses, transportation equipment, etc.) in a specific time period in the central dispatch system. Load data is used to monitor the operating status of each node and help determine whether the allocation of resources is reasonable and whether there is a risk of overload or insufficient resources.

[0052] Common payload data types include:

[0053] Stock Load:

[0054] The actual inventory in the warehouse, including the quantity and type of specific products.

[0055] The corresponding load data represents the ratio of the warehouse inventory usage to the warehouse capacity at a certain moment.

[0056] Transport equipment load:

[0057] The carrying load of transport vehicles, freight trains, drones and other equipment indicates the ratio of the actual amount of cargo currently loaded on the equipment to its maximum carrying capacity.

[0058] Equipment processing load:

[0059] The load condition of robots or mechanical equipment during automated production or loading and unloading, such as the ratio of the number of goods processed per second by the equipment on the production line to its maximum processing capacity.

[0060] Order processing load:

[0061] During peak order periods, the load on the order processing nodes in the system refers to the volume of orders processed per unit time by the processing center, warehouse, or other order nodes.

[0062] Network and system load:

[0063] The load of the central dispatch system itself, including the processing capacity and request response time of the server or data processing system. Load data includes network bandwidth usage, processor utilization, etc.

[0064] Environmental load:

[0065] Environmental loads may also be taken into account, particularly where external factors such as warehouse temperature and humidity may affect storage conditions.

[0066] To analyze the load anomaly, use the timing model to detect the abnormal load change rate of each node. The calculation expression is as follows: In the formula, ξ i (t) represents the abnormal load change rate, λ i (t) is the scheduling anomaly response coefficient of node i, which indicates the response sensitivity of scheduling anomaly. is the time derivative of the load, indicating the speed of change of the load;

[0067] It should be noted that the time series model is a mathematical model used to analyze and predict time series data. Time series data refers to observations or data points recorded in chronological order. The time series model analyzes the historical behavior of these data to capture the trend, periodicity, volatility and randomness in them to predict the future or detect anomalies. Common time series models include autoregressive model (AR), moving average model (MA), autoregressive moving average model (ARMA), etc.

[0068] Characteristics of the timing model:

[0069] 1. Time dependency: The key feature of a time series model is that it captures the autocorrelation of data by observing its evolution over time. That is, past load data affects future load behavior, so a time series model is able to predict future trends or identify anomalies.

[0070] 2. Trends, seasonality, and noise: Time series models can identify long-term trends (such as gradual increases or decreases in load), seasonal fluctuations (cyclical changes), and random noise (irregular fluctuations) in load data.

[0071] 3. Continuity of time series: Time series data is usually recorded continuously, which enables the model to use observation data at time intervals to dynamically adjust the prediction or detection results.

[0072] Advantages of using a timing model to detect abnormal load change rates at each node:

[0073] In load management, the load change of the system is often a dynamic process over time. Therefore, the time series model is very suitable for analyzing the abnormal change rate of node load. The specific reasons are as follows:

[0074] 1. Dynamically capture load change trends: Load data changes over time, and the time series model can capture load trends and fluctuations. If the load change of a node in the system deviates from the normal change pattern, the time series model can identify this anomaly. For example, if the load of a node is usually stable, but suddenly there is a rapid increase or sharp decrease, the time series model can mark this change as an anomaly.

[0075] 2. Combined with scheduling response sensitivity: In the timing model formula In the i (t) represents the response sensitivity of scheduling anomalies. By dynamically adjusting this coefficient through historical data, the system can have different sensitivities to load changes at different nodes. For some key nodes, the system may require higher response sensitivity, and the timing model can monitor the load changes of these nodes more closely.

[0076] 3. Time derivative of load change rate: Represents the time derivative of the load, that is, the rate of change of the load over time. Through the timing model, the system can monitor in real time whether the load change rate of each node is abnormal. If the load change rate of a node deviates significantly from the normal range, such as a sudden rapid increase or decrease, the timing model can help detect this anomaly and issue an alarm.

