Intelligent logistics dispatching and distribution method and system

Abstract

The invention discloses an intelligent logistics scheduling and distribution method and system, and the method comprises the steps: obtaining a data set of to-be-distributed packages in a current delivery period, and the data set comprises the delivery deadline, the volume parameter and the target user identifier of each package; when the number of the parcels to be delivered exceeds a preset threshold value, a dynamic scheduling strategy is triggered, and the dynamic scheduling strategy comprises the steps that historical delivery records are called based on the target user identification, a historical signing time interval set of the user is calculated, and an emergency degree coefficient is obtained according to the historical signing time interval set; meanwhile, a multi-dimensional evaluation matrix is constructed, the matrix dimensionality covers an emergency degree coefficient, a package volume coefficient and a residual delivery time length coefficient, the scheduling priority of each package is calculated according to the evaluation matrix, and the packages with the priorities lower than a critical value are automatically distributed to the next delivery period according to a sorting result. According to the method, the historical signing behavior of the user is considered, intelligent scheduling is carried out in combination with multi-dimensional parameters, the problem of package overstock of a logistics final station is effectively relieved, and resource allocation is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to an intelligent logistics scheduling and distribution method and system. Background Art

[0002] At present, with the booming development of e-commerce and the increasingly diverse consumption demands, the efficient operation of the logistics industry has become even more crucial. However, there are serious deficiencies in the flexibility and intelligence of the current logistics scheduling system, resulting in an increasingly severe problem of package backlog at the final logistics station. This not only seriously occupies the warehousing space, significantly increases the logistics operation cost, but also seriously affects the logistics service quality and customer satisfaction, becoming a huge obstacle hindering the development of the logistics industry towards intelligence and high efficiency, and there is an urgent need for innovative logistics scheduling technologies to reverse this unfavorable situation. Summary of the Invention

[0003] To solve at least one of the above-mentioned technical problems, the present invention provides an intelligent logistics scheduling and distribution method and system.

[0004] In a first aspect, the present invention provides an intelligent logistics scheduling and distribution method, and the method includes:

[0005] Obtain a data set of packages to be delivered in the current delivery cycle, where the data set includes the delivery deadline, volume parameter, and target user identifier of each package;

[0006] When the number of packages to be delivered exceeds a preset threshold, execute a dynamic scheduling strategy;

[0007] The execution of the dynamic scheduling strategy includes:

[0008] Retrieve historical delivery records based on the target user identifier, and calculate a set of historical signing time intervals corresponding to each user. The historical signing time interval refers to the time difference between the moment when the package arrives at the final delivery node and the moment when the user actually signs for it;

[0009] Calculate the urgency coefficient according to the set of historical signing time intervals; construct a multi-dimensional evaluation matrix, and the dimensions of the evaluation matrix include the urgency coefficient, package volume coefficient, and remaining delivery duration coefficient;

[0010] According to the evaluation matrix, calculate the scheduling priority of each package through a weighted fuzzy decision algorithm; based on the sorting result of the scheduling priority, automatically assign the packages with a priority lower than the critical value to the next delivery cycle.

[0011] Preferably, the dynamic update mechanism of the set of historical signing time intervals includes:

[0012] After completing the delivery of a new package, add the actual signing time interval to the time series database of the corresponding user;

[0013] Maintain the most recent N delivery records using a sliding window mechanism, where N is dynamically adjusted according to user activity.

[0014] Preferably, the urgency coefficient is calculated according to the following algorithm:

[0015]

[0016] In the formula, W e is the urgency coefficient, μ is the mean of the historical signing time intervals, σ is the variance, T max is the maximum allowed delivery duration, T re is the current remaining delivery duration, and both α and β are adjustment factors, with the default values of α and β being 0.5.

[0017] Preferably, the weighted fuzzy decision algorithm is expressed as follows:

[0018] P = γ1·W e + γ2·S e + γ3·T e ,

[0019] In the formula, P is the scheduling priority, W e is the urgency coefficient, S e is the normalized package volume coefficient, T e is the remaining delivery duration urgency coefficient, and γ1, γ2, and γ3 are dynamic weight parameters.

[0020] Preferably, the calculation of the package volume coefficient includes:

[0021] Establish a volume classification model to map the package size to a preset volume level;

[0022] Calculate the space occupancy weight of each volume level according to the actual loading capacity of the delivery vehicle.

