Big data adaptive analysis logistics work order management method and system and medium

Abstract

The application provides a logistics work order management method and system for big data adaptive analysis and a medium, relates to the technical field of big data processing, and comprises the following steps: performing multi-modal data acquisition to obtain multiple meal characteristic information and multiple logistics demand information of multiple meal delivery tasks; performing temperature-sensitive demand grouping to obtain P groups of meal delivery tasks; performing space-time path merging to output K initial task sequences; calling logistics box volume characteristics, performing loading conflict analysis, and outputting K loading conflict information; performing cross-box collaborative analysis to obtain W target task sequences; and constructing a logistics work order to schedule temperature-sensitive logistics box delivery of multiple meal delivery tasks. The application solves the technical problems that the logistics work order management of the prior art is mainly concentrated in static task allocation and path optimization, cannot fully utilize meal characteristic information for dynamic adaptation, and results in low delivery efficiency and unguaranteed product quality in high sensitivity delivery scenarios.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data processing, and particularly relates to a logistics work order management method and system based on big data adaptive analysis and a medium. BACKGROUND

[0002] With the increasing demand for the distribution of fresh food, medicine and other high-sensitivity goods, how to ensure that the food or medicine products in the transportation process remain in the best state under suitable preservation conditions has become a major challenge, especially in the distribution of temperature-sensitive goods. The mismatch of preservation conditions may cause the product to deteriorate, thereby affecting its quality and safety. Existing logistics work order management technology mainly focuses on static task allocation and path optimization, and fails to fully utilize food characteristics information (such as preservation temperature, temperature sensitivity, etc.) for dynamic adaptation, resulting in the inability to effectively avoid food deterioration caused by the mismatch of preservation conditions during transportation. Therefore, in the high-sensitivity distribution scenario, there are often problems such as low distribution efficiency and unguaranteed product quality. SUMMARY

[0003] The present application provides a logistics work order management method and system based on big data adaptive analysis and a medium, aiming to solve the technical problems of the prior art that the logistics work order management mainly focuses on static task allocation and path optimization, fails to fully utilize food characteristics information for dynamic adaptation, and results in low distribution efficiency and unguaranteed product quality in the high-sensitivity distribution scenario.

[0004] The first aspect of the present application provides a logistics work order management method based on big data adaptive analysis, which comprises: obtaining multiple food characteristics information and multiple logistics demand information of multiple food distribution tasks by performing multi-modal data collection in a food task center; grouping the multiple food distribution tasks according to the multiple food characteristics information, obtaining P groups of food distribution tasks; merging the space-time paths according to the multiple logistics demand information, taking the P groups of food distribution tasks as constraints, and outputting K initial task sequences; calling the logistics box volume characteristics locally, and performing loading conflict analysis on the K initial task sequences according to the logistics box volume characteristics and the multiple food characteristics information, and outputting K loading conflict information; performing cross-box collaborative analysis according to the K loading conflict information, updating the K initial task sequences according to the analysis results, and obtaining W target task sequences, wherein W is a positive integer greater than K; and constructing a logistics work order based on the W target task sequences to distribute the multiple food distribution tasks by using temperature-sensitive logistics boxes.

[0005] In a second aspect, the application discloses a logistics work order management system for big data adaptive analysis, which is used for the logistics work order management method for big data adaptive analysis. The system comprises a data acquisition module, a demand grouping module, a space-time path merging module, a loading conflict analysis module, an initial task updating module and a distribution module. The data acquisition module is used for acquiring multiple meal characteristic information and multiple logistics demand information of multiple meal delivery tasks by performing multi-modal data acquisition in a meal task center. The demand grouping module is used for grouping temperature-sensitive demands of the multiple meal delivery tasks according to the multiple meal characteristic information, and obtaining P groups of meal delivery tasks. The space-time path merging module is used for merging space-time paths according to the multiple logistics demand information, taking the P groups of meal delivery tasks as constraints, and outputting K initial task sequences. The loading conflict analysis module is used for locally calling logistics box volume characteristics, and performing loading conflict analysis on the K initial task sequences according to the logistics box volume characteristics and the multiple meal characteristic information, and outputting K loading conflict information. The initial task updating module is used for performing cross-box collaborative analysis according to the K loading conflict information, and updating the K initial task sequences according to an analysis result, and obtaining W target task sequences, wherein W is a positive integer greater than K. The distribution module is used for constructing logistics work orders based on the W target task sequences, so as to schedule temperature-sensitive logistics box to deliver the multiple meal delivery tasks.