[0077] 4. Abnormal prediction and early warning: The time series model can not only detect abnormal changes in load, but also predict future load trends based on historical data. Therefore, the system can respond in advance when load anomalies are about to occur to prevent resource overload or supply shortage.

[0078] In summary, the time series model can dynamically monitor and detect abnormal changes in load based on time dependency and changing trends in historical data, ensuring that the central dispatching system makes timely adjustments to resource allocation and avoiding the risk of imbalance in warehousing resources or supply chain disruptions.

[0079] Based on the load anomaly analysis, the load balancing value is calculated by combining the load and capacity ratio through a nonlinear function. The calculation expression is as follows: In the formula, B i (t) represents the load balancing value, θ is the response sensitivity coefficient of the scheduling system, which is used to adjust the change amplitude of the load balancing degree;

[0080] It should be noted that a nonlinear function is a function in which the relationship between the output and input is not linear, that is, a change in the input value does not cause the output value to change in the same proportion. Unlike linear functions, nonlinear functions may exhibit more complex relationships, such as power functions, exponential functions, logarithmic functions, etc., where the output value increases or decreases in a non-uniform proportion with the input value. This nonlinear relationship can often capture the dynamic characteristics of complex systems, such as monitoring the relationship between load and capacity in a central dispatch system.

[0081] Characteristics of nonlinear functions:

[0082] 1. Different proportional changes in input and output: In a nonlinear function, a small change in the input may lead to a drastic change in the output, or conversely, a significant change in the input may only cause a small change in the output.

[0083] 2. Diverse behaviors: Nonlinear functions can describe complex phenomena that linear functions cannot, such as threshold effects, rapid growth or decrease, and saturation.

[0084] 3. Asymmetry and complexity: Due to their nonlinear characteristics, this type of function can better model asymmetric situations or complex system behaviors in real systems.

[0085] Advantages of using a non-linear function to combine load and capacity ratios:

[0086] 1. Handling the nonlinear characteristics of load: In the central dispatch system, the relationship between load and capacity is not a simple linear relationship. When the load approaches the capacity limit, the pressure on the system will increase significantly, but at low loads, the impact on the system is small. Using nonlinear functions can better capture this nonlinear growth, especially when the load gradually approaches capacity. For example, the closer the load is to the maximum capacity of a warehouse or equipment, the system risk will increase exponentially, and linear functions cannot accurately capture this complex growth process.

[0087] 2. Improve the sensitivity of the dispatch system: Nonlinear functions can increase the system's sensitivity to load changes, especially under high load conditions. For example, when the load-to-capacity ratio reaches a certain critical point, the use of nonlinear functions causes the load balance to change rapidly, causing the central dispatch system to respond quickly and adjust resource allocation. This mechanism can effectively prevent overload or uneven resource allocation.

[0088] 3. Better risk assessment: By using nonlinear functions, the system can predict and handle the risks that may be caused by load changes in advance. For example, the load balancing value This formula uses an exponential function form. When the load L i (t) Approaching available capacity C i (t), the change of load balancing value will become more drastic, reflecting the greater risk of high load to the system. Here α is a tuning parameter that controls the sensitivity of the load-to-capacity ratio.

[0089] 4. Optimize system resource allocation: Nonlinear functions help the system more accurately evaluate the dynamic changes in the load-to-capacity ratio, thereby optimizing resource allocation. If the system only uses linear models, it may not be able to respond quickly when the load approaches capacity, causing system overload or crash. Nonlinear functions can detect high load risks earlier and prevent resource imbalance.

[0090] in conclusion:

[0091] Combining the load and capacity ratio through a nonlinear function can better capture and reflect the complexity of load growth in actual systems, especially the rapid changes when the load is close to capacity. It can increase the system's sensitivity to load changes, thereby optimizing scheduling decisions and preventing resource allocation imbalances or overload risks.