[0023] Preferably, the method further includes:

[0024] When it is detected that the remaining delivery duration coefficient of a certain package is lower than the safety threshold, automatically trigger the manual review process;

[0025] Generate a visual warning interface to display the spatio-temporal trajectory map of the package and the historical behavior characteristics of the associated user.

[0026] In a second aspect, the present invention also provides an intelligent logistics scheduling and delivery system, which includes:

[0027] A data acquisition module for acquiring a data set of packages to be delivered in the current delivery cycle, where the data set includes the delivery deadline, volume parameters, and target user identifiers of each package;

[0028] A dynamic scheduling trigger module, which is used to execute a dynamic scheduling strategy when the number of packages to be delivered exceeds a preset threshold;

[0029] The execution of the dynamic scheduling strategy includes:

[0030] Retrieving historical delivery records based on the target user identifier, and calculating the set of historical signing time intervals corresponding to each user, where the historical signing time interval refers to the time difference between the moment when the package arrives at the final delivery node and the moment when the user actually signs for it;

[0031] Calculating the urgency coefficient according to the set of historical signing time intervals; constructing a multi-dimensional evaluation matrix, and the dimensions of the evaluation matrix include the urgency coefficient, the package volume coefficient, and the remaining delivery duration coefficient;

[0032] According to the evaluation matrix, calculating the scheduling priority of each package through a weighted fuzzy decision algorithm; based on the sorting result of the scheduling priority, automatically allocating the packages with a priority lower than the critical value to the next delivery cycle.

[0033] In a third aspect, the present invention also provides an electronic device, including a processor and a memory, where the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the method according to the first aspect and any one of its possible implementation manners as described above.

[0034] In a fourth aspect, the present invention also provides a computer-readable storage medium, in which a computer program is stored, and the computer program includes program instructions. When the program instructions are executed by the processor of the electronic device, the processor is caused to execute the method according to the first aspect and any one of its possible implementation manners as described above.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0036] By fully mining the user's historical signing time interval data, combining a multi-dimensional evaluation matrix with a weighted fuzzy decision algorithm, the present invention realizes the intelligence and flexibility of logistics scheduling, effectively solves the problem of package backlog at the final logistics station. Specifically, based on the calculation of the urgency coefficient of the user's historical behavior, it can accurately identify the time-sensitive requirements of different users, thereby optimizing the sorting of delivery priorities. Introducing multi-dimensional parameters such as the package volume coefficient and the remaining delivery duration coefficient ensures the comprehensiveness and scientificity of the scheduling decision. The dynamic adjustment mechanism further enhances the system's adaptability to complex scenarios, avoiding resource waste, improving the delivery efficiency, and significantly improving the user experience, providing key technical support for the intelligent upgrade of the logistics industry.

[0037] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the background art, the drawings required for use in the embodiments of the present invention or in the background art will be described below.

[0039] The drawings herein are incorporated into the specification and constitute a part of this specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0040] Figure 1 It is a schematic flowchart of an intelligent logistics scheduling and distribution method provided by an embodiment of the present invention;

[0041] Figure 2 It is a schematic structural diagram of an intelligent logistics scheduling and distribution system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0043] The mention of "embodiment" in this context means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0044] Current logistics scheduling, due to its traditional mode, insufficient utilization of real-time data and poor adaptability, is difficult to balance parcel characteristics and user needs, resulting in parcel backlogs at the final logistics stations and reducing logistics efficiency.

[0045] Please refer to Figure 1 , Figure 1 It is a schematic flowchart of an intelligent logistics scheduling and distribution method provided by an embodiment of the present invention. As Figure 1 shown, the method includes:

[0046] S100. Obtain the dataset of packages to be delivered in the current delivery cycle. The dataset includes the delivery deadline, volume parameters, and target user identifiers of each package.

[0047] By deploying a large number of intelligent sensors and data terminal devices with data collection and transmission functions at various key nodes in the logistics network, such as package collection stations, transport vehicles, sorting centers, and distribution stations, real-time communication and interaction are carried out with the labels attached to the packages with unique identification codes (such as QR codes, RFID tags). When a package passes through these nodes during the logistics process, the intelligent sensors and data terminal devices quickly read the relevant information of the package, including using a high-precision timestamp recording device to obtain the expected delivery deadline of the package, which is accurately calculated by a complex time prediction algorithm based on the agreement between the e-commerce platform and consumers and the time efficiency standards formulated by the logistics enterprise for different transportation routes and distribution methods; using a volume measurement instrument based on the fusion technology of laser ranging and image recognition to scan the package comprehensively to obtain the accurate size data of the length, width, and height of the package, and obtaining the volume parameters of the package according to the pre-set volume calculation formula; at the same time, by quickly identifying and parsing the target user identifier (such as the unique digital ID, mobile phone number, or ID card number generated when the user registers for the logistics service) on the package label, this information is summarized and transmitted to the central database of the logistics information management system in real time and accurately, thereby constructing a complete and accurate dataset of packages to be delivered in the current delivery cycle.

