Automatic sorting and conveying method and system for logistics
Through the combination of reinforcement learning algorithm and ARIMA model, the intelligence and automation of the logistics sorting system are realized, dynamically optimized sorting paths and predicted cargo flow, solving the problem of the existing system's efficiency decline in complex environments, and improving sorting Efficiency and accuracy reduce costs and error rates.
Patent Information
- Application Number
- CN202411135663.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-12-13
AI Technical Summary
The existing logistics sorting system lacks flexibility and adaptability and cannot dynamically optimize the sorting path, resulting in a decrease in sorting efficiency when complex logistics environments change.
Using reinforcement learning algorithms and ARIMA models, intelligent sorting is achieved by automatically identifying cargo information, dynamically optimizing sorting paths and predicting cargo flow. The reinforcement learning algorithm initializes the Q table, selects actions and updates the Q value, and the ARIMA model predicts future cargo flows, adjusts sorting strategies and resource allocation.
It significantly improves sorting efficiency, reduces error rates, improves the accuracy and reliability of the system, maintains efficient operation in complex environments, and reduces operating costs through forward-looking resource management, meets customer needs, and enhances market competitiveness.
Smart Images
Figure CN119130279A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of logistics sorting, and in particular relates to a logistics automatic sorting and conveying method and system. Background Art
[0002] Logistics sorting is a crucial link in the modern logistics system. It mainly refers to the process of quickly and accurately classifying and distributing various goods in a logistics center or warehouse according to certain rules and standards. The efficiency and accuracy of logistics sorting are directly related to the speed and quality of logistics distribution, and are of great significance to improving the overall operational efficiency of the supply chain. Logistics sorting systems usually include three parts: automation equipment, information processing systems, and manual operations. Automation equipment such as sorting robots, conveyor belts, slides, etc. can realize the rapid handling and classification of goods; the information processing system collects goods information in real time through barcode recognition, RFID technology and other means to provide data support for sorting; manual operations are responsible for monitoring the entire sorting process to ensure the accuracy of sorting.
[0003] However, the sorting systems in the prior art usually rely on preset rules or require manual adjustment of the sorting path, which results in a lack of flexibility and adaptability. When faced with complex changes in the logistics environment, such as congestion at the sorting port or changes in the type of goods, these systems cannot dynamically optimize the sorting path, thus affecting the sorting efficiency. Summary of the invention
[0004] The purpose of the present invention is to provide a method and system for automatic logistics sorting and conveying in order to solve the above-mentioned problems.
[0005] The technical solution adopted by the present invention is as follows: a method for automatic logistics sorting and conveying, comprising the following steps:
[0006] S1: The incoming goods area receives goods. After the goods arrive at the incoming goods area, the goods information is automatically identified by the automated scanning equipment; the goods are unloaded from the transport vehicle to the receiving platform of the incoming goods area using automated loading and unloading equipment;
[0007] S2: Cargo information registration. Cargo information is uploaded to the central control system through a scanning device. The central control system registers the cargo information and assigns a unique identification code to each piece of cargo.
[0008] S3: The conveyor line automatically transports the goods. The goods are placed on the conveyor line, and the conveyor line starts to transport the goods to the sorting area. The sensors on the conveyor line ensure that the goods move forward correctly without deviation or accumulation.
[0009] S4: Cargo identification in the sorting area: When the cargo arrives at the sorting area, the cargo information is reconfirmed through a high-resolution camera or sensor; the central control system generates sorting instructions based on the cargo information;
[0010] S5: Perform automatic sorting operations. The sorting mechanical arm or sorting robot grabs or pushes the goods to the corresponding sorting port according to the instructions. The sorting equipment guides the goods to the designated sorting lane, adds intelligent algorithms to improve the performance of the system, realizes dynamic sorting path optimization through reinforcement learning algorithms, and uses ARIMA models to predict cargo flow through time series analysis to achieve intelligent sorting.
[0011] S6: Sorting completion confirmation: the sorted goods are confirmed to have been sorted correctly through sensors; the sorting results are fed back to the central control system to update the goods status;
[0012] S7: Automatic packaging in the packaging area. When the goods arrive at the packaging area, the automatic packaging machine will pack them according to the size and shape of the goods. The information of the packed goods will be collected again and uploaded to the central control system.
