Intelligent control method of express sorting system

Abstract

The application discloses an intelligent control method of an express sorting system, and relates to the field of express sorting control. The method comprises the following steps: analyzing express envelope information, extracting time limit commitment, calculating the route emergency degree score of each express, and dividing the urgency level and the destination subgroup, so as to obtain the express priority; calculating the real-time sorting efficiency value of each sorting port by the route emergency degree score of the express, the transport time of the express to the candidate sorting port and the real-time queue length of the sorting port, and selecting the optimal target sorting port; dynamically adjusting the speed of the conveying belt by real-time monitoring the queue state on the route section of the conveying belt corresponding to the target sorting point, and distributing the grabbing task to the idle manipulator according to the route emergency degree score of the express, and realizing the cooperative control of the conveying belt and the manipulator; quantifying the time limit urgency and dynamically evaluating the sorting port efficiency, so as to guarantee the priority processing of the high-time-limit express and improve the overall efficiency of the sorting system.

Description

Technical Field

[0001] This invention belongs to the field of express sorting control technology, and relates to an intelligent control method for an express sorting system. Background Technology

[0002] With the development of e-commerce and the logistics industry, express sorting centers, as core nodes of the logistics network, directly affect the operational efficiency of the entire logistics chain. Faced with ever-increasing business volume and increasingly stringent timeliness commitments, traditional express sorting systems are facing severe challenges in terms of intelligence and dynamic scheduling.

[0003] Currently, the intelligent control technology solutions of existing express sorting systems have the following shortcomings: First, existing technologies mostly rely on scheduling based on first-come-first-served or fixed rules, failing to process and schedule according to the urgency of the packages themselves. However, in actual operation, express delivery faces constantly changing traffic pressure and diverse timeliness requirements. Static scheduling rules cannot respond to the urgent needs of urgent packages in real time, resulting in delays in the processing of urgent packages and failing to guarantee delivery timeliness.

[0004] Secondly, existing technologies typically only consider a single optimization dimension when selecting sorting exits for packages, such as fixed path matching or shortest queue. This results in sorting path selection failing to make optimal allocations in complex scenarios, easily causing resource mismatch problems such as continuous overload of local nodes and idleness of other nodes, leading to low overall system operating efficiency.

[0005] Finally, existing technologies typically treat each control link of a sorting system as an isolated module that operates independently, lacking a collaborative mechanism and closed-loop feedback based on a unified optimization goal. This can easily lead to mismatches in the actions of different links in the system, causing congestion or idleness between links. Summary of the Invention

[0006] In view of this, in order to solve the problems mentioned in the background art, the present invention provides an intelligent control method for an express sorting system.

[0007] The objective of this invention can be achieved through the following technical solution: an intelligent control method for an express sorting system, comprising: S1, parsing express waybill information, and assigning designated abnormal processing ports for centralized processing of unparsable express packages.

[0008] S2. For successfully parsed express deliveries, obtain the delivery time commitment, calculate the routing urgency score for each express delivery, and determine the express delivery priority based on the routing urgency score.

[0009] S3. Based on the destination information of the express delivery, determine the candidate sorting points that can handle the destination. For each candidate sorting point, calculate the real-time sorting efficiency value by combining the urgency score of the express delivery route, the delivery time to the sorting point, and the queue length of the sorting point.

[0010] S4. Select the target sorting point according to the priority order of express delivery and the real-time sorting efficiency value of each candidate sorting point.

[0011] S5. Based on the real-time monitoring of the queue status on the conveyor belt segment corresponding to the target sorting point, adjust the speed of the conveyor belt segment, assign tasks to idle robotic arms according to the urgency score of the express route, and coordinate the adjustment of conveyor belt speed and the assignment of robotic arm tasks.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention analyzes the express waybill information and extracts the time commitment, calculates the route urgency score of each express, and divides the urgency level and destination subgroup to obtain the express priority, which overcomes the problem that the existing static rules cannot identify and respond to the urgent needs of expedited packages, and ensures that packages with high time commitments can be processed first, thereby guaranteeing the delivery time.