[0048] S200. When the number of packages to be delivered exceeds the preset threshold, execute the dynamic scheduling strategy.

[0049] Continuously monitor and update in real time the number of packages to be delivered in the current delivery cycle. Once it is detected that this number exceeds the preset threshold, the system immediately triggers the execution program of the internally pre-written and integrated dynamic scheduling strategy, and quickly starts a series of subsequent dynamic scheduling processes to ensure that the logistics scheduling can respond to abnormal situations in a timely manner.

[0050] The execution of the dynamic scheduling strategy includes:

[0051] S210. Retrieve the historical delivery records based on the target user identifier, and calculate the set of historical signing time intervals corresponding to each user. The historical signing time interval refers to the time difference between the moment when the package arrives at the final distribution node and the moment when the user actually signs for it.

[0052] Precisely query in the massive historical delivery record database stored distributively with the target user identifier as the index. Through distributed query, distribute the query tasks in parallel to multiple storage nodes and utilize the computing resources of each node to retrieve simultaneously. Quickly locate and retrieve all historical delivery records related to the target user identifier. The historical delivery records include key time node information of the package from the starting station to the user's hands, detailed package attributes (such as weight, category, value, etc.), and the logistics transportation track, etc. Automatically extract the timestamp when the package arrives at the final delivery node and the timestamp when the user actually signs for the package. Use the time difference calculation function to accurately calculate the historical signing time interval corresponding to each package, and then integrate these time interval data by user to form a set of historical signing time intervals corresponding to each user.

[0053] S220, calculate the urgency coefficient according to the set of historical signing time intervals; construct a multi-dimensional evaluation matrix, and the dimensions of the evaluation matrix include the urgency coefficient, the package volume coefficient, and the remaining delivery duration coefficient;

[0054] Preferably, the urgency coefficient is calculated according to the following algorithm:

[0055]

[0056] In the formula, W e is the urgency coefficient, μ is the mean of the historical signing time intervals, σ is the variance, T max is the maximum allowed delivery duration, T re is the current remaining delivery duration, and both α and β are adjustment factors, and by default, both α and β are 0.5.

[0057] After obtaining the set of historical signing time intervals corresponding to each user, for the historical signing time interval data of each user, use the mean calculation method in statistics. By performing a summation operation on all historical signing time interval data in the set and then dividing by the number of data in the set, the mean μ of the historical signing time intervals of this user can be obtained. At the same time, using the variance calculation formula, square the difference between each historical signing time interval data and the mean μ, then sum these squared differences and divide by the number of data to obtain the variance σ of the historical signing time intervals of this user. Obtain the relevant time information of the current package to be delivered. Among them, T max (the maximum allowed delivery duration) is a fixed value preset according to comprehensive factors such as the logistics service contract agreement, the characteristics of the logistics route, and the service standards formulated within the logistics enterprise, and this value remains relatively stable throughout the logistics scheduling process. And T re (the current remaining delivery duration) is obtained by obtaining the current moment in real time and calculating the difference from the delivery deadline of the package. For example, assume the current moment is T now , and the delivery deadline of the package is Tend , then T re = T end - T now . After obtaining all the above parameters , according to the formula calculate the urgency coefficient W e . Among them, α and β are adjustment factors. By default, both α and β are set to 0.5. However, in actual applications, logistics schedulers can flexibly adjust the values of α and β according to different logistics business scenarios, user demand characteristics, and logistics resource conditions. For example, during e-commerce promotion activities, since users generally have higher requirements for the timeliness of package delivery, the value of α can be appropriately increased to enhance the influence weight of the user's historical signing time interval on the urgency coefficient. During periods when logistics transportation resources are relatively tight, to more reasonably allocate logistics resources, the value of β can be appropriately adjusted to balance the influence of the remaining delivery duration on the urgency coefficient. Through the above calculation process, an urgency coefficient W e that accurately reflects the urgency of each package to be delivered can be calculated for each package. Then, combined with the package volume coefficient (by comparing the volume parameters of each package with the average volume of all packages to be delivered during the current transportation cycle, the relative volume ratio is obtained) and the remaining delivery duration coefficient (by comparing the remaining delivery duration with the average delivery duration of the same type of packages statistically obtained by the logistics enterprise based on historical data and performing proportional conversion), a multi-dimensional evaluation matrix is constructed. The dimensions of this matrix include the urgency coefficient, the package volume coefficient, and the remaining delivery duration coefficient, thereby providing comprehensive and accurate basic data for calculating the scheduling priority of each package based on the weighted fuzzy decision algorithm.