[0013] S8: The shipping area is ready for shipment. The packaged goods are sent to the designated location of the shipping area through the conveyor line. The automated equipment in the shipping area loads the goods onto the shipping vehicle.
[0014] S9: Shipping information update. After the goods are loaded, the central control system updates the shipping information. The shipping information is notified to the customer through the logistics management system, completing the entire logistics automatic sorting and transportation process.
[0015] In a preferred embodiment, in step S1, a plurality of parallel unloading points are set in the cargo area, and each unloading point is equipped with corresponding automated scanning and loading and unloading equipment; during the unloading process, the system will monitor the cargo flow in the cargo area in real time, and dynamically assign the tasks of the unmanned forklifts through the intelligent scheduling system to ensure that all cargo can be quickly and accurately unloaded from the transport vehicle to the receiving platform; at the same time, the environmental monitoring system of the cargo area will monitor the temperature and humidity to ensure that the cargo is in a suitable environment waiting for the next step of processing.
[0016] In a preferred embodiment, in step S2, during the cargo information registration process, the central control system not only registers the cargo information, but also performs data analysis, including the type, volume, weight, and destination of the cargo; the system will perform classification management based on this information, and provide data support for subsequent sorting and packaging processes; in addition, the system will also conduct risk assessments on the cargo, and take additional protective measures for fragile or valuable cargo; the allocation of identification codes uses encryption technology to ensure the uniqueness and security of the cargo throughout the entire logistics process.
[0017] In a preferred embodiment, in step S4, in the cargo identification link in the sorting area, the identification system composed of high-resolution cameras and sensors is highly fault-tolerant and can accurately identify cargo under different lighting and environments; when generating sorting instructions, the central control system will consider the priority of the cargo and the real-time status of the sorting port to optimize the sorting efficiency; the system can also predict possible sorting errors based on historical data and take preventive measures in advance.
[0018] In a preferred embodiment, in step S6, during the sorting completion confirmation process, the sensor not only confirms that the goods have been sorted correctly, but also checks the integrity of the goods; after the sorting results are fed back to the central control system, the system will perform data analysis, evaluate the sorting efficiency and quality, and provide a basis for continuously improving the sorting process; at the same time, the system will automatically record abnormal situations in the sorting process for subsequent analysis and processing.
[0019] In a preferred embodiment, in step S5, the specific steps of implementing dynamic sorting path optimization by reinforcement learning algorithm include:
[0020] Initialize Q-table: Create a Q-table containing the Q-values of all possible sorting states and actions;
[0021] Select action: In the current state, select an action based on the Q value and ε-greedy exploration strategy;
[0022] Perform actions and observe rewards: Perform the selected actions and observe the reward values given by the system;
[0023] Update Q value: Update Q value according to the following formula;
[0024] Repeat steps: Return to step 2 until the system reaches a stable state;
[0025] The formula for updating the Q value is:
[0026] Q(s,a)←Q(s,a)+α*(r+γ*max(Q(s',a'))-Q(s,a));
[0027] Where: Q(s,a) represents the Q value of taking action a in state s; α represents the learning rate, ranging from 0 to 1, indicating the weight of new information; r represents the immediate reward obtained after performing action a; γ represents the discount factor, ranging from 0 to 1, indicating the importance of future rewards; max(Q(s',a')) represents the maximum Q value of all possible actions in the next state s'.
[0028] In a preferred embodiment, in step S5, predictive sorting is achieved by time series analysis, and the ARIMA model is used to predict the cargo flow, and the specific steps include:
[0029] Data collection: Collect historical sorting data, including timestamps and cargo flow information;
[0030] Data preprocessing: cleaning data, dealing with missing values and outliers;
[0031] Model fitting: Fitting the ARIMA model using historical data;
[0032] Predict future traffic: Use the fitted model to predict future cargo traffic;
[0033] Adjust sorting strategy: adjust sorting strategy and resource allocation according to prediction results;
[0034] The ARIMA (p, d, q) model consists of the following three parts:
[0035] Autoregressive term (AR): (1-φ1L-φ2L^2-…-φp*L^p);
[0036] Difference term (I): (1-L)^d
[0037] Moving average (MA): (1-θ1L-θ2L^2-…-θq*L^q)
[0038] Where: L is the lag operator, L^k*X_t=X_{tk};
[0039] p is the order of the autoregressive term;
[0040] d is the number of differences;
[0041] q is the order of the moving average term;
[0042] φ1, φ2,…, φp are autoregressive coefficients;
[0043] θ1,θ2,…,θq are moving average coefficients;
[0044] X_t is the value of the time series at time t;
[0045] ε_t is the error term at time t.