[0006] In a third aspect, the application discloses a storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the logistics work order management method for big data adaptive analysis in the first aspect are implemented.

[0007] The one or more technical solutions provided in the application have at least the following beneficial effects:

[0008] Through multi-modal data collection, meal characteristics information and logistics demand information can be collected from multiple sources. After big data processing, comprehensive analysis and accurate grouping of complex distribution tasks can be realized. Multi-modal data collection enables the system to process data from different sources and effectively integrate and apply them. Based on the temperature control characteristics of meals, multi-modal data collection enables the system to process data from different sources and effectively integrate and apply them. Based on the temperature control characteristics of meals, big data analysis is used to group temperature-sensitive demand for multiple distribution tasks, so that meals with similar temperature control requirements can be reasonably allocated to the same group. This grouping method makes the distribution path planning and resource allocation more targeted, reducing unnecessary resource waste. According to the results of temperature-sensitive demand grouping, combine multiple logistics demand information to merge space-time paths. This process optimizes the distribution route and combines temperature control and timeliness requirements to generate an initial task sequence, providing effective path planning for subsequent task scheduling. Through big data processing technology, analyze the matching of meals and logistics boxes and identify potential loading conflicts. This analysis result provides data support for subsequent cross-box collaborative analysis, further optimizing the task sequence and resource allocation, and improving the utilization of logistics resources. Based on the optimization results of the target task sequence, intelligently build a logistics work order and distribute it according to the scheduling requirements of temperature-sensitive logistics boxes. Big data processing makes the generation of logistics work orders more efficient, and can dynamically adjust the scheduling scheme according to the characteristics of meals and distribution requirements, thereby improving the execution efficiency of distribution tasks.

[0009] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the content of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 The big data adaptive analysis logistics work order management method flowchart provided by the embodiments of the present application.

[0011] Figure 2 The big data adaptive analysis logistics work order management system structure diagram provided by the embodiments of the present application.

[0012] Explanation of reference signs: data collection module 10, demand grouping module 20, space-time path merging module 30, loading conflict analysis module 40, initial task updating module 50, distribution module 60. DETAILED DESCRIPTION

[0013] The embodiment of the application provides a logistics work order management method and system based on big data adaptive analysis and a medium, and solves the technical problems that the logistics work order management in the prior art mainly focuses on static task allocation and path optimization, cannot fully utilize meal characteristics information for dynamic adaptation, and results in low delivery efficiency and unguaranteed product quality in a high sensitivity delivery scenario.

[0014] After introducing the basic principle of the application, various non-limiting embodiments of the application will be specifically introduced in combination with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the application and not to limit the application.

[0015] Embodiment one, as shown in the figure, the embodiment of the application provides a logistics work order management method based on big data adaptive analysis, which comprises the following steps: Figure 1

[0016] Through multi-modal data collection in the meal task center, a plurality of meal characteristics information and a plurality of logistics demand information of a plurality of meal delivery tasks are obtained.

[0017] The meal characteristics information and the logistics demand information of a plurality of meal delivery tasks are collected by performing multi-modal data collection, wherein the meal characteristics information includes temperature sensitivity level, three-dimensional volume model, transportation time limit threshold, etc. The temperature sensitivity level is the temperature requirement of the meal, for example, the temperature requirement is within the range of 0-5℃±ΔT, ΔT is a preset temperature fluctuation interval, which means that the temperature of the meal must be kept within the specified temperature interval during the delivery process to ensure its quality and safety; the three-dimensional volume model is the volume data of the meal, which is helpful for subsequent logistics planning, especially for the rational use of space during packaging and transportation; the transportation time limit threshold refers to the maximum time limit that each meal needs to maintain during the delivery process, that is, it must be completed within a certain time to prevent expiration or quality decline. The logistics demand information includes start and end point coordinates, path priority, wherein the start and end point coordinates are the geographic coordinates of the starting point and the ending point of each delivery task, which helps to define the delivery route; in a plurality of delivery tasks, some meals may need to be delivered preferentially due to special requirements (such as temperature sensitivity), and the path priority indicates the priority of these tasks so as to give priority to these requirements when planning the delivery path.