[0058] From the perspective of the historical signing time interval, μ (the mean of the historical signing time interval) and σ (the variance) in the formula reflect the central tendency and dispersion degree of the user's historical signing habits. For this part, the historical signing time interval is associated with the maximum allowed delivery duration T max , and the weight is adjusted through the adjustment factor. If the mean of a user's historical signing time interval is small and the variance is also small, it indicates that the user receives packages relatively punctually and regularly. When calculating the urgency coefficient, the value of this term is relatively large, meaning that in the current logistics scheduling, the package of this user may have a higher urgency and should be given priority for delivery, so as to better meet the user's habits and improve user satisfaction.

[0059] From the perspective of the current remaining delivery duration analysis, this part reflects the influence of the remaining delivery duration T re on the urgency coefficient through an exponential function. When the remaining delivery duration T re is short, the exponential function The value is relatively large, making the calculation result of this item relatively large, thereby increasing the urgency coefficient of the package, prompting the logistics system to give priority to processing packages approaching the deadline, and avoiding delays.

[0060] In this embodiment, the urgency coefficient comprehensively considers the user's historical signing habits and the current remaining delivery duration. Through a flexible and adjustable adjustment factor, it provides a scientific, accurate and highly adaptable urgency evaluation method for logistics scheduling, which helps to optimize the allocation of logistics resources, improve the efficiency of logistics distribution, reduce package backlogs, and enhance the quality of user services.

[0061] S230. According to the evaluation matrix, calculate the scheduling priority of each package through the weighted fuzzy decision algorithm; based on the sorting result of the scheduling priority, automatically assign the packages with a priority lower than the critical value to the next delivery cycle.

[0062] Preferably, the weighted fuzzy decision algorithm is expressed as follows:

[0063] P = γ1·W e + γ2·S e + γ3·T e ,

[0064] In the formula, P is the scheduling priority, W e is the urgency coefficient, S e is the normalized package volume coefficient, T e is the remaining delivery duration urgency coefficient, and γ1, γ2 and γ3 are dynamic weight parameters.

[0065] After the construction of the multi-dimensional evaluation matrix is completed, that is, a matrix containing dimension information such as the urgency coefficient W e , the package volume coefficient S e , and the remaining delivery duration coefficient T e is obtained, and it enters the key link of calculating the scheduling priority of each package through the weighted fuzzy decision algorithm.

[0066] Based on in-depth analysis of a large number of actual logistics distribution cases and a comprehensive understanding of the logistics business process, the logistics scheduling expert team uses multi-criteria decision analysis methods such as the Analytic Hierarchy Process (AHP) to comprehensively consider the relative importance of different factors in the actual logistics scheduling scenario, and assigns weight values γ1, γ2, and γ3 to the urgency coefficient, package volume coefficient, and remaining delivery duration coefficient respectively. When determining the weight values, various factors will be fully considered. For example, during e-commerce promotion activities, consumers' requirements for the timeliness of packages increase significantly. At this time, the weight of the urgency coefficient will increase accordingly to highlight the priority satisfaction of user needs; during periods of tight logistics transportation resources, the size of the package has a more critical impact on the loading efficiency of transportation tools and the occupancy of warehouse space, so the weight of the package volume coefficient will be increased. To ensure the rationality and accuracy of the weights, the expert team will conduct multiple simulations and verifications, and continuously adjust the weight values based on actual logistics operation data and feedback to adapt to different logistics scenarios and business requirements.

[0067] In the weighted fuzzy decision algorithm, the fuzzy set theory is used to handle the uncertainty and fuzziness of each coefficient. For each package, the urgency coefficient, package volume coefficient, and remaining delivery duration coefficient in the evaluation matrix are multiplied by the corresponding weight values respectively to obtain the weighted coefficient values. These weighted coefficient values are then comprehensively calculated. A common calculation method is summation, that is, the scheduling priority P = γ1·W e +γ2·S e +γ3·T e . During the calculation process, fuzzy logic rules can also be used to fuzzify each coefficient. For example, the coefficient values can be divided into different fuzzy levels (such as high, medium, low), and reasoning can be carried out according to the fuzzy inference rules to more accurately reflect the complex situation in actual logistics scheduling. For example, when the urgency coefficient is at the "high" level, the package volume coefficient is at the "medium" level, and the remaining delivery duration coefficient is at the "low" level, according to the pre-set fuzzy inference rules, the scheduling priority of the package is calculated through weighted calculation.