[0092] After calculating the load balance of each node, the time-weighted integration method is used to generate the load distribution index. The load balance of each node in the entire time window is comprehensively considered. The calculation expression is as follows: In the formula, I L (T) is the load sharing index, W i (t) is the weight factor of node i at time t, n represents the upper limit of time, which refers to the interval from time t = 0 to time t = n, and N represents the total number of nodes;

[0093] It should be noted that time-weighted integration is an integration method that assigns different weights to time during the calculation process, which is used to emphasize the different impacts of values ​​in different time periods on the overall result. Specifically, time-weighted integration not only considers the values ​​that change over time, but also adjusts the influence of values ​​at different times through a certain weight function. This weight can be a function of time, indicating that the contribution of time to a process gradually increases or decreases over time.

[0094] Features of time-weighted integration:

[0095] 1. Time dependence: Time-weighted integration assigns different weights to different time points, making changes at certain moments contribute more to the overall result. This is suitable for systems that change dynamically over time, such as load management systems.

[0096] 2. Weight adjustment: By defining a time weight function, the influence of a certain period of time on the final result can be flexibly adjusted to capture the significant features of certain key time periods in the system. For example, the time period close to the critical point of the system may be more important than the time period of stable operation.

[0097] Advantages of using time-weighted integration to generate load sharing indices

[0098] 1. Capture the dynamics of load changes: The changes in load distribution in the system are often a process that evolves over time. In a load management system, load fluctuations are not linear or constant, but rather periodic, sudden, or gradual. Time-weighted integration can better capture these changes by introducing time weights. For example, when the load approaches the upper limit of the system capacity, the time weight may increase, thereby amplifying the load impact at that moment and helping the system make timely adjustments.

[0099] 2. Distribution of the impact of historical data: The load distribution index is a comprehensive indicator that not only reflects the current load status, but also takes into account the load change trend over the past period of time. Through time-weighted integration, the system can more scientifically distribute the impact of historical data. More recent load data may be more important than earlier data, so it can be given a larger weight, while the weight of distant data gradually decays. This approach ensures that the index is more consistent with the current system status.

[0100] 3. Risk perception in advance: Time-weighted integration can help the system identify potential risks in load distribution. This design allows the system to pay more attention to load changes close to the current moment when generating the load distribution index, while reducing the impact on loads at more distant moments. This can improve the ability to perceive recent load anomalies and generate a more accurate load distribution index.

[0101] 4. Balance historical and immediate impacts: In the process of load distribution, it is necessary to consider the cumulative impact of historical loads and to keenly capture the dynamic changes of current loads. The time-weighted integration method can find a balance between the two by adjusting the time weight, avoiding over-reliance on historical data or ignoring current load fluctuations, thereby generating a more reasonable and predictable load distribution index.

[0102] in conclusion:

[0103] The main purpose of using the time-weighted integral method to generate the load distribution index is to more accurately reflect the dynamic changes of the system load in different time periods. It gives different weights to the load data at different time points, highlights those moments that have a greater impact on the system, and ensures that the load distribution index can not only reflect the historical load trend of the system, but also respond sensitively to current load changes, thereby optimizing resource allocation and preventing potential system risks.

[0104] From the load distribution index calculation expression, it can be seen that the larger the load distribution index performance value generated during the operation of the central dispatching system, the greater the deviation in the load distribution of each node in the central dispatching system, the system resource allocation may be unbalanced, and the greater the probability of abnormal load management. This abnormality may be caused by overload operation of some nodes, imbalanced resource allocation, or untimely update of inventory data, which in turn leads to a decrease in the overall operation efficiency of the system. On the contrary, the smaller the load distribution index performance value, the more reasonable and balanced the system's load distribution is, the lower the probability of abnormality is, and the system runs more smoothly.

[0105] The Supply Chain Disruption Index is an indicator that measures the continuity and robustness of each link in the supply chain, reflecting the degree of risk of rupture or bottleneck in the supply chain. The index assesses whether there is a potential risk of disruption in each link of the supply chain, such as transportation delays, insufficient supply, equipment failure, etc.