[0013] (2) The present invention calculates the real-time sorting efficiency value of each sorting point by the urgency score of the express route, the delivery time to the candidate sorting point and the real-time queue length of the sorting point, and selects the optimal target sorting point. This overcomes the limitation of relying on a single dimension for decision-making, and can achieve global optimization of resource allocation in a dynamic environment, effectively balance the load of each sorting point, avoid local congestion and resource idleness, and thus maximize the overall processing efficiency.

[0014] (3) This invention dynamically adjusts the speed of the conveyor belt by monitoring the queue status on the corresponding conveyor belt section of the target sorting point in real time, and assigns grabbing tasks to the idle robot arm according to the urgency score of the express route. It also realizes the coordinated control of the conveyor belt and the robot arm, overcomes the problem of action mismatch caused by the isolated operation of each control link in the prior art, realizes the dynamic coordination and rhythm synchronization of the execution unit, and reduces congestion or idle time between links. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a diagram illustrating the implementation steps of the method of the present invention.

[0017] Figure 2 This is a flowchart illustrating the real-time sorting efficiency calculation process of this invention.

[0018] Figure 3 This is a flowchart illustrating the coordination process between conveyor belt speed adjustment and robotic arm task allocation in this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 As shown, the present invention provides an intelligent control method for a courier sorting system, including: S100, parsing courier waybill information, and assigning a designated exception handling port for centralized processing of unparsable courier packages.

[0021] Specifically, the image of the waybill of the express delivery to be sorted is obtained, optical character recognition is performed, and text information is extracted.

[0022] Furthermore, firstly, an industrial camera installed above the conveyor belt automatically captures images of the shipping label area as the package enters the image acquisition station. A diffuse light source is used during the shooting process to obtain high-resolution images.

[0023] Subsequently, the acquired image was subjected to grayscale conversion, binarization, noise reduction, and perspective correction to enhance the contrast between the label background and the printed characters and highlight the character edge features.

[0024] Finally, key information areas such as destination address, postal code, and delivery time commitment are located, and sub-images of each text area are extracted. Each text area sub-image is binarized, and text lines are determined by horizontal projection and individual characters are segmented by vertical projection. In this way, the destination address, postal code, tracking number, and carrier code are extracted from the text for subsequent sorting.

[0025] If the text information contains missing routing data elements or is unrecognizable due to image quality defects, the package is determined to be an unresolvable package.

[0026] Select the exception handling port with the fewest allocated express delivery counts as the candidate exception handling port. If there are multiple candidate exception handling ports with the same number, select one of them in order of number.

[0027] The principle of selecting the processing port with the fewest allocated express delivery counts is to evenly distribute the tasks to be processed to multiple parallel processing ports, preventing individual processing ports from becoming overloaded and causing a decrease in processing efficiency or queue congestion. Secondly, when the load is the same, a deterministic rule of selecting according to the number order is adopted to avoid the scheduling complexity caused by random selection, and to ensure that the same output decision can be made every time under the same input conditions.

[0028] Assign unresolvable packages to the candidate exception handling port and update the package count already assigned to the candidate exception handling port.

[0029] Periodically compare the number of express deliveries already assigned to each exception handling port, and redetermine the allocation order based on the order of quantity from smallest to largest.

[0030] At the start of each 30-second cycle, the latest assigned package counts for all exception handling ports are synchronously retrieved. Based on the retrieved counts, all exception handling ports are reordered in ascending order to generate a new recommended allocation order list. In the next cycle, newly generated exception packages will be allocated according to this list. Simultaneously, if the assigned package count for a particular exception handling port exceeds its maximum processing capacity, the allocation of new exception packages to that port will be suspended until it has completed part of its processing tasks.

[0031] Since the changes in express delivery counts at the abnormal processing station are mainly due to differences in processing speed and the changes are relatively slow, periodic reordering not only ensures a stable allocation order within each cycle, making the system behavior predictable, but also continuously corrects the load imbalance caused by uneven processing efficiency.

[0032] The drive sorting mechanism moves unresolved packages to their assigned target exception handling port.

[0033] S200. For successfully parsed express deliveries, obtain the delivery time commitment and calculate the routing urgency score for each express delivery.