[0046] In a preferred embodiment, in step S5, the specific steps of the intelligent sorting operation include:
[0047] S1. Use the ARIMA model to predict cargo flow in the future;
[0048] S2. Initialize the Q table based on the prediction results and set the expected state of the sorting system;
[0049] S3. At the beginning of each sorting cycle, the optimal sorting path is selected according to the current state and Q value;
[0050] S4. Perform sorting actions and collect instant feedback rewards from the system;
[0051] S5. Update the Q value using the Q-learning formula;
[0052] S6. Repeat steps S3-S5 until the sorting cycle ends;
[0053] S7. According to the performance of the sorting cycle, adjust the ARIMA model parameters to more accurately predict future cargo flows.
[0054] In a preferred embodiment, in step S8, when the shipping area is ready to ship, the conveyor line will sort the goods according to the destination and priority of the goods to ensure that the goods are loaded onto the shipping vehicle in the correct order; the automated equipment in the shipping area adopts a collaborative operation mode to improve loading efficiency; the management system of the shipping area will monitor the loading progress of the goods in real time and connect with the transportation management system to ensure that the goods are shipped on time;
[0055] In step S9, during the delivery information update phase, the central control system will generate an electronic waybill while updating the delivery information, and communicate with the customer in real time through the logistics management system; the system will also provide customers with logistics tracking services based on the transportation trajectory and estimated arrival time of the goods; in addition, the system will summarize the entire logistics process, collect feedback information, and provide data support for the continuous optimization of logistics services.
[0056] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0057] 1. In the present invention, the reinforcement learning algorithm enables the sorting system to autonomously learn and optimize the sorting path, thereby significantly improving the sorting efficiency. Traditional sorting systems often rely on preset rules or manual adjustments, while the reinforcement learning algorithm can continuously adjust and optimize the sorting strategy based on feedback from actual operations. The application of the reinforcement learning algorithm helps to reduce the sorting error rate. In the logistics sorting process, incorrect sorting can lead to serious economic losses and reduced customer satisfaction. Through reinforcement learning, the system can learn from the results of each sorting and reduce the occurrence of repeated errors. The algorithm can identify the key factors that lead to sorting errors and avoid them in future sorting decisions. This continuous learning and improvement process continuously improves the accuracy and reliability of the sorting system, thereby improving the service quality of the entire logistics system.
[0058] 2. In the present invention, the ARIMA model can provide accurate cargo flow forecasts for the sorting system, which is crucial for resource allocation and process planning. By predicting the cargo flow in the future, the sorting system can prepare resources in advance, such as adjusting the number of sorting personnel, optimizing equipment utilization, etc. This forward-looking resource management not only improves sorting efficiency, but also reduces operating costs. It can also provide customized sorting solutions based on the characteristics and needs of different goods. In this way, the logistics center can better meet customer needs, improve customer satisfaction, and enhance its own market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] Figure 1 It is a schematic diagram of the process principle of the present invention. DETAILED DESCRIPTION
[0060] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0061] Example:
[0062] Reference Figure 1 ,
[0063] A method for automatic logistics sorting and conveying, comprising the following steps:
[0064] S1: The incoming goods area receives the goods. After the goods arrive at the incoming goods area, the goods information is automatically identified by automated scanning equipment (such as barcode scanners or RFID readers). Automated loading and unloading equipment (such as unmanned forklifts) is used to unload the goods from the transport vehicle to the receiving platform in the incoming goods area;
[0065] S2: Cargo information registration, cargo information is uploaded to the central control system through a scanning device. The central control system registers the cargo information and assigns a unique identification code to each piece of cargo;
[0066] S3: The conveyor line automatically transports the goods. The goods are placed on the conveyor line, and the conveyor line starts to transport the goods to the sorting area. The sensors on the conveyor line ensure that the goods move forward correctly without deviation or accumulation;
[0067] S4: Cargo identification in the sorting area: When the cargo arrives at the sorting area, the cargo information is reconfirmed through a high-resolution camera or sensor. The central control system generates sorting instructions based on the cargo information;