[0068] After calculating the scheduling priorities of all packages, sort all packages according to the calculated priority values. The sorting method can be selected as descending or ascending according to actual needs. Usually, descending order (i.e., the priority values from large to small) can more intuitively show the priority levels of each package. Identify the packages with priorities lower than a pre-set critical value. The setting of this critical value is also based on in-depth analysis of logistics operations and practical experience. Through statistical analysis of historical logistics data and simulation experiments, a reasonable threshold is determined to ensure that, on the premise of meeting user needs, the logistics resource allocation is optimized to the greatest extent. For the packages with priorities lower than the critical value, remove them from the task list of the current delivery cycle and reassign them to the to-be-delivered task queue of the next delivery cycle. During the assignment process, comprehensively consider the logistics resource situation of the next delivery cycle, such as the transportation capacity of transportation tools, the number and work arrangements of delivery personnel, the available capacity of storage space, etc., to ensure that the re-assigned packages can be properly handled at the appropriate time and conditions, realizing the efficient utilization and reasonable allocation of logistics resources, thus effectively avoiding the package backlog problem at the logistics terminal and improving the operation efficiency and service quality of the entire logistics distribution system.

[0069] In this embodiment, by fully mining the user's historical signature time interval data, combining with the multi-dimensional evaluation matrix and the weighted fuzzy decision algorithm, the intelligence and flexibility of logistics scheduling are realized, and the package backlog problem at the logistics terminal is effectively solved. Specifically, based on the calculation of the urgency coefficient of the user's historical behavior, the time limit requirements of different users can be accurately identified, so as to optimize the delivery priority sorting. The introduction of multi-dimensional parameters such as the package volume coefficient and the remaining delivery duration coefficient ensures the comprehensiveness and scientificity of the scheduling decision. The dynamic adjustment mechanism further enhances the system's adaptability to complex scenarios, avoiding resource waste, improving the delivery efficiency, and greatly improving the user experience, providing key technical support for the intelligent upgrade of the logistics industry.

[0070] Preferably, the dynamic update mechanism of the historical signature time interval set includes:

[0071] After completing the delivery of a new package, add the actual signature time interval to the time series database of the corresponding user;

[0072] Adopt a sliding window mechanism to maintain the recent N delivery records, where N is dynamically adjusted according to user activity.

[0073] To ensure that the set of historical receipt time intervals can reflect the user's recent receiving habits in real time, the system adopts a sliding window mechanism to maintain the most recent N delivery records. The sliding window mechanism is a commonly used technique in data processing and analysis. It defines a fixed-size window and slides it over the data sequence to achieve dynamic screening and analysis of the data. The size of the sliding window is N, that is, the window always contains the historical receipt time interval records of the most recent N deliveries. As new packages are continuously delivered and the actual receipt time intervals are continuously added, the sliding window will automatically slide forward, removing the earliest record from the window and incorporating the new record into the window. For example, when N = 5, assuming the records in the current window are the historical receipt time intervals of the 1st, 2nd, 3rd, 4th, and 5th deliveries, after the 6th delivery is completed and the actual receipt time interval is added to the database, the sliding window will automatically slide forward. At this time, the records in the window become the historical receipt time intervals of the 2nd, 3rd, 4th, 5th, and 6th deliveries, and the record of the 1st delivery is removed from the window.

[0074] To make the sliding window mechanism more flexible and adaptable to the characteristics of different users, the value of N is dynamically adjusted according to user activity. The number of packages received by the user within a certain time period (such as the past month, three months, etc.) is counted. If the user receives a large number of packages within this time period, it indicates that the user has a high level of activity; conversely, if the number of received packages is small, it indicates that the user has a low level of activity. For example, if a user received 10 packages in the past month, while another user only received 2 packages in the same time, then the former has a relatively higher level of activity. In addition to the package receiving frequency, the system also monitors other related behaviors of the user's use of the logistics service, such as the frequency of querying logistics information, the number of times of modifying the delivery address, etc. If the user frequently queries logistics information or modifies the delivery address multiple times, it indicates that the user has a high level of attention to the logistics service and a correspondingly high level of activity. The feedback and evaluation information of the user on the logistics service is collected, such as the satisfaction evaluation, complaint suggestions, etc. submitted by the user after completing the package receipt. Users who actively participate in feedback and evaluation usually have a high level of activity.