[0018] According to the plurality of meal characteristics information, the plurality of meal delivery tasks are grouped according to temperature sensitivity requirements, and P groups of meal delivery tasks are obtained.

[0019] ​On the basis of the collected meal characteristic information, the meal delivery tasks are grouped according to temperature-sensitive requirements. Specifically, according to the temperature-sensitive level of each meal, the delivery tasks with the same temperature requirement are grouped into one group. For example, all meals requiring delivery within a temperature range of 0-5℃±ΔT are grouped into one group. This grouping is to ensure that meals in the same group can be kept at similar temperature conditions during delivery, avoiding quality problems caused by inconsistent delivery temperatures. After grouping, P groups of meal delivery tasks are obtained.

[0020] With the P groups of meal delivery tasks as constraints, the spatio-temporal path merging is performed according to the plurality of logistics requirement information, and K initial task sequences are output.

[0021] Spatio-temporal path merging refers to integrating paths between tasks based on the known start and end point coordinates, transportation time limit, path priority, and other requirements of each delivery task. The purpose of merging is to optimize delivery routes, reduce delivery time and cost, and improve overall efficiency. The constraints in the merging process include temperature control requirements, transportation time limit, path priority, etc. According to the results of spatio-temporal path merging, K initial task sequences are generated. These sequences are the preliminary results of task allocation and need to be further optimized in subsequent steps.

[0022] The local logistics box volume characteristics are called, and loading conflict analysis is performed on the K initial task sequences based on the logistics box volume characteristics and the plurality of meal characteristic information, and K loading conflict information is output.

[0023] After generating K initial task sequences, loading conflict analysis is performed on them. This step is based on the volume characteristics of the logistics box and the plurality of meal characteristic information to analyze whether there is a conflict in the loading of meals in each task sequence. Specifically, the volume characteristics of the logistics box refer to the capacity and shape characteristics of the logistics box (or delivery vehicle) used to transport meals, such as the volume, shape of the box, and the size of each partition. Different logistics boxes have different loading restrictions, affecting the storage and handling efficiency of meals. Each meal has its specific volume and shape information (represented by a three-dimensional volume model). Therefore, the volume and shape information of the meal need to be combined with the volume characteristics of the logistics box to calculate whether the meals in each delivery task can be reasonably loaded in the specified logistics box. If the volumes and shapes of multiple meals do not match the box volume, loading conflicts may occur.

[0024] The loading conflict analysis is used to determine whether the meal items in the task sequence can be successfully loaded into the delivery box due to the volume, weight, etc. Specifically, if the number or volume of meal items in a logistics box exceeds the volume limit, or the shape of the meal items does not match the structure of the current box (e.g., there are multiple partitioned areas in the box), a loading conflict will occur. In order to accurately analyze the loading conflict, a three-dimensional modeling technology is used to model each meal item and logistics box, and a simulation method is used to analyze the conflict during the loading process. These three-dimensional models can reflect the volume and shape of the meal items, and help calculate the space utilization during loading. Based on the above analysis, K loading conflict information is output, which indicates the possible loading conflict in each initial task sequence, for example, some meal items need to use a larger volume logistics box, or some meal items need to change the loading order. The loading conflict information provides a basis for subsequent optimization.

[0025] Based on the K loading conflict information, cross-box collaborative analysis is performed, and the K initial task sequences are updated based on the analysis results to obtain W target task sequences, where W is a positive integer greater than K.

[0026] Cross-box collaborative analysis is an analysis of the collaborative relationship between multiple logistics boxes (or delivery vehicles) to ensure that the loading problem of meal items in the overall delivery process is effectively optimized. At this time, a single logistics box may not be able to perfectly solve all loading conflicts, so the collaborative cooperation of multiple logistics boxes needs to be considered. Through cross-box collaborative analysis, meal items are redistributed so that the loading of each delivery box is more efficient. If the space of a certain box is not fully utilized, excess meal items in other boxes can be transferred to ensure that the space of each box is fully utilized. For task sequences with conflicts, cross-box collaborative analysis can also adjust the loading order of meal items to reduce loading conflicts in each logistics box and avoid space waste. Through collaborative analysis, the delivery path, time efficiency requirement, and priority of each box in the cross-box delivery process can be coordinated.