[0068] S5: Automatic sorting operation is performed, and the sorting mechanical arm or sorting robot grabs or pushes the goods to the corresponding sorting port according to the instructions. The sorting equipment guides the goods to the designated sorting lane, adds intelligent algorithms to improve the performance of the system, realizes dynamic sorting path optimization through reinforcement learning algorithms, and uses ARIMA models to predict cargo flow through time series analysis to achieve intelligent sorting;
[0069] S6: Sorting completion confirmation: the sorted goods are confirmed to have been sorted correctly through sensors. The sorting results are fed back to the central control system to update the goods status;
[0070] S7: Automatic packaging in the packaging area. When the goods arrive at the packaging area, the automatic packaging machine will pack them according to the size and shape of the goods. The information of the packed goods is collected again and uploaded to the central control system;
[0071] S8: The shipping area is ready for shipment, and the packaged goods are sent to the designated location of the shipping area through the conveyor line. The automated equipment in the shipping area (such as unmanned forklifts) loads the goods onto the shipping vehicle;
[0072] S9: Shipping information update: After the goods are loaded, the central control system updates the shipping information. The shipping information is notified to the customer through the logistics management system, completing the entire logistics automatic sorting and delivery process.
[0073] In step S1, multiple parallel unloading points are set up in the cargo area, and each unloading point is equipped with corresponding automated scanning and loading and unloading equipment. During the unloading process, the system will monitor the cargo flow in the cargo area in real time, and dynamically assign the tasks of unmanned forklifts through the intelligent scheduling system to ensure that all cargo can be quickly and accurately unloaded from the transport vehicle to the receiving platform. At the same time, the environmental monitoring system of the cargo area will monitor key indicators such as temperature and humidity to ensure that the cargo is in a suitable environment waiting for the next step of processing.
[0074] In step S2, during the cargo information registration process, the central control system not only registers cargo information, but also performs data analysis, including cargo type, volume, weight, destination, etc. The system will classify and manage based on this information, and provide data support for subsequent sorting and packaging. In addition, the system will also conduct risk assessments on cargo and take additional protective measures for fragile or valuable cargo. The allocation of identification codes uses encryption technology to ensure the uniqueness and security of cargo throughout the entire logistics process.
[0075] In step S4, in the cargo identification link of the sorting area, the identification system composed of high-resolution cameras and sensors is highly fault-tolerant and can accurately identify cargo under different lighting and environments. When generating sorting instructions, the central control system will consider the priority of the cargo and the real-time status of the sorting port to optimize the sorting efficiency. The system can also predict possible sorting errors based on historical data and take preventive measures in advance.
[0076] In step S6, during the sorting completion confirmation process, the sensor not only confirms that the goods have been sorted correctly, but also checks the integrity of the goods. After the sorting results are fed back to the central control system, the system will analyze the data, evaluate the sorting efficiency and quality, and provide a basis for continuous improvement of the sorting process. At the same time, the system will automatically record abnormal situations in the sorting process for subsequent analysis and processing.
[0077] In step S5, the specific steps of implementing dynamic sorting path optimization through reinforcement learning algorithm include:
[0078] Initialize Q-table: Create a Q-table containing the Q-values of all possible sorting states and actions.
[0079] Select action: In the current state, select an action based on the Q value and ε-greedy exploration strategy.
[0080] Perform actions and observe rewards: Perform the selected actions and observe the reward values given by the system.
[0081] Update Q value: Update Q value according to the following formula.
[0082] Repeat steps: Return to step 2 until the system reaches a stable state. ;
[0083] The formula for updating the Q value is:
[0084] Q(s,a)←Q(s,a)+α*(r+γ*max(Q(s',a'))-Q(s,a));
[0085] Where: Q(s,a) represents the Q value of taking action a in state s. α represents the learning rate, ranging from 0 to 1, indicating the weight of new information. r represents the immediate reward after taking action a. γ represents the discount factor, ranging from 0 to 1, indicating the importance of future rewards. max(Q(s',a')) represents the maximum Q value of all possible actions in the next state s'.