[0075] Based on the monitoring results of user activity, the value of N is dynamically adjusted. For users with a high level of activity, the value of N is appropriately increased to obtain more historical delivery records and more comprehensively understand the user's receiving habits and patterns. For example, for users with extremely high activity, the value of N can be adjusted from the default 5 to 8 or 10. For users with a low level of activity, the value of N is appropriately decreased to reduce data storage and computational volume, while ensuring that the records in the window can reflect the limited recent receiving situation of the user. For example, for users with extremely low activity, the value of N can be adjusted from 5 to 3.

[0076] In this embodiment, through the dynamic update mechanism, the set of historical receipt time intervals can reflect the latest receiving habits and patterns of users in real time and accurately, providing more reliable and effective data support for calculating the urgency coefficient based on the historical receipt time intervals and the entire logistics scheduling decision-making in the subsequent stage. Thus, it further improves the intelligent level and service quality of logistics scheduling and better solves practical problems such as package backlog at the final logistics station.

[0077] Preferably, the calculation of the package volume coefficient includes:

[0078] Establish a volume classification model to map the package size to a preset volume level;

[0079] According to the actual loading capacity of the delivery vehicle, calculate the space occupancy weight of each volume level.

[0080] In order to more effectively manage and analyze the impact of package volume on logistics scheduling, a scientific and reasonable volume classification model is constructed. The establishment of this model is based on the statistical analysis of a large amount of package size data. By investigating and classifying the common size ranges of different types of packages (such as electronic products, clothing, household items, etc.), a series of representative volume intervals are determined as the preset volume levels. For example, packages with a relatively small volume (such as length, width, and height all less than 20 cm) are classified into the "small package" level, packages with a medium volume (such as length, width, and height between 20 - 50 cm) are classified into the "medium package" level, and packages with a large volume (such as length, width, and height greater than 50 cm) are classified into the "large package" level. When a new package enters the logistics system, the length, width, and height size data of the package are obtained through high-precision measurement devices (such as laser rangefinders, 3D scanners, etc.), and then according to the preset volume level standard, the package size is accurately mapped into the corresponding volume level. This volume classification method can simplify and classify the complex and diverse package volume information, facilitating subsequent analysis and processing.

[0081] During the logistics distribution process, packages of different volume levels occupy different amounts of space in distribution tools (such as trucks, express delivery tricycles, etc.). Therefore, it is necessary to calculate the space occupancy weights of each volume level according to the actual loading capacity of the distribution tools. Collect and analyze the detailed parameters of various distribution tools, including information such as the carriage volume, internal dimensions, and loading restrictions. For example, for a standard van, its carriage volume is 10 cubic meters, and its internal dimensions are 4 meters in length, 2 meters in width, and 1.25 meters in height. Considering factors such as the stacking method of goods, loading and unloading convenience, and the vehicle's load limit, the system will calculate the space proportion that packages of different volume levels can occupy in this truck through complex mathematical models and algorithms. For the "small package" level, assuming its average volume is 0.01 cubic meters and it can be placed and stacked more flexibly in the truck, after calculation, its space occupancy weight may be set to 0.1; for the "medium package" level, with an average volume of 0.1 cubic meters, due to its relatively large size, space utilization and cargo stability need to be considered during loading, and its space occupancy weight may be set to 0.3; for the "large package" level, with an average volume of 1 cubic meter, due to its large space occupancy and the possible need for special loading methods, its space occupancy weight may be set to 0.6. Through such a calculation method, it can accurately reflect the relative importance of packages of different volume levels in actually occupying space in the distribution tool, providing an important basis for subsequent logistics scheduling decisions.

[0082] By establishing a volume classification model to map the package size to a preset volume level and calculating the space occupancy weights of each volume level according to the actual loading capacity of the distribution tool, it is possible to comprehensively and accurately quantify the impact of the package volume on logistics scheduling. Thus, when calculating the package volume coefficient, the actual role of the package volume in logistics resource allocation can be fully considered, making the logistics scheduling more scientific and reasonable, effectively improving the logistics distribution efficiency, reducing the logistics cost, and better adapting to the needs of different distribution tools and logistics scenarios, further optimizing the performance of the entire logistics scheduling and distribution system.