[0027] After cross-box collaborative analysis, the K initial task sequences are adjusted and updated based on the analysis results. The key to this process is effective loading and path planning, which avoids loading conflicts and space waste and ensures that each delivery box can carry tasks more efficiently. Finally, W target task sequences are generated. Since cross-box collaborative analysis introduces the cooperation of multiple logistics boxes, W is greater than K, indicating that more target task sequences are generated after optimization, and the task allocation is more balanced.

[0028] Based on the W target task sequences, a logistics work order is constructed to schedule the delivery of the plurality of meal delivery tasks by the temperature-sensitive logistics boxes.

[0029] Based on the optimized W target task sequences, a logistics work order is constructed for scheduling temperature-sensitive logistics boxes to deliver multiple meal delivery tasks. The logistics work order contains detailed information of the delivery tasks, including task sequence, logistics box configuration, delivery time limit, path information, etc. The logistics work order is an important basis for the scheduling system. The dispatcher will arrange delivery vehicles, determine the delivery sequence and adjust the appropriate temperature-sensitive logistics box based on the work order. Through the detailed information in the work order, the dispatcher can ensure that each delivery task can be reasonably allocated resources to ensure the timeliness and temperature control requirements of delivery.

[0030] Further, by performing multi-modal data collection at the meal task center, a plurality of meal characteristics information and a plurality of logistics demand information of a plurality of meal delivery tasks are obtained. The method comprises:

[0031] At the meal task center, multi-dimensional temperature-sensitive parameter mapping is performed according to the task type of the first meal delivery task to obtain a first preservation temperature interval, a first temperature sensitivity weight, a first meal volume model and a first time limit tolerance. The first preservation temperature interval, the first temperature sensitivity weight and the first meal volume model constitute the first meal characteristics information. The first task order of the first meal delivery task is analyzed to obtain a first reference transportation time limit and first start and end point coordinates. According to the first time limit tolerance and the first reference transportation time limit, a first transportation time limit threshold is calculated. The first transportation time limit threshold and the first start and end point coordinates constitute the first logistics demand information.

[0032] According to the task type of the first meal delivery task, the delivery requirement of the meal is identified, and the task type includes, for example, cold chain delivery, normal temperature delivery, hot chain delivery, etc., which will affect the temperature control requirement and the time limit. For different task types, the following aspects are mapped and calculated to obtain the temperature-sensitive characteristics of the meal, including: a first preservation temperature interval, based on the task type, the temperature interval that the meal needs to maintain during delivery is determined, for example, for a cold chain delivery task, the temperature interval may be 0-5℃, to ensure that the meal remains fresh, if the task type is hot chain delivery, a higher temperature needs to be maintained (such as 60-70℃) to avoid the meal from cooling down; a first temperature sensitivity weight, the temperature sensitivity weight reflects the sensitivity of the meal to temperature changes, and the temperature sensitivity weight is calculated according to the characteristics of the meal (such as whether it is perishable or requires special temperature control), which means that some meals may be very sensitive to temperature changes, so higher priority and more stringent temperature control requirements are required; a first meal volume model, a three-dimensional volume model of the meal is generated according to its shape, size, weight and other characteristics, which helps subsequent loading analysis, path planning and space optimization; a first time limit tolerance, the time limit tolerance reflects the flexibility of the meal delivery time limit, some meals may have very strict time requirements, while some meals can be delivered within a certain time limit, by analyzing the task type and meal characteristics, the specific value of the time limit tolerance is determined. Through the above mapping process, the first preservation temperature interval, the first temperature sensitivity weight, the first meal volume model and the first time limit tolerance are obtained, which constitute the first meal characteristic information.

[0033] The first task order contains all information related to the delivery task, and key data is automatically extracted from the task order, including a first baseline transportation time limit and first start and end point coordinates, wherein the baseline transportation time limit refers to the standard transportation time from the task starting point to the ending point, and in the absence of other influencing factors (such as traffic conditions, weather, etc.), the baseline transportation time limit defines the ideal time required for delivery; the start and end point coordinates are the geographic coordinates of the starting location and target location of the delivery task, which are used for path planning to ensure that the delivery task can be completed smoothly.