[0034] The specific steps for calculating the route urgency score of each express delivery are as follows: Extract the pickup timestamp and delivery time commitment from the successfully parsed express delivery waybill information, and calculate the commitment deadline.

[0035] The specific steps for extracting the pickup timestamp and delivery time commitment of the express delivery are as follows: First, locate and read the pickup time field from the successfully parsed express delivery waybill information, and directly parse the pickup time field into a date and time object according to the standard format of the pickup time field, which is used as the pickup timestamp.

[0036] Secondly, through keyword matching and syntactic analysis, the commitment type and time constraint details, such as arrival before 18:00 the next day, are separated and extracted from the successfully parsed express waybill information text.

[0037] The calculation of the commitment deadline is based on the commitment type and time constraint details extracted from the time commitment text. The date or clock operation is performed on the pickup timestamp to obtain the commitment deadline. The specific implementation process includes: First, when the description of the next day, the day after tomorrow, etc. is identified, the corresponding number of days is directly added to the year, month and day part of the pickup timestamp.

[0038] Secondly, when a 24-hour numerical description is recognized, the corresponding number of hours is directly added to the pickup timestamp.

[0039] Finally, when a description containing date offset and specific time, such as "before 18:00 the next day", is identified, the date deviation is first calculated according to the date offset mentioned above, and then the hour, minute and second part of the result time point is adjusted to the specified time.

[0040] A specific embodiment of the above steps is as follows: If the pickup time is 14:30:00 on January 21, 2026.

[0041] If the delivery time commitment is identified as the next day, the calculated deadline is 23:59:59 on January 22, 2026.

[0042] If the delivery time commitment is identified as 72 hours, the calculated deadline is 14:30:00 on January 24, 2026.

[0043] If the time commitment is identified as being to be delivered before 18:00 the next day, then the calculated deadline for the commitment is 18:00:00 on January 22, 2026.

[0044] The difference between the promised deadline and the pickup timestamp is recorded as the promised duration. The time from the pickup timestamp to the current time is the consumed time. The ratio of the consumed time to the promised duration is recorded as the route urgency score. The route urgency score is a dynamic indicator used to quantify the urgency of the express delivery relative to its promised delivery time limit. Its value is between 0 and 1. The larger the value, the greater the time pressure and the more priority it needs to be handled.

[0045] It should be noted that during the delivery process, the time already consumed continuously increases, while the promised delivery time remains constant. Therefore, the ratio increases monotonically with time. Time pressure is positively correlated with the proportion of promised delivery time consumed; the higher the proportion of time consumed, the higher the urgency and the more urgent the delivery.

[0046] At the moment of pickup, the time elapsed is 0, so the route urgency score is 0. As time progresses, the route urgency score approaches 1. When the current time equals the promised deadline, the time elapsed equals the total promised time, and the urgency score is 1. That is, in the early stages of transportation, the time pressure is not obvious; when the urgency score exceeds 0.5, the passage of each unit of time will result in a greater increase in the urgency score, thus enabling all express deliveries to be prioritized according to their completed fulfillment progress, solving the problem of scheduling priority distortion caused by differences in promised time, and driving resources to automatically tilt towards express deliveries with a higher proportion of elapsed time and closer to the promised deadline.

[0047] To prevent extreme commitment durations from causing urgency scores to change too quickly or too slowly, which could lead to layout scheduling oscillations or sluggish responses, effective boundaries need to be set for the commitment duration: a lower limit and an upper limit should be set, for example, a lower limit of 2 hours and an upper limit of 30 days. If the commitment duration is less than the lower limit, it will be considered the lower limit when calculating the route urgency score; if the commitment duration is greater than the upper limit, it will be considered the upper limit when calculating the route urgency score.

[0048] Meanwhile, for the time already consumed, when the transit time of the express delivery abnormally exceeds the promised time, the system will forcibly set the route urgency score to 1 and trigger the exception handling process to avoid scheduling distortion caused by extreme data.

[0049] S201. Determine the priority of express delivery based on the urgency score of the route.

[0050] The steps for determining the priority of express delivery based on the route urgency score are as follows: Sort all currently successfully parsed express delivery packages from high to low according to their route urgency score, divide the sorted express delivery sequence into multiple urgency intervals, and each urgency interval corresponds to an urgency level.