[0083] Preferably, the method further includes:

[0084] When it is detected that the remaining delivery duration coefficient of a certain package is lower than the safety threshold, automatically trigger the manual review process;

[0085] Generate a visual warning interface to display the spatio-temporal trajectory map of the package and the historical behavior characteristics of the associated user.

[0086] Through the real-time monitoring mechanism, continuously obtain the current moment information of each package, and accurately calculate the time difference with the preset delivery deadline of the package. Then, based on the average delivery duration of the same type of packages statistically obtained by the logistics enterprise from historical data, calculate the remaining delivery duration coefficient through a predefined proportional conversion. Once the system determines that the remaining delivery duration coefficient of a certain package is lower than the pre-set safety threshold, it immediately initiates an automatic trigger for the manual review process. In this process, the system quickly pushes the relevant key information of this package, such as the package number, origin station, destination station, type of goods, estimated weight, etc., to the working platform of the manual review team. The manual review team consists of experienced logistics schedulers who have professional logistics knowledge and rich practical experience, and can conduct in-depth analysis and judgment on the delivery situation of the package.

[0087] Generate a visual alarm interface to intuitively and clearly display the spatio-temporal trajectory map of the package and the historical behavior characteristics of the associated user. The spatio-temporal trajectory map integrates the package location information and corresponding timestamps recorded at each key node in the logistics information system, and uses geographic information system (GIS) technology and data visualization algorithms to present the complete transportation route of the package from the origin to the current location in the form of a dynamic map, including details such as the residence time of the package at each transfer station and the driving path during transportation. The historical behavior characteristics of the associated user are obtained through in-depth mining and analysis of the user's historical data in the logistics system, covering multi-dimensional information such as the user's historical signing time interval, historical package volume preference, whether frequently modifying the delivery address, and evaluation feedback on logistics services. These information are intuitively displayed in the visual alarm interface in the form of charts, reports, etc., facilitating the manual review team to comprehensively understand the delivery status of the package and the characteristics of the associated user, thereby quickly and accurately judging possible problems in the package delivery process and formulating targeted solutions, such as adjusting the delivery route, increasing the input of delivery resources, communicating and negotiating with the user for a new delivery time, etc., effectively ensuring that the package can be delivered on time, improving the quality of logistics services, reducing the risk of package delays, and further optimizing the reliability and stability of the entire logistics scheduling and delivery system.

[0088] In summary, the method provided in this embodiment can at least achieve the following effects:

[0089] By fully mining the historical delivery time interval data of users and combining with the multi-dimensional evaluation matrix and weighted fuzzy decision algorithm, the intelligence and flexibility of logistics scheduling are realized, effectively solving the problem of package backlog at the final logistics station. Specifically, based on the calculation of the urgency coefficient of users' historical behaviors, the time limit requirements of different users can be accurately identified, so as to optimize the sorting of delivery priorities. By introducing multi-dimensional parameters such as the package volume coefficient and the remaining delivery time coefficient, the comprehensiveness and scientificity of the scheduling decision are ensured. The dynamic adjustment mechanism further enhances the system's adaptability to complex scenarios, avoiding resource waste, improving the delivery efficiency, and greatly enhancing the user experience, providing key technical support for the intelligent upgrade of the logistics industry.

[0090] See Figure 2 , in one embodiment, an intelligent logistics scheduling and delivery system is further provided. The system includes:

[0091] A data acquisition module 100, configured to acquire a data set of packages to be delivered in the current delivery cycle. The data set includes the delivery deadline, volume parameter, and target user identifier of each package;

[0092] A dynamic scheduling trigger module 200, configured to execute a dynamic scheduling strategy when the number of packages to be delivered exceeds a preset threshold;

[0093] The execution of the dynamic scheduling strategy includes:

[0094] Retrieving historical delivery records based on the target user identifier, and calculating the set of historical delivery time intervals corresponding to each user. The historical delivery time interval refers to the time difference between the moment when the package arrives at the final delivery node and the moment when the user actually signs for it;

[0095] Calculating the urgency coefficient according to the set of historical delivery time intervals; constructing a multi-dimensional evaluation matrix, and the dimensions of the evaluation matrix include the urgency coefficient, the package volume coefficient, and the remaining delivery time coefficient;

[0096] According to the evaluation matrix, calculating the scheduling priority of each package through a weighted fuzzy decision algorithm; based on the sorting result of the scheduling priority, automatically allocating the packages with a priority lower than the critical value to the next delivery cycle.