[0034] The first transportation time limit threshold is calculated based on the first time tolerance and the first benchmark transportation time limit, and the first logistics demand information is obtained in combination with the first start-stop point coordinates. Specifically, the transportation time limit threshold is a flexible time window indicating how long the task must be completed for delivery, which is calculated based on the benchmark transportation time limit and the time tolerance. The calculation of this threshold takes into account the time tolerance of the meal, so it can tolerate certain time fluctuations. For example, if the time tolerance is large, the delivery task can be completed in a longer period of time, otherwise the time requirement is more stringent and needs to be shortened as much as possible. According to the first transportation time limit threshold and the start-stop point coordinates, the first logistics demand information is formed, which provides key data support for subsequent delivery path planning, temperature-sensitive logistics box scheduling, etc., ensuring that the meal can be delivered to the destination within a reasonable time and under appropriate temperature conditions.

[0035] Further, the space-time path merging is performed according to the plurality of logistics demand information under the constraint of the P groups of meal delivery tasks, and K initial task sequences are output. The method comprises:

[0036] The first group of logistics demand information corresponding to the first group of meal delivery tasks is extracted from the plurality of logistics demand information, wherein the first group of meal delivery tasks comprises T meal delivery tasks; a high sensitivity task feature is preset, and the high sensitivity task feature is used to traverse the first group of meal characteristics information of the first group of meal delivery tasks to locate N seed delivery tasks, wherein the high sensitivity task feature comprises temperature interval scale and temperature sensitivity weight scale; the first logistics demand information is decomposed to obtain N logistics demand information of the N seed delivery tasks and T-N logistics demand information of the remaining T-N meal delivery tasks; N start-stop point coordinates are extracted from the N logistics demand information to construct N benchmark delivery paths; the T transportation time limit thresholds are used as constraints to perform path filling fitting on the T-N logistics demand information in the N benchmark delivery paths to obtain a first group of initial task sequences; and similarly, after obtaining the P groups of initial task sequences, the group division of the P groups of initial task sequences is removed to obtain the K initial task sequences.

[0037] The first group of logistics demand information corresponding to the first group of meal delivery tasks is extracted from the plurality of logistics demand information, and the first group of meal delivery tasks is a specific group of meal delivery tasks used as the current analysis object, comprising T meal delivery tasks.

[0038] The high-sensitivity task feature is used to measure the sensitivity of the meal delivery task to environmental changes, especially temperature changes. The specific features include temperature interval scale and temperature sensitivity weight scale. The temperature interval scale refers to the range of temperature interval that the meal needs to maintain. For example, some meals may require the temperature to be maintained within the range of 0°C to 5°C, which is relatively narrow and belongs to high-sensitivity tasks. Meals with a wider temperature control interval (e.g., 5°C to 10°C) are less sensitive. The temperature sensitivity weight scale is used to measure the sensitivity of the meal to temperature changes. For example, some meals are prone to quality changes when the temperature changes, so these meals have a higher temperature sensitivity weight.

[0039] Each meal in the first group of meal delivery tasks is analyzed to check their temperature interval scale and temperature sensitivity weight scale to determine whether they meet the criteria of high-sensitivity task features. Specifically, if the temperature control interval of the meal is narrow and the temperature sensitivity weight is high, the meal is considered a high-sensitivity task. Based on the temperature requirements and temperature sensitivity criteria, N seed delivery tasks are selected that require special attention to temperature control to ensure they maintain the appropriate temperature during delivery.

[0040] The first logistics demand information is decomposed into two main parts: N logistics demand information of N seed delivery tasks and T-N logistics demand information of the remaining T-N meal delivery tasks. Specifically, N logistics demand information is determined through the N seed delivery tasks, which have high-sensitivity temperature control and time-sensitive requirements, so they need to be handled separately to ensure their delivery path and time are prioritized. T-N logistics demand information is determined through the remaining T-N meal delivery tasks, which also have temperature control and time-sensitive requirements, but compared to seed delivery tasks, they have lower temperature sensitivity and time-sensitive requirements, so their logistics demand information will be placed in the second group and handled flexibly.

[0041] Each seed delivery task has clear start and end point coordinates, which will be used for path planning. These coordinates are extracted from the logistics demand information of the seed task. The baseline delivery path is the shortest path calculated based on the start and end point coordinates through path planning algorithms (e.g., Dijkstra or A* algorithm). Since the temperature control and timeliness of seed delivery tasks are more stringent, their paths will be planned as priority paths to ensure they can arrive at the destination within the specified time and meet the temperature control requirements.