[0106] During the operation of the central dispatching system, changes in the supply chain breakpoint index may cause the system to make wrong judgments on storage resources, thereby causing the risk of excessive backlog of goods or supply shortages in some warehouses due to untimely inventory data updates. The supply chain breakpoint index measures the stability and connectivity of each link in the supply chain. When the index rises, it means that there is a risk of delay or interruption in certain nodes in the supply chain (such as transportation links and supply channels), which will affect the central dispatching system's perception of the actual flow of goods. If a link in the supply chain is interrupted, the dispatching system may not be able to accurately obtain real-time inventory and transportation data, and thus make wrong decisions. For example, the system may believe that the goods of a warehouse have not been shipped yet, and continue to allocate resources to it, resulting in a backlog of goods in the warehouse; or the system may misjudge that a warehouse has replenished its inventory, but in fact, due to a supply chain break, the goods failed to arrive in time, resulting in a shortage in the warehouse. In addition, the increase in the supply chain breakpoint index may also affect the dispatching system's prediction of global demand, causing scheduling imbalance and further exacerbating the irrationality of storage resource allocation. Therefore, the fluctuation of the supply chain breakpoint index directly affects the judgment of the dispatching system. Especially in scenarios that are highly dependent on real-time data, changes in the supply chain breakpoint index will amplify the risk of resource scheduling.

[0107] The logic for obtaining the supply chain breakpoint index S(t) is as follows:

[0108] Real-time status monitoring is performed on each node in the supply chain at different time periods within T time, and key data parameters of each node are collected, including node load data L i (t), delay time D i (t), interruption frequency F i (t) and external risk factors N i (t); where L i (t) Node load data represents the load of node i at time t, delay time D i (t) represents the delay time of node i, and the interruption frequency F i (t) represents the frequency of interruption of node i per unit time, N j (t) represents the external risk faced by node i;

[0109] The node failure risk is evaluated through the nonlinear interaction of risk factors, considering the mutual influence between the delay, load and interruption frequency of each node. The calculation expression is as follows: In the formula, H i (t) represents the fracture risk, i.e., the fracture risk of node i at time t, β 1 is the node load data L i The weight coefficient of (t), β 2 is the delay time D iThe weight coefficient of (t), γ 1 is the interrupt frequency F i (t), δ is the weight coefficient of the external risk factor N i The weight coefficient of (t);

[0110] It should be noted that the nonlinear interaction of risk factors means that the various risk factors in the assessment system are not simply linearly related, but rather determine the overall risk level of the system through complex mutual influence and amplification effects. Nonlinear interaction means that when multiple factors exist at the same time, the increase or decrease of risk will not be a linear superposition, but may cause more significant changes through certain specific combinations, and may even lead to a sudden surge in risk.

[0111] Characteristics of nonlinear interactions:

[0112] 1. Multiple factors work together: Various risk factors (such as load, delay, interruption frequency, etc.) will affect each other under certain conditions, and different combinations may produce greater risks.

[0113] 2. Synergistic effect: Some risk factors can have an amplifying effect when they interact with each other. For example, when the load is high and the delay time is long, the two may jointly increase the vulnerability of the system and bring greater risks than when they act alone.

[0114] 3. Threshold effect: Nonlinear relationships usually mean that when the risk factor reaches a certain critical point, the risk of the system will rise rapidly instead of increasing proportionally.

[0115] Advantages of using nonlinear interactions of risk factors to assess fracture risk:

[0116] 1. Closer to reality: Risks in real systems often manifest as complex, nonlinear interactions. For example, the relationship between delay and load in a warehouse system is often nonlinear. When the load is small, the increase in delay has little impact on the system, but when the load approaches the limit, the delay will quickly cause the system to fail. Therefore, nonlinear interactions can more accurately reflect the complex risk mechanisms in reality.

[0117] 2. Capturing sudden risks: Linear models cannot effectively capture sudden system collapses, while nonlinear models can explain system disruptions caused by the simultaneous action of multiple risk factors. For example, when load, delay, and interruption frequency reach a certain threshold at the same time, the supply chain may experience large-scale disruptions in a short period of time, and nonlinear interactions can reveal these potential high-risk points.