[0051] The higher the urgency score, the more urgent the task. By sorting the tasks from highest to lowest urgency, the most time-sensitive packages can be identified from all pending tasks in real time, ensuring that the most urgent packages are prioritized for service when resources are limited.

[0052] The sorted express delivery sequence is divided into multiple urgency intervals based on the score distribution of the current batch of express delivery. It is divided into three equal parts, for example, the first 33% is the high urgency level, the middle 33% is the medium urgency level, and the last 34% is the low urgency level.

[0053] If items are sorted strictly according to their scores, a large number of invalid idle strokes may be generated, reducing overall efficiency. By dividing the process into levels, the freedom to perform batch optimization is gained within the same urgency level.

[0054] The hierarchical division is equivalent to setting up several buffer zones for the scheduling system, making the system relatively stable when processing express deliveries within a level, avoiding high-frequency fluctuations in the processing target due to small fluctuations in scores, and making the subsequent operation of robotic arms and conveyor belts smoother.

[0055] Within the same urgency level, packages heading to the same destination are clustered into multiple destination subgroups based on their destination information.

[0056] Since the urgency of packages within the same priority level is considered similar, the efficiency of sorting is affected by the idle time and positioning losses caused by physical switching between different target sorting points. Therefore, by clustering packages heading to the same destination into subgroups, the aim is to integrate discrete sorting tasks into batch tasks with a consistent direction, thereby reducing mechanical wear and energy consumption of the actuators.

[0057] Within each destination subgroup, packages are sorted by route urgency score, and different urgency levels are processed in descending order of urgency. By mandating that different urgency levels must be processed in descending order of urgency, the highest-level packages are guaranteed to be processed before any packages at lower levels, thus forming a hard constraint boundary for timeliness guarantee.

[0058] S300: Determine the candidate sorting port that can handle the destination based on the express delivery destination information.

[0059] Specifically, the set of destination codes that can be processed at each sorting point is obtained in real time.

[0060] Furthermore, firstly, the status monitoring unit of each sorting station reports all currently valid destination codes configured at that sorting station, along with its own identification information, to the central controller; secondly, the central controller receives this reported information and updates the real-time correspondence between each sorting station identifier and all destination codes it can currently process; finally, when it is necessary to determine a candidate sorting station for a package, the package's destination code is compared with the correspondence to obtain all sorting station identifiers that can process that destination.

[0061] Only by performing route matching based on real-time snapshots of sorting station capabilities can we ensure the correctness of subsequent candidate sorting station decisions and avoid assigning packages to sorting stations that cannot handle their destinations.

[0062] Extract standardized destination codes from express delivery destination information.

[0063] Specifically, firstly, the original description of the recipient address extracted from the waybill text is parsed to identify and separate the included administrative region and detailed address elements; secondly, the identified address elements are matched and calibrated with the system's built-in addresses level by level to eliminate writing errors and obtain standardized provincial, municipal, district, or county-level administrative place names; finally, each standardized administrative place name is uniquely mapped to a specific numeric or alphanumeric code, and the above three-level standardized place names are combined to generate a final standard destination code.

[0064] The standardized destination code is matched one by one with the set of destination codes that each sorting point can process, and the sorting point that successfully matches is determined as the candidate sorting point for the express delivery; this fundamentally avoids missorting.

[0065] S301. For each candidate sorting point, calculate the real-time sorting efficiency value by combining the urgency score of the express route, the delivery time to the sorting point, and the queue length of the sorting point.

[0066] See Figure 2 As shown, the specific steps for calculating the real-time sorting efficiency value are as follows: Based on the path distance between each candidate sorting port and the current location of the express delivery on the conveyor belt, and the speed of the conveyor belt, calculate the delivery time to each candidate sorting port.

[0067] Considering that the physical path length between different candidate sorting points and the current location of the express delivery is different, and the conveyor belt speed varies from section to section, the actual transit time of the express delivery to different sorting points is different, and this time cost affects the express delivery processing speed.