[0042] The transportation time limit threshold is the maximum time limit of each delivery task calculated according to the time limit tolerance and the benchmark transportation time limit of each delivery task, which limits how long the delivery task must be completed. For the remaining T-N delivery tasks, according to their logistics demand information (including start and end point coordinates and transportation time limit threshold), combined with the existing N benchmark delivery paths, path filling fitting is performed. Specifically, according to the start and end point coordinates and transportation time limit of the remaining tasks, the path is filled on the basis of the benchmark path to ensure that these tasks are completed within the specified time limit. Through path filling fitting, the first group of initial task sequences is generated, which includes the path planning and time limit requirements of the seed delivery task and other tasks.

[0043] According to the generation rule of the first group of initial task sequences, similar path planning and filling are continued for other groups of delivery tasks (such as the second group, the third group, etc.). Through step-by-step optimization of the path and time limit requirements of each task, the P group of initial task sequences is finally generated. Then, the group division is removed, i.e. the division criteria between different groups are no longer considered, to ensure that all initial task sequences are combined together to form the final K initial task sequences. In this way, all delivery tasks will no longer be processed according to the group division, but will be executed according to the optimized task sequences. These task sequences have considered path filling, timeliness optimization, and temperature control requirements, and can efficiently complete the delivery tasks and strictly guarantee the temperature control and timeliness of each task.

[0044] Further, T transportation time limit thresholds are used as constraints, and the T-N logistics demand information is fitted with the N benchmark delivery paths to obtain the first group of initial task sequences. The method comprises:

[0045] T-N start and end point coordinates are extracted from the T-N logistics demand information for feasible path fitting, and T-N accompanying delivery paths are output. The T-N group of accompanying delivery paths is merged into the N benchmark delivery paths with path overlap expansion as a constraint, and N group of expanded delivery paths are output. The N group of expanded delivery paths are combined and enumerated to obtain a plurality of expanded delivery path group sets. Based on the T food delivery tasks, the plurality of expanded delivery path group sets are searched for delivery tasks to obtain O expanded delivery path group sets. The O expanded delivery path group sets are calculated for delivery timeliness, and the T transportation time limit thresholds are used for timeliness adaptability judgment to obtain a target delivery path group set. N target delivery paths in the target delivery path group set are extracted to obtain N initial task sequences, which constitute the first group of initial task sequences.

[0046] From the T-N logistics demand information, extract T-N start and end point coordinates, and perform path fitting on these coordinates, output T-N sets of accompanying distribution paths. Specifically, the T-N logistics demand information corresponds to the remaining T-N distribution tasks, which were not included in the seed distribution tasks in the previous steps, so separate path planning is needed. From the logistics demand information of these distribution tasks, extract the geographic coordinates of the starting point and endpoint of each distribution task, which will be used for subsequent path fitting and planning.

[0047] After obtaining the start and end point coordinates, use path planning algorithms (such as Dijkstra or A* algorithm) to calculate the feasible distribution paths for these distribution tasks. These paths are calculated and fitted according to the start and end point coordinates and other logistics requirements (such as transportation time limit threshold, traffic conditions, etc.). Through path fitting, an accompanying distribution path is generated for each distribution task. This path is the possible route for the distribution task, ensuring that it can be completed within the specified time limit and conditions from the starting point to the endpoint.

[0048] In actual distribution, the distribution paths of different tasks may have overlapping parts, for example, the starting points of two distribution tasks may be the same, or their endpoints may coincide. Path overlap expansion is to make full use of these overlapping parts to reduce distribution time and resource waste. For each set of accompanying distribution paths, perform overlap expansion with the corresponding reference distribution paths. Specifically, combine the T-N sets of accompanying distribution paths with the N reference distribution paths according to the overlapping parts of the paths, thereby generating expanded distribution paths. These expanded paths consider the order of tasks and try to improve path utilization efficiency. According to the path overlap expansion rules, generate N sets of expanded distribution paths. Each set of expanded paths corresponds to a new distribution path, which may include multiple distribution tasks, but not all tasks must be included. The specific task selection will be based on path optimization strategies and resource scheduling.