[0118] 3. Improve prediction accuracy: Through nonlinear interactions, the risk of disruption can be predicted more accurately. When the load on a certain node is too high or the delay time increases, the nonlinear model can more sensitively reflect its impact on the entire supply chain, helping companies take measures in advance to avoid supply chain disruptions.

[0119] 4. Dealing with complexity: The sources of risk in the supply chain are diverse and intertwined. The use of nonlinear models can fully consider the complex relationships between these factors, avoid simplified analysis, and thus more comprehensively assess the vulnerability and stability of the system.

[0120] Therefore, using the nonlinear interactions of risk factors to assess disruption risk can better reflect the dynamic changes in complex systems, capture high-risk areas, and provide more effective decision support for supply chain management.

[0121] The breakage risks of all nodes in the entire supply chain are summarized to generate the overall supply chain breakpoint index. The calculation expression is as follows: In the formula, S(t) represents the supply chain breakpoint index, α represents the time decay rate, and e -αt represents the time decay function;

[0122] From the calculation expression of the supply chain breakpoint index, it can be seen that the larger the performance value of the supply chain breakpoint index generated during the operation of the central dispatching system, the higher the vulnerability of the supply chain in the current operating state, and the probability of abnormalities in the central dispatching system also increases. The breakpoint index is generated by abnormal analysis of the supply chain robustness information, reflecting the risk of breakage of each node when it is subject to external or internal interference. As the breakpoint index increases, key nodes or resource allocation in the supply chain may be unbalanced, which may lead to the system's inability to normally dispatch and coordinate various storage resources. Conversely, the smaller the performance value of the breakpoint index, the higher the robustness of the supply chain, and the possibility of abnormalities in the central dispatching system during operation is relatively low, indicating that the system as a whole is in a more stable and controlled state.

[0123] It should be noted that the above T time is selected as a relatively short time period. The time within the time period is not specifically limited here and can be set according to actual conditions. Its purpose is to monitor the situation during the network operation within the T time, so as to monitor the situation in different time periods (T time) during the network operation in this way;

[0124] After processing the system load management information and the supply chain robustness information, a data analysis model is established for the system load management information and the supply chain robustness information to generate a data evaluation index;

[0125] Get the load distribution index I LAfter determining the supply chain breakpoint index S(t) and supply chain breakpoint index S(t), a data analysis model is established to generate the data evaluation index DE, based on the following formula:

[0126]

[0127] , where f 1 , f 2 They are load distribution index I L (T) and the preset coefficient of the supply chain breakpoint index S(t), and f 1 , f 2 Both are greater than 0.

[0128] It can be seen from the calculation expression of the data evaluation index that the larger the performance value of the load distribution index generated during the operation of the central dispatching system, the larger the performance value of the supply chain breakpoint index, and the larger the performance value of the data evaluation index, indicating that the probability of abnormalities occurring during the operation of the central dispatching system is greater; the smaller the performance value of the load distribution index generated during the operation of the central dispatching system, the smaller the performance value of the supply chain breakpoint index, and the smaller the performance value of the data evaluation index, indicating that the probability of abnormalities occurring during the operation of the central dispatching system is smaller.

[0129] Compare the data evaluation index generated during the operation of the central dispatching system with the pre-set data evaluation index reference threshold, generate high-risk abnormal signals or low-risk abnormal signals, and issue early warning prompts for high-risk abnormal signals;

[0130] The data evaluation index generated during the operation of the central dispatching system is compared with the pre-set data evaluation index reference threshold. If the generated data evaluation index is greater than or equal to the pre-set data evaluation index reference threshold, indicating that an abnormal situation occurs during the operation of the central dispatching system, a high-risk abnormal signal is generated, and an early warning is issued for the high-risk abnormal signal. If the generated data evaluation index is less than the pre-set data evaluation index reference threshold, indicating that the central dispatching system operates normally and no abnormal situation occurs, a low-risk abnormal signal is generated, and no early warning is issued for the low-risk abnormal signal;

[0131] When a high-risk abnormal signal is generated and an early warning is issued during the operation of the central dispatching system, a number of data evaluation indexes are collected, and a data set is established based on the collected data evaluation indexes. A comprehensive analysis is performed on the data evaluation indexes in the data set to comprehensively judge the operating status of the central dispatching system.