[0068] Based on this, the steps for calculating the delivery time to each candidate sorting point are as follows: First, the real-time location of the express delivery in the conveyor network is determined by the visual positioning module installed at each node of the conveyor belt, and the path distance from the real-time location of the express delivery to the entrance of each candidate sorting point is obtained according to the path topology data; second, the running speed of the conveyor belt in the current section is obtained in real time from the encoder of the conveyor belt motor; finally, for each candidate sorting point, the corresponding path distance is divided by the running speed to calculate the delivery time of the candidate sorting point.

[0069] The number of express parcels waiting to be processed at each candidate sorting point is obtained in real time and used as the queue length for each candidate sorting point.

[0070] The real-time acquisition of the number of express parcels waiting to be processed at each candidate sorting point is achieved by using pairs of vision sensors deployed above the conveyor belt to detect the real-time count of express parcels, thereby obtaining the number of express parcels currently in a waiting state.

[0071] Obtain the single-item processing time for each candidate sorting point, and then compare it with the queue length of the corresponding candidate sorting point to obtain its queue waiting time. Specifically, this is obtained by multiplying the single-item processing time by the queue length of the corresponding candidate sorting point.

[0072] The single-item processing time for each candidate sorting station is calculated by taking the arithmetic mean of the time spent on each task recorded in its timing unit, and then updating this average value to the current single-item processing time for each candidate sorting station.

[0073] Calculate the delivery time and queue waiting time to obtain the processing time for each candidate sorting point.

[0074] The efficiency coefficient is obtained by mapping the processing time using an exponential decay function.

[0075] It should be noted that the formula for the exponential decay function is as follows: Where i is the candidate sorting port number; T i E is the processing time for the i-th candidate sorting port; i λ represents the original efficiency coefficient obtained after mapping the i-th candidate sorting port through the exponential decay function, and its value range is (0, 1]; λ represents the decay constant, and λ>0, which determines the rate at which the efficiency decreases with the increase of processing time. It can be obtained by setting an empirical value. For example, λ can be set to 0.1. This value is derived from the statistical analysis of the historical data processing time distribution. In practical applications, it can be adjusted in the range of 0.05 to 0.2 to adapt to the time sensitivity requirements of different sorting scenarios.

[0076] Furthermore, Indicates processing time T i The negative nonlinear effect on efficiency, the negative sign indicates T i Increasing the value of λ will lead to a decrease in the result value. The larger the value of λ, the more sensitive it is to the increase in processing time, and the faster the efficiency coefficient decreases.

[0077] It is to make the linear processing time T i Mapped as T i The coefficient E increases and decays exponentially. i When T i =0 E i =1, indicating the ideal maximum efficiency; as T... i Increase E i The rapid approach to 0 indicates that excessively long processing times will drastically reduce the willingness to choose that sorting port, thus penalizing sorting ports with excessively long processing times in the calculation.

[0078] Multiply the route urgency score by the efficiency coefficient to obtain the real-time sorting efficiency value of each candidate sorting point.

[0079] For high-urgency deliveries, the difference in efficiency coefficients is amplified. This means that when selecting sorting points for high-urgency deliveries, the system tends to assign them to the sorting point with the highest expected processing efficiency, thus driving the system to find the most efficient path for them. Conversely, the impact of the difference in efficiency coefficients on low-urgency deliveries is weakened, and the sensitivity to efficiency differences is reduced when selecting sorting points for them.

[0080] S400: Select target sorting ports according to the priority order of express delivery and the real-time sorting efficiency value of each candidate sorting port.

[0081] To ensure that urgent parcels are prioritized, the sorting station with the highest overall processing efficiency is dynamically selected for each parcel, and when efficiency values ​​are the same, a definite and unique allocation is made based on queue length and sorting station number.

[0082] Based on this, the specific steps for screening target sorting points are as follows: select subsequent express packages in sequence according to the priority processing order of urgency level, destination subgroup, and sorting within the group.

[0083] Obtain all candidate sorting ports corresponding to the currently selected express delivery and their respective real-time sorting efficiency values, and select the candidate sorting port with the largest real-time sorting efficiency value as the target sorting port for the current express delivery.