[0086] In step S5, predictive sorting is implemented through time series analysis, using the ARIMA model to predict cargo flow. The specific steps include:
[0087] Data collection: Collect historical sorting data, including timestamps, cargo flow and other information.
[0088] Data preprocessing: cleaning data and handling missing values and outliers.
[0089] Model Fitting: Fit an ARIMA model using historical data.
[0090] Predict future traffic: Use the fitted model to predict future cargo traffic.
[0091] Adjust sorting strategy: adjust sorting strategy and resource allocation according to prediction results;
[0092] The ARIMA (p, d, q) model consists of the following three parts:
[0093] Autoregressive term (AR): (1-φ1L-φ2L^2-…-φp*L^p);
[0094] Difference term (I): (1-L)^d
[0095] Moving average (MA): (1-θ1L-θ2L^2-…-θq*L^q)
[0096] Where: L is the lag operator, L^k*X_t=X_{tk}.
[0097] p is the order of the autoregressive term.
[0098] d is the number of differences.
[0099] q is the order of the moving average term.
[0100] φ1,φ2,…,φp are the autoregressive coefficients.
[0101] θ1,θ2,…,θq are moving average coefficients.
[0102] X_t is the value of the time series at time t.
[0103] ε_t is the error term at time t.
[0104] In step S5, the specific steps of the intelligent sorting operation include:
[0105] S1. Use the ARIMA model to predict cargo flow in the future.
[0106] S2. Initialize the Q table based on the prediction results and set the expected state of the sorting system.
[0107] S3. At the beginning of each sorting cycle, the optimal sorting path is selected according to the current state and Q value.
[0108] S4. Perform sorting actions and collect immediate feedback rewards from the system.
[0109] S5. Update the Q value using the Q-learning formula.
[0110] S6. Repeat steps S3-S5 until the sorting cycle ends.
[0111] S7. According to the performance of the sorting cycle, adjust the ARIMA model parameters to more accurately predict future cargo flows.
[0112] In step S8, when the shipping area is ready to ship, the conveyor line will sort the goods according to the destination and priority of the goods to ensure that the goods are loaded onto the shipping vehicle in the correct order. The automated equipment in the shipping area adopts a collaborative operation mode to improve loading efficiency. The management system of the shipping area will monitor the loading progress of the goods in real time and connect with the transportation management system to ensure that the goods are shipped on time;
[0113] In step S9, when updating the shipping information, the central control system will generate an electronic waybill while updating the shipping information, and communicate with the customer in real time through the logistics management system. The system will also provide customers with logistics tracking services based on the transportation trajectory and estimated arrival time of the goods. In addition, the system will summarize the entire logistics process, collect feedback information, and provide data support for the continuous optimization of logistics services.
[0114] In the present invention, the reinforcement learning algorithm enables the sorting system to autonomously learn and optimize the sorting path, thereby significantly improving the sorting efficiency. Traditional sorting systems often rely on preset rules or manual adjustments, while the reinforcement learning algorithm can continuously adjust and optimize the sorting strategy based on feedback from actual operations. This self-learning and adaptive ability enables the sorting system to maintain efficient operation in a complex and changeable logistics environment. For example, when a sorting port is congested, the system can automatically select other paths for sorting to avoid a decrease in overall efficiency due to local problems. In addition, the reinforcement learning algorithm can also learn the rules of sorting from historical data, predict future sorting needs, and further optimize resource allocation and path planning.
[0115] In the present invention, the application of reinforcement learning algorithm helps to reduce the sorting error rate. In the logistics sorting process, incorrect sorting can lead to serious economic losses and reduced customer satisfaction. Through reinforcement learning, the system can learn from the results of each sorting and reduce the occurrence of repeated errors. The algorithm can identify the key factors that lead to sorting errors and avoid them in future sorting decisions. This continuous learning and improvement process continuously improves the accuracy and reliability of the sorting system, thereby improving the service quality of the entire logistics system.
[0116] In the present invention, the ARIMA model can provide accurate cargo flow forecasts for the sorting system, which is crucial for resource allocation and process planning. By predicting the cargo flow in the future, the sorting system can prepare resources in advance, such as adjusting the number of sorting personnel, optimizing equipment utilization, etc. This forward-looking resource management not only improves sorting efficiency, but also reduces operating costs. For example, when predicting the upcoming peak period, the system can increase the capacity of the sorting line in advance to ensure that the goods can be sorted quickly and accurately, avoiding bottlenecks caused by excessive traffic.