[0132] When a high-risk abnormal signal is generated during the operation of the central dispatching system and an early warning prompt is issued, a number of data evaluation indexes are collected and a data set is established based on the collected data evaluation indexes;

[0133] Find the average value DE of the data evaluation index in the data set 平均and data evaluation index standard deviation DE 标准 , and evaluate the data exponential mean DE 平均 and data evaluation index standard deviation DE 标准 The reference threshold DE of the pre-set data evaluation index average value is 参考平均 and data evaluation index standard deviation reference threshold DE 参考标准 The comparison results are as follows:

[0134] If DE 平均 ≥DE 参考平均 , indicating that the central dispatching system has an abnormality during operation, an early warning signal is generated to prompt relevant personnel to check the operating status of the central dispatching system;

[0135] like This indicates that the central dispatching system is unstable during operation. If the central dispatching system is running well or badly, an unstable signal will be generated, which will also prompt relevant personnel to check the operating status of the central dispatching system.

[0136] Ruoruo This indicates that the central dispatching system is operating stably, no abnormal situations occur, and a stable operation signal is generated.

[0137] The present invention collects the load distribution index and supply chain breakpoint index during the operation of the central dispatching system, and generates a data evaluation index based on these parameters, so as to analyze the operating status of the system in real time. The preset threshold is used to determine whether the system is in a high-risk state, thereby achieving accurate early warning. When the data evaluation index exceeds the preset reference threshold, the system immediately generates a high-risk abnormal signal and issues an early warning prompt. This real-time and accuracy improves the system's ability to perceive potential faults or anomalies, avoids supply chain imbalances and logistics interruptions caused by delayed responses, and can effectively prevent cargo backlogs or shortages, especially when cargo demand fluctuates greatly, and ensure the stable operation of the supply chain.

[0138] After the high-risk abnormal signal is generated, the present invention further judges the stability of the system by comprehensively analyzing multiple groups of data evaluation indexes and comparing the average value and standard deviation with the preset reference value. This intelligent analysis can not only identify abnormal situations, but also detect unstable signals in time when the system state fluctuates to prevent potential system failures. Through this mechanism, the system can effectively carry out dynamic adjustment and optimization, ensuring that the central dispatching system has stronger adaptability when facing complex and changing environments, improving the reasonable allocation and dispatching efficiency of storage resources, reducing operating costs, and avoiding losses caused by system failures.

[0139] The present invention provides Figure 2The smart cabin networked multi-warehouse collaborative dispatching management system shown includes a data collection module, an abnormality analysis module, a comparison module, a comprehensive analysis module and an early warning module;

[0140] The data collection module collects various parameter information generated during the operation of the central dispatching system, including system load management information and supply chain robustness information. After collection, the load management information and supply chain robustness information are processed and passed to the abnormal analysis module;

[0141] The abnormal analysis module establishes a data analysis model for the processed system load management information and supply chain robustness information, generates a data evaluation index, and transmits the data evaluation index to the comparison module;

[0142] The comparison module compares the data evaluation index generated during the operation of the central dispatching system with the pre-set data evaluation index reference threshold, generates a high-risk abnormal signal or a low-risk abnormal signal, and transmits the abnormal signal to the comprehensive analysis module;

[0143] The comprehensive analysis module collects several data evaluation indexes and establishes a data set based on the collected data evaluation indexes when a high-risk abnormal signal is generated and an early warning is issued during the operation of the central dispatching system. The comprehensive analysis module conducts a comprehensive analysis on the data evaluation indexes in the data set, comprehensively judges the operating status of the central dispatching system, and issues an early warning signal through the early warning module.