[0084] The candidate sorting point with the highest real-time sorting efficiency value is selected because the maximum value in the real-time sorting efficiency value corresponds to the expected path that can make the package complete the sorting process the fastest at the moment, thereby maximizing the processing efficiency of a single package while ensuring that urgent packages are handled first.

[0085] If multiple candidate sorting ports have the same real-time sorting efficiency value, and all of them are the maximum value, then the sorting port with the smallest queue length is selected as the target sorting port. If the queue lengths are still the same, then the sorting port with the smallest number is selected.

[0086] Given the same efficiency value, i.e., similar expected overall processing time, a sorting station with a shorter current queue indicates that the immediate workload at that sorting station is less, and the actual queuing time for express packages may be shorter. Selecting the sorting station with the shortest queue length helps prevent task backlog at individual sorting stations and avoids the uncertainty of random selection.

[0087] S500: Adjust the speed of the conveyor belt segment based on the queue status of the corresponding conveyor belt segment at the target sorting point in real time.

[0088] Given the need to adjust the logistics buffer state before the target sorting point to avoid queue congestion due to lag, a speed control strategy based on queue change trends is adopted.

[0089] Therefore, the steps for adjusting the speed of the conveyor belt segment are as follows: monitor the queue length of the currently pending express delivery on the conveyor belt segment corresponding to the target sorting point, calculate the rate of change of the queue length over time, and record the rate of change multiple times.

[0090] The optimal rate is recorded as three consecutive changes. This is mainly to effectively filter out the conveyor belt oscillation caused by the instantaneous fluctuations resulting from the random arrival of express packages, while avoiding congestion or idle running due to misjudgment or delay.

[0091] If the rate of change is consistently positive multiple times, the speed of the conveyor belt segment is increased; if the rate of change is consistently negative multiple times, the speed of the conveyor belt segment is decreased; if the rate of change is zero, the current speed is maintained.

[0092] Because extreme conditions can cause conveyor belt speeds to rise or fall indefinitely, it is crucial to ensure that the speed is controlled within the minimum and maximum safe operating speeds required to maintain smooth package movement when increasing or decreasing the operating speed of a conveyor belt section. These minimum and maximum safe operating speeds can be directly obtained from the conveyor belt system's design specifications. For example, for cross-belt sorting machines handling ordinary e-commerce parcels, the minimum speed is typically no less than 0.3 m / s, and the maximum safe operating speed is typically no more than 2.5 m / s.

[0093] It should be noted that a positive rate of change for several consecutive times indicates that the flow of express parcels entering the preparatory area of ​​the sorting port is continuously greater than its processing capacity, and the queue is on an increasing trend. In this case, actively increasing the conveyor belt speed aims to increase the supply to the sorting port per unit time, prevent the queue from growing indefinitely, and prevent potential congestion. Conversely, a negative rate of change for several consecutive times indicates that the processing capacity has exceeded the input flow, and the queue is on a dissipating trend. In this case, reducing the speed can save energy and avoid insufficient supply. A rate of change of zero indicates that the system is in a dynamic equilibrium state and no adjustment is required.

[0094] Speed ​​adjustment is triggered only when the signs of the rate of change are consistent multiple times, which enables smoother control and prevents violent oscillations between overstocking and supply interruption.

[0095] S501. Assign tasks to idle robotic arms based on the urgency score of the express delivery route.

[0096] To avoid resource waste and ensure that packages with the highest time priority are processed immediately upon arrival at the sorting point, robotic arms are used for real-time task allocation, eliminating idle and wasteful execution resources and ensuring that their operation always prioritizes the most urgent deliveries.

[0097] Therefore, the specific implementation steps for assigning tasks to idle robotic arms include: sorting express packages that have been identified as having a target sorting point and have entered the preparatory area before that sorting point in descending order according to their route urgency score, thereby generating a dynamic task queue.

[0098] Monitor the working status of the robotic arms at each sorting station. When an idle robotic arm is detected, query the dynamic task queue for all express delivery tasks located in the preparation area of ​​the sorting station to which the idle robotic arm belongs, and select the express delivery task with the highest urgency score.