[0049] Combine and enumerate the generated N sets of expanded distribution paths. Since different path combinations may produce different distribution task orders and paths, enumerate the combinations of these expanded paths to produce multiple sets of expanded distribution paths. Each set of expanded paths contains some specific distribution paths, and each set of paths can represent a different distribution scheme. These sets of expanded distribution paths represent different distribution task arrangement methods. Through these enumeration combinations, the optimal distribution path scheme can be analyzed and selected.

[0050] Traverse all the extended distribution path sets, ensure that each extended distribution path set can cover each of the T meal delivery tasks, specifically, each path in the path set should include at least part of the delivery task, ensure that all T tasks are considered, through the whole process of checking, filter out O extended distribution path sets that can completely cover all delivery tasks, which means, exclude those path sets that cannot completely cover all delivery tasks, only keep the path sets that can completely meet the delivery tasks, get O extended distribution path sets.

[0051] For each extended distribution path set, calculate its total delivery time limit, the calculated time limit not only considers the length of the path and the transportation time limit, but also considers the time limit requirement of each delivery task, to ensure that the timeliness of the path meets the requirements. Each delivery task has a corresponding transportation time limit threshold, which indicates that the task should be completed within the specified time range, compare these time limit thresholds with the actual time limit of each path set, and judge whether it meets the task requirements. In the timeliness adaptation judgment process, filter out the path sets that meet the time limit requirements, and eliminate those path sets that cannot meet the timeliness requirements. Finally, the target distribution path set that meets the time limit requirements is obtained.

[0052] From the target distribution path set, extract N target distribution paths, these paths are the optimal distribution routes, which not only meet the timeliness requirements of the task, but also can cover all delivery tasks. Through the extraction of N target distribution paths, an initial task sequence corresponding to each path is generated, each task sequence represents a group of optimized delivery tasks, ensuring that the temperature control and timeliness requirements of each task are met. By extracting tasks from the target path set, the first group of initial task sequences is finally generated, which represents the final optimized delivery task arrangement, ready for the subsequent scheduling and execution stage.

[0053] Further, the local call logistics box volume feature is called, and the K initial task sequences are loaded conflict analyzed according to the logistics box volume feature and the plurality of meal characteristics information, and K loading conflict information is output. The method comprises:

[0054] According to the K initial task sequences, K meal volume model sequences are extracted from the plurality of meal characteristics information; a logistics box volume model is constructed according to the logistics box volume feature; and the K meal volume model sequences are dynamically superimposed on the logistics box volume model according to the task parallel relationship of the K initial task sequences, to locate K loading conflict node sequences, thereby constituting the K loading conflict information.

[0055] The meal characteristic information includes the temperature control requirements, volume, weight and other multi-dimensional characteristics of each meal. The volume information of the meal is represented by a three-dimensional volume model, which reflects the space occupation of the meal. K meal volume model sequences are extracted, and each volume model sequence represents the volume information of the meals of a group of tasks, facilitating subsequent loading optimization.

[0056] The logistics box volume features include the external dimensions of the box, the available internal space, different types of partition areas, carrying capacity, etc. Different box designs can affect the loading efficiency. Therefore, the volume of the logistics box needs to be modeled. The logistics box volume model reflects the three-dimensional spatial configuration of each logistics box, including the total volume, effective volume, number and size of partition areas, and whether it is suitable for transporting specific types of meals. According to these features, a logistics box volume model is constructed for subsequent loading calculation and conflict detection.

[0057] Each task sequence includes multiple tasks, which may need to be loaded in parallel in the same delivery box. The parallel relationship between these tasks is considered, i.e., which tasks can be loaded together in the same logistics box and which tasks need to be loaded separately. The parallel relationship of the tasks is related to the volume, weight, and whether there is a special temperature control requirement of the meals. Based on the logistics box volume model, the meal volume model of each delivery task is dynamically superimposed. According to the task parallel relationship, multiple meal volume models are sequentially superimposed into the effective volume of the logistics box. By superimposing the meal volume model, it is analyzed whether any meal occupies space that exceeds the effective volume of the logistics box during loading, or whether multiple meals overlap in the same area. Whenever such a situation occurs, it is marked as a loading conflict node. The loading conflict node represents the conflict area between the meal volume and the logistics box volume in the current task sequence. According to the result of dynamic superposition, all loading conflict nodes are identified and recorded to generate loading conflict information. Each information includes the specific location of the conflict node and the conflict reason (such as insufficient volume, meal overlap, etc.).