[0144] The smart cabin networked multi-warehouse collaborative scheduling and management system provided by the embodiment of the present invention is realized through the above-mentioned smart cabin networked multi-warehouse collaborative scheduling and management method. The smart cabin networked multi-warehouse collaborative scheduling and management method and process are detailed in the embodiment of the above-mentioned smart cabin networked multi-warehouse collaborative scheduling and management method, which will not be repeated here.

[0145] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. The smart cabin network multi-warehouse collaborative scheduling management method is characterized by: The following steps are involved: Collect various parameter information generated during the operation of the central dispatching system, including system load management information and supply chain robustness information, and process the system load management information and supply chain robustness information after collection; After processing the system load management information and the supply chain robustness information, a data analysis model is established for the system load management information and the supply chain robustness information to generate a data evaluation index; Compare the data evaluation index generated during the operation of the central dispatching system with the pre-set data evaluation index reference threshold, generate high-risk abnormal signals or low-risk abnormal signals, and issue early warning prompts for high-risk abnormal signals; When a high-risk abnormal signal is generated and an early warning is issued during the operation of the central dispatching system, a number of data evaluation indexes are collected, and a data set is established based on the collected data evaluation indexes. A comprehensive analysis is performed on the data evaluation indexes in the data set to comprehensively judge the operating status of the central dispatching system.

2. The smart cabin network multi-warehouse collaborative scheduling management method according to claim 1 is characterized by: The system load management information and supply chain robustness information obtained include load distribution index and supply chain breakpoint index, respectively. The load distribution index and supply chain breakpoint index are calibrated as I L (T) and S(t).

3. The smart cabin network multi-warehouse collaborative scheduling management method according to claim 2 is characterized by: Load sharing index I L (T) The acquisition logic is as follows: Collect the load data L of the central dispatching system in different time periods within T time i (t), T={t k }={t1,t2,t3……,t n }, n represents the upper limit of time, and the available capacity C of each node is collected at the same time i (t) and the scheduling request R i (t), where L i (t) represents the load of node i at time t, C i (t) represents the available capacity of node i at time t, R i (t) represents the scheduling request amount of node i at time t; To analyze the load anomaly, use the timing model to detect the abnormal load change rate of each node. The calculation expression is as follows: In the formula, ξ i (t) represents the abnormal load change rate, λ i (t) is the scheduling anomaly response coefficient of node i, which indicates the response sensitivity of scheduling anomaly. is the time derivative of the load, indicating the speed of change of the load; Based on the load anomaly analysis, the load balancing value is calculated by combining the load and capacity ratio through a nonlinear function. The calculation expression is as follows: In the formula, B i (t) represents the load balancing value, θ is the response sensitivity coefficient of the scheduling system, which is used to adjust the change amplitude of the load balancing degree; After calculating the load balance of each node, the time-weighted integration method is used to generate the load distribution index. The load balance of each node in the entire time window is comprehensively considered. The calculation expression is as follows: In the formula, I L (T) is the load sharing index, W i (t) is the weight factor of node i at time t, which refers to the interval of the system from time t = 0 to time t = n, and N represents the total number of nodes.

4. The smart cabin network multi-warehouse collaborative scheduling management method according to claim 2 is characterized by: The logic for obtaining the supply chain breakpoint index S(t) is as follows: Real-time status monitoring is performed on each node in the supply chain at different time periods within T time, and key data parameters of each node are collected, including node load data L i (t), delay time D i (t), interruption frequency F i (t) and external risk factors N i (t); where L i (t) Node load data represents the load of node i at time t, delay time D i (t) represents the delay time of node i, and the interruption frequency F i (t) represents the frequency of interruption of node i per unit time, N i (t) represents the external risk faced by node i; The node failure risk is evaluated through the nonlinear interaction of risk factors, considering the mutual influence between the delay, load and interruption frequency of each node. The calculation expression is as follows: In the formula, H i (t) represents the fracture risk, i.e., the fracture risk of node i at time t, and β1 is the node load data L i (t), β2 is the delay time D i (t), γ1 is the interruption frequency F i (t), δ is the weight coefficient of the external risk factor N i The weight coefficient of (t); The breakage risks of all nodes in the entire supply chain are summarized to generate the overall supply chain breakpoint index. The calculation expression is as follows: In the formula, S(t) represents the supply chain breakpoint index, α represents the time decay rate, and e -αt represents the time decay function.