[0099] The sorting system must ensure that the highest priority packages with time-sensitive commitments receive optimal processing rights throughout the entire process. If the robotic arms do not prioritize grabbing the most urgent packages when they are idle, it will cause delays in the final processing stage for packages with high time-sensitive requirements, disrupting the consistency of global priorities and increasing their risk of delay.

[0100] The instructions for grabbing and delivering the package are assigned to the idle robotic arm for execution.

[0101] S502, and coordinates the adjustment of conveyor belt speed and the allocation of robot tasks.

[0102] Considering the mechanical inertia and response delay in conveyor belt speed adjustment, if the task queue is updated and tasks are assigned to the robot arm before the conveyor belt speed has stabilized or when it is vibrating, the robot arm is likely to perform grasping based on incorrect position information, resulting in missing grasps, incorrect grasps, or the need for repositioning, thereby reducing the sorting success rate and efficiency.

[0103] See Figure 3 As shown, the coordination of conveyor belt speed adjustment and robot task allocation includes: after executing the speed adjustment of the conveyor belt segment and issuing the control command, continuously monitoring until a confirmation feedback that the speed of the conveyor belt segment has reached the target value is received.

[0104] After receiving confirmation feedback, the system waits for the predetermined stabilization time window based on the mechanical inertial response characteristics of the conveyor belt.

[0105] The predetermined stable time window is dynamically calculated based on the conveyor belt length and speed, covering the time required for the express delivery to move from the acceleration starting point to the sorting preparation area, specifically: Where L is the length of the conveyor belt segment, v is the target speed, and Δt is the mechanical inertial response delay time, which is usually 2 to 5 seconds and is obtained through experimental calibration.

[0106] After the stabilization window ends, real-time queue information of express packages in the preparation area in front of the target sorting port will be collected again.

[0107] Based on the newly collected real-time queue information and the urgency score of the express delivery route, the task queue is updated synchronously, and then the step of assigning tasks to the idle robotic arm is executed.

[0108] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0109] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0110] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0111] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0112] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent control method for an express sorting system, characterized in that: include: Parse the express waybill information, and assign designated exception handling ports to centrally process unparseable express packages; For successfully parsed packages, obtain the delivery time commitment, calculate the routing urgency score for each package, and determine the package priority based on the routing urgency score; The calculation of the urgency score for each express delivery route includes: From the successfully parsed express waybill information, extract the pickup timestamp and delivery time commitment of the express delivery, and calculate the commitment deadline. The difference between the commitment deadline and the pickup timestamp is recorded as the commitment duration. The time from the pickup timestamp to the current time is the consumed duration. The ratio of the consumed duration to the commitment duration is recorded as the route urgency score. The method of determining express delivery priority based on route urgency score includes: Sort all currently successfully parsed express packages in descending order of their route urgency score, and divide the sorted express package sequence into multiple urgency intervals, with each urgency interval corresponding to an urgency level. Within the same urgency level, packages heading to the same destination are clustered into multiple destination subgroups based on their destination information. Within each destination subgroup, routes are sorted by urgency score, and between different urgency levels, they are processed in descending order of level. Based on the destination information of the express delivery, candidate sorting points that can handle the destination are determined. For each candidate sorting point, the real-time sorting efficiency value is calculated by combining the urgency score of the express route, the delivery time to the sorting point, and the queue length of the sorting point. Based on the priority of express delivery, the target sorting point is selected according to the real-time sorting efficiency value of each candidate sorting point. The calculation of the real-time sorting efficiency value includes: Based on the path distance between each candidate sorting point and the current location of the express delivery on the conveyor belt, as well as the speed of the conveyor belt, calculate the delivery time to each candidate sorting point. The number of express parcels waiting to be processed at each candidate sorting point is obtained in real time and used as the queue length of each candidate sorting point; Get the single-item processing time of each candidate sorting point, and compare it with the queue length of the corresponding candidate sorting point to obtain its queue waiting time; Calculate the delivery time and queue waiting time to obtain the processing time for each candidate sorting point; The efficiency coefficient is obtained by mapping the processing time using an exponential decay function; Multiply the route urgency score by the efficiency coefficient to obtain the real-time sorting efficiency value of each candidate sorting point; Based on the real-time monitoring of the queue status on the corresponding conveyor belt segment of the target sorting point, the speed of that conveyor belt segment is adjusted. Based on the urgency score of the express route, tasks are assigned to idle robotic arms, and the adjustment of conveyor belt speed and task allocation of robotic arms are coordinated.