[0117] In the present invention, the prediction results of the ARIMA model help to realize intelligent sorting operations. Combined with the reinforcement learning algorithm, the system can dynamically adjust the sorting strategy according to the predicted cargo flow, thereby realizing a more flexible and intelligent sorting process. This intelligent sorting operation can not only cope with sudden changes in cargo flow, but also provide customized sorting solutions according to the characteristics and needs of different goods. In this way, the logistics center can better meet customer needs, improve customer satisfaction, and enhance its own market competitiveness.
[0118] In summary, the combination of dynamic sorting path optimization through reinforcement learning algorithm and the use of ARIMA model to predict cargo flow through time series analysis has brought significant efficiency improvement, cost reduction and increased customer satisfaction to the automatic sorting and transportation method of logistics, and is an important technical support for the development of logistics industry towards intelligence and automation.
[0119] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0120] The above description enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for automatic sorting and conveying of logistics, Features: The steps include: S1: The incoming goods area receives goods. After the goods arrive at the incoming goods area, the goods information is automatically identified by the automated scanning equipment; the goods are unloaded from the transport vehicle to the receiving platform of the incoming goods area using automated loading and unloading equipment; S2: Cargo information registration. Cargo information is uploaded to the central control system through a scanning device. The central control system registers the cargo information and assigns a unique identification code to each piece of cargo. S3: The conveyor line automatically transports the goods. The goods are placed on the conveyor line, and the conveyor line starts to transport the goods to the sorting area. The sensors on the conveyor line ensure that the goods move forward correctly without deviation or accumulation. S4: Cargo identification in the sorting area: When the cargo arrives at the sorting area, the cargo information is reconfirmed through a high-resolution camera or sensor; the central control system generates sorting instructions based on the cargo information; S5: Perform automatic sorting operations. The sorting mechanical arm or sorting robot grabs or pushes the goods to the corresponding sorting port according to the instructions. The sorting equipment guides the goods to the designated sorting lane, adds intelligent algorithms to improve the performance of the system, realizes dynamic sorting path optimization through reinforcement learning algorithms, and uses ARIMA models to predict cargo flow through time series analysis to achieve intelligent sorting. S6: Sorting completion confirmation: the sorted goods are confirmed to be correctly sorted through sensors; the sorting results are fed back to the central control system to update the goods status; S7: Automatic packaging in the packaging area. When the goods arrive at the packaging area, the automatic packaging machine will pack them according to the size and shape of the goods. The information of the packed goods will be collected again and uploaded to the central control system. S8: The shipping area is ready for shipment. The packaged goods are sent to the designated location of the shipping area through the conveyor line. The automated equipment in the shipping area loads the goods onto the shipping vehicle. S9: Shipping information update. After the goods are loaded, the central control system updates the shipping information. The shipping information is notified to the customer through the logistics management system, completing the entire logistics automatic sorting and transportation process.
2. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S1, a plurality of parallel unloading points are set up in the cargo receiving area, and each unloading point is equipped with corresponding automated scanning and loading and unloading equipment; during the unloading process, the system will monitor the cargo flow in the cargo receiving area in real time, and dynamically allocate the tasks of the unmanned forklifts through the intelligent scheduling system to ensure that all cargo can be quickly and accurately unloaded from the transport vehicle to the receiving platform; at the same time, the environmental monitoring system of the cargo receiving area will monitor the temperature and humidity to ensure that the cargo is in a suitable environment waiting for the next step of processing.
3. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S2, during the cargo information registration process, the central control system not only registers the cargo information, but also performs data analysis, including the type, volume, weight, and destination of the cargo; the system will classify and manage the cargo based on this information, and provide data support for subsequent sorting and packaging processes; in addition, the system will also conduct risk assessments on the cargo, and take additional protective measures for fragile or valuable cargo; the allocation of identification codes uses encryption technology to ensure the uniqueness and security of the cargo throughout the entire logistics process.
4. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S4, in the cargo identification link in the sorting area, the identification system composed of high-resolution cameras and sensors is highly fault-tolerant and can accurately identify cargo under different lighting and environments; when generating sorting instructions, the central control system will consider the priority of the cargo and the real-time status of the sorting port to optimize the sorting efficiency; the system can also predict possible sorting errors based on historical data and take preventive measures in advance.
5. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S6, during the sorting completion confirmation process, the sensor not only confirms that the goods have been sorted correctly, but also checks the integrity of the goods; after the sorting results are fed back to the central control system, the system will perform data analysis, evaluate the sorting efficiency and quality, and provide a basis for continuous improvement of the sorting process; at the same time, the system will automatically record abnormal situations in the sorting process for subsequent analysis and processing.
6. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S5, the specific steps of implementing dynamic sorting path optimization by reinforcement learning algorithm include: Initialize Q-table: Create a Q-table containing the Q-values of all possible sorting states and actions; Select action: In the current state, select an action based on the Q value and ε-greedy exploration strategy; Perform actions and observe rewards: Perform the selected actions and observe the reward values given by the system; Update Q value: Update Q value according to the following formula; Repeat steps: Return to step 2 until the system reaches a stable state; The formula for updating the Q value is: Q(s,a)←Q(s,a)+α*(r+γ*max(Q(s',a'))-Q(s,a)); Where: Q(s,a) represents the Q value of taking action a in state s; α represents the learning rate, ranging from 0 to 1, indicating the weight of new information; r represents the immediate reward obtained after performing action a; γ represents the discount factor, ranging from 0 to 1, indicating the importance of future rewards; max(Q(s',a')) represents the maximum Q value of all possible actions in the next state s'.
7. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S5, predictive sorting is achieved through time series analysis, and the ARIMA model is used to predict the cargo flow. The specific steps include: Data collection: Collect historical sorting data, including timestamps and cargo flow information; Data preprocessing: cleaning data, dealing with missing values and outliers; Model fitting: Fitting the ARIMA model using historical data; Predict future traffic: Use the fitted model to predict future cargo traffic; Adjust sorting strategy: adjust sorting strategy and resource allocation according to prediction results; The ARIMA (p, d, q) model consists of the following three parts: Autoregressive term (AR): (1-φ1L-φ2L^2-…-φp*L^p); Difference term (I): (1-L)^d Moving average (MA): (1-θ1L-θ2L^2-…-θq*L^q) Where: L is the lag operator, L^k*X_t=X_{tk}; p is the order of the autoregressive term; d is the number of differences; q is the order of the moving average term; φ1, φ2,…, φp are autoregressive coefficients; θ1,θ2,…,θq are moving average coefficients; X_t is the value of the time series at time t; ε_t is the error term at time t.
8. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S5, the specific steps of the intelligent sorting operation include: S1. Use the ARIMA model to predict cargo flow in the future; S2. Initialize the Q table according to the prediction results and set the expected state of the sorting system; S3. At the beginning of each sorting cycle, the optimal sorting path is selected according to the current state and Q value; S4. Perform sorting actions and collect instant feedback rewards from the system; S5. Update the Q value using the Q-learning formula; S6. Repeat steps S3-S5 until the sorting cycle ends; S7. According to the performance of the sorting cycle, adjust the ARIMA model parameters to more accurately predict future cargo flows.
9. A method for automatic logistics sorting and conveying as claimed in claim 1, Features: In step S8, when the shipping area is ready to ship, the conveyor line will sort the goods according to the destination and priority of the goods to ensure that the goods are loaded onto the shipping vehicle in the correct order; the automated equipment in the shipping area adopts a collaborative operation mode to improve loading efficiency; the management system of the shipping area will monitor the loading progress of the goods in real time and connect with the transportation management system to ensure that the goods are shipped on time; In step S9, during the delivery information update phase, the central control system will generate an electronic waybill while updating the delivery information, and communicate with the customer in real time through the logistics management system; the system will also provide customers with logistics tracking services based on the transportation trajectory and estimated arrival time of the goods; in addition, the system will summarize the entire logistics process, collect feedback information, and provide data support for the continuous optimization of logistics services.
10. A logistics automatic sorting and conveying system, Features: The system includes a memory, a processor, and an automatic logistics sorting and conveying program stored on the processor. When the automatic logistics sorting and conveying program is run by the processor, the automatic logistics sorting and conveying method according to any one of claims 1 to 9 is executed.