5. The smart cabin network multi-warehouse collaborative scheduling management method according to claim 4 is characterized by: Get the load distribution index I L After determining the supply chain breakpoint index S(t) and supply chain breakpoint index S(t), a data analysis model is established to generate the data evaluation index DE, based on the following formula: ， Where f1 and f2 are load distribution index I respectively. L (T) and the preset coefficients of the supply chain breakpoint index S(t), and both f1 and f2 are greater than 0.

6. The smart cabin network multi-warehouse collaborative scheduling management method according to claim 5 is characterized by: The data evaluation index generated during the operation of the central dispatching system is compared with the pre-set data evaluation index reference threshold. If the generated data evaluation index is greater than or equal to the pre-set data evaluation index reference threshold, indicating that an abnormal situation has occurred during the operation of the central dispatching system, a high-risk abnormal signal is generated and an early warning is issued for the high-risk abnormal signal. If the generated data evaluation index is less than the pre-set data evaluation index reference threshold, indicating that the central dispatching system is operating normally and no abnormal situation has occurred, a low-risk abnormal signal is generated and no early warning is issued for the low-risk abnormal signal.

7. The smart cabin network multi-warehouse collaborative scheduling management method according to claim 6 is characterized by: When a high-risk abnormal signal is generated during the operation of the central dispatching system and an early warning prompt is issued, a number of data evaluation indexes are collected and a data set is established based on the collected data evaluation indexes; Find the average value DE of the data evaluation index in the data set 平均 and data evaluation index standard deviation DE 标准 , and evaluate the data exponential mean DE 平均 and data evaluation index standard deviation DE 标准 The reference threshold DE of the pre-set data evaluation index average value is 参考平均 and data evaluation index standard deviation reference threshold DE 参考标准 The comparison results are as follows: If DE 平均 ≥DE 参考平均 , indicating that the central dispatching system has an abnormality during operation, an early warning signal is generated to prompt relevant personnel to check the operating status of the central dispatching system; like This indicates that the central dispatching system is unstable during operation. If the central dispatching system is running well or badly, an unstable signal will be generated, which will also prompt relevant personnel to check the operating status of the central dispatching system. Ruoruo This indicates that the central dispatching system is operating stably, no abnormal situations occur, and a stable operation signal is generated.

8. A smart cabin networked multi-warehouse collaborative dispatching management system, used to implement the smart cabin networked multi-warehouse collaborative dispatching management method described in any one of claims 1 to 7, characterized in that: Including data collection module, abnormal analysis module, comparison module, comprehensive analysis module and early warning module; The data collection module collects various parameter information generated during the operation of the central dispatching system, including system load management information and supply chain robustness information. After collection, the load management information and supply chain robustness information are processed and passed to the abnormal analysis module; The abnormal analysis module analyzes the processed system load management information and supply chain robustness information, generates a data evaluation index, and transmits the data evaluation index to the comparison module; The comparison module compares the data evaluation index generated during the operation of the central dispatching system with the pre-set data evaluation index reference threshold, generates a high-risk abnormal signal or a low-risk abnormal signal, and transmits the abnormal signal to the comprehensive analysis module; The comprehensive analysis module collects several data evaluation indexes and establishes a data set based on the collected data evaluation indexes when a high-risk abnormal signal is generated and an early warning is issued during the operation of the central dispatching system. The comprehensive analysis module conducts a comprehensive analysis on the data evaluation indexes in the data set, comprehensively judges the operating status of the central dispatching system, and issues an early warning signal through the early warning module.

Images