2. The intelligent control method for an express sorting system according to claim 1, characterized in that: The process of parsing express waybill information, and assigning unparseable express packages to designated exception handling ports for centralized processing, includes: Obtain images of waybills for parcels to be sorted, perform optical character recognition, and extract text information; If the text information contains missing routing data elements or is unrecognizable due to image quality defects, the express delivery is determined to be an unresolvable express delivery. Select the exception handling port with the fewest allocated express delivery counts as the candidate exception handling port. If there are multiple candidate exception handling ports with the same number, select one of them in order of number. Assign unresolvable packages to candidate exception handling ports and update the package count already assigned to candidate exception handling ports; Periodically compare the number of express deliveries already assigned to each exception handling point, and redetermine the assignment order based on the number in ascending order; The drive sorting mechanism moves unresolved packages to their assigned target exception handling port.

3. The intelligent control method for an express sorting system according to claim 1, characterized in that: The process of determining candidate sorting points for processing the destination based on the express delivery destination information includes: Real-time acquisition of the current set of destination codes that can be processed at each sorting point; Extract standardized destination codes from express delivery destination information; The standardized destination code is matched one by one with the set of destination codes that each sorting point can process, and the sorting point that successfully matches is determined as the candidate sorting point for the express delivery.

4. The intelligent control method for an express sorting system according to claim 1, characterized in that: The screening target sorting port includes: Following the priority order of urgency level, destination subgroup, and sorting within the group, subsequent express deliveries are selected in sequence; Obtain all candidate sorting ports corresponding to the currently selected express delivery and their respective real-time sorting efficiency values, and select the candidate sorting port with the largest real-time sorting efficiency value as the target sorting port for the current express delivery; If multiple candidate sorting ports have the same real-time sorting efficiency value, and all of them are the maximum value, then the sorting port with the smallest queue length is selected as the target sorting port. If the queue lengths are still the same, then the sorting port with the smallest number is selected.

5. The intelligent control method for an express sorting system according to claim 1, characterized in that: The adjustment of the speed of the conveyor belt section includes: Monitor the queue length of the currently pending express delivery on the conveyor belt section corresponding to the target sorting point, calculate the rate of change of the queue length over time, and record the rate of change multiple times consecutively. If the rate of change is consistently positive multiple times, the speed of the conveyor belt segment is increased; if the rate of change is consistently negative multiple times, the speed of the conveyor belt segment is decreased; if the rate of change is zero, the current speed is maintained.

6. The intelligent control method for an express sorting system according to claim 5, characterized in that: The process of assigning tasks to idle robotic arms based on the urgency score of express delivery routes includes: Express packages that have been identified as having a target sorting point and have entered the preparation area before that sorting point are sorted in descending order according to their route urgency score to generate a dynamic task queue. Monitor the working status of the robotic arms at each sorting station. When a robotic arm is found to be idle, query all express delivery tasks in the dynamic task queue that are located in the preparation area of ​​the sorting station to which the idle robotic arm belongs, and select the express delivery task with the highest urgency score. The instructions for grabbing and delivering the package are assigned to the idle robotic arm for execution.

7. The intelligent control method for an express sorting system according to claim 6, characterized in that: The coordinated conveyor belt speed adjustment and robotic arm task allocation include: After the speed adjustment of the conveyor belt section is executed and the control command is issued, continuous monitoring is carried out until confirmation feedback is received that the speed of the conveyor belt section has reached the target value. After receiving confirmation feedback, wait for the predetermined stabilization time window based on the mechanical inertial response characteristics of the conveyor belt; After the stabilization time window ends, the real-time queue information of express packages in the preparation area in front of the target sorting port will be collected again. Based on the newly collected real-time queue information and the urgency score of the express delivery route, the task queue is updated synchronously, and then the step of assigning tasks to the idle robotic arm is executed.

Images