[0097] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0098] The present invention also provides an electronic device, including a processor and a memory. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the method according to any one of the above possible implementation manners.

[0099] The present invention also provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor is caused to execute the method according to any one of the above possible implementation manners.

[0100] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0101] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. Those skilled in the art can also clearly understand that each embodiment of the present invention has different emphases. For the convenience and brevity of description, the same or similar parts may not be elaborated in different embodiments. Therefore, the parts not described or not detailedly described in a certain embodiment can be referred to the descriptions of other embodiments.

Claims

1. An intelligent logistics dispatching and distribution method, characterized in that: The method comprises: Obtaining a data set of packages to be delivered in the current delivery cycle, the data set including a delivery deadline, volume parameters, and a target user identifier of each package; When the number of packages to be delivered exceeds a preset threshold, a dynamic scheduling strategy is executed; The execution of the dynamic scheduling strategy includes: Based on the target user identifier, retrieve the historical delivery records and calculate the set of historical receipt time intervals corresponding to each user, where the historical receipt time interval refers to the time difference between the time when the package arrives at the final delivery node and the time when the user actually receives the package; Calculate the urgency coefficient based on the historical signing time interval set; construct a multi-dimensional evaluation matrix, the dimensions of which include the urgency coefficient, the package volume coefficient, and the remaining delivery time coefficient; According to the evaluation matrix, the dispatch priority of each package is calculated through a weighted fuzzy decision algorithm; based on the dispatch priority sorting results, the packages with a priority lower than the critical value are automatically assigned to the next delivery cycle.

2. The intelligent logistics dispatching and distribution method according to claim 1 is characterized in that: The dynamic update mechanism of the historical receipt time interval set includes: When the new package is delivered, the actual signing time interval is added to the corresponding user's time series database; A sliding window mechanism is used to maintain the most recent N delivery records, where N is dynamically adjusted based on user activity.

3. The intelligent logistics dispatching and distribution method according to claim 1 is characterized in that: The urgency coefficient is calculated according to the following algorithm: Where W e is the urgency coefficient, μ is the mean of the historical signing time interval, σ is the variance, T max is the maximum allowed delivery time, T re is the current remaining delivery time, α and β are adjustment factors, and the default values ​​are both 0.

5.

4. The intelligent logistics dispatching and distribution method according to claim 3 is characterized in that: The weighted fuzzy decision algorithm is expressed as follows: P=γ1·W e +γ2·S e +γ3·T e , Where P is the scheduling priority, W e is the urgency coefficient, S e is the normalized package volume coefficient, T e is the urgency coefficient of the remaining delivery time, and γ1, γ2 and γ3 are dynamic weight parameters.

5. The intelligent logistics dispatching and distribution method according to claim 4 is characterized in that: The calculation of the package volume coefficient includes: Establish a volume classification model to map package sizes to preset volume classes; According to the actual loading capacity of the delivery vehicle, the space occupancy weight of each volume level is calculated.

6. The intelligent logistics dispatching and distribution method according to claim 1 is characterized in that: The method further comprises: When it is detected that the remaining delivery time coefficient of a package is lower than the safety threshold, the manual review process is automatically triggered; Generate a visual alarm interface to display the spatiotemporal trajectory map of the package and the historical behavior characteristics of the associated users.

7. An intelligent logistics dispatching and distribution system, characterized in that: The system comprises: A data acquisition module, used to acquire a data set of packages to be delivered in the current delivery cycle, wherein the data set includes a delivery deadline, a volume parameter, and a target user identifier of each package; A dynamic scheduling trigger module, used to execute a dynamic scheduling strategy when the number of packages to be delivered exceeds a preset threshold; The execution of the dynamic scheduling strategy includes: Based on the target user identifier, retrieve the historical delivery records and calculate the set of historical receipt time intervals corresponding to each user, where the historical receipt time interval refers to the time difference between the time when the package arrives at the final delivery node and the time when the user actually receives the package; Calculate the urgency coefficient based on the historical signing time interval set; construct a multi-dimensional evaluation matrix, the dimensions of which include the urgency coefficient, the package volume coefficient, and the remaining delivery time coefficient; According to the evaluation matrix, the dispatch priority of each package is calculated through a weighted fuzzy decision algorithm; based on the dispatch priority sorting results, the packages with a priority lower than the critical value are automatically assigned to the next delivery cycle.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions. When the processor executes the computer instructions, the electronic device executes the intelligent logistics scheduling and distribution method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the intelligent logistics scheduling and distribution method according to any one of claims 1 to 6.

Images