[0058] Further, according to the plurality of meal characteristic information, the plurality of meal delivery tasks are grouped according to temperature sensitive requirements to obtain P groups of meal delivery tasks, and the method comprises:

[0059] extract a second preservation temperature interval and a second temperature sensitivity weight of a second meal delivery task from the plurality of meal characteristic information; solve a first overlap interval length and a first merged interval length by overlapping the first preservation temperature interval and the second preservation temperature interval; calculate a first temperature sensitivity weight ratio according to the first temperature sensitivity weight and the second temperature sensitivity weight; calculate and output a first temperature sensitivity correlation degree based on the first overlap interval length, the first merged interval length, and the first temperature sensitivity weight ratio; and iteratively combine and enumerate the plurality of meal delivery tasks, and perform temperature sensitivity correlation analysis based on the plurality of meal characteristic information to output a plurality of groups of temperature sensitivity correlation degrees of the plurality of meal delivery tasks; and group the plurality of meal delivery tasks according to the plurality of groups of temperature sensitivity correlation degrees to obtain the P groups of meal delivery tasks.

[0060] extract a second preservation temperature interval and a second temperature sensitivity weight of a second meal delivery task from the plurality of meal characteristic information; solve a first overlap interval length and a first merged interval length by overlapping the first preservation temperature interval and the second preservation temperature interval; calculate a first temperature sensitivity weight ratio according to the first temperature sensitivity weight and the second temperature sensitivity weight; calculate and output a first temperature sensitivity correlation degree based on the first overlap interval length, the first merged interval length, and the first temperature sensitivity weight ratio; and iteratively combine and enumerate the plurality of meal delivery tasks, and perform temperature sensitivity correlation analysis based on the plurality of meal characteristic information to output a plurality of groups of temperature sensitivity correlation degrees of the plurality of meal delivery tasks; and group the plurality of meal delivery tasks according to the plurality of groups of temperature sensitivity correlation degrees to obtain the P groups of meal delivery tasks.

[0061] overlap the first preservation temperature interval and the second preservation temperature interval, and calculate a first overlap interval length and a first merged interval length, wherein the first overlap interval length represents an overlap of the two temperature intervals, i.e., an intersection of the two temperature intervals, for example, the temperature interval of the first meal may be 0-5℃, and the temperature interval of the second meal may be 3-8℃, in which case, they have an overlap interval of 3-5℃, and by calculating the intersection of the two temperature intervals, the temperature control range shared by the two meals during delivery can be determined; the first merged interval length represents the union of the two temperature intervals, i.e., the merging of the temperature control ranges of the two meals, which can help determine how large a temperature control environment is needed to accommodate both meals during delivery, for example, if the temperature control interval of the first meal is 0-5℃ and the temperature control interval of the second meal is 3-8℃, the merged interval is 0-8℃, and the length of the merged interval is 8℃.

[0062] The difference between the first temperature sensitivity weight and the second temperature sensitivity weight is calculated, and the absolute value of the difference is taken, which reflects the difference in temperature control requirements between the two dishes. For example, if the temperature sensitivity weight of the first dish is 0.8 and the temperature sensitivity weight of the second dish is 0.6, the absolute value of the weight difference is |0.8-0.6|=0.2. Then, the average of the first temperature sensitivity weight and the second temperature sensitivity weight is calculated, which represents the average temperature sensitivity level of the two dishes. For example, if the weight of the first dish is 0.8 and the weight of the second dish is 0.6, the average is (0.8+0.6) / 2=0.7. Finally, the ratio of the absolute value of the weight difference to the average weight is calculated to obtain the first temperature sensitivity weight ratio, which reflects the relative difference in temperature control sensitivity between the two dishes. A higher ratio indicates a greater difference in temperature control requirements between the two dishes, while a lower ratio indicates a smaller difference.

[0063] The first temperature sensitivity correlation degree is calculated and output according to the first overlap interval length, the first merging interval length, and the first temperature sensitivity weight ratio. The specific calculation process is detailed in subsequent steps. The temperature sensitivity correlation degree reflects the degree of association between the two dishes in terms of temperature control requirements. This indicator takes into account the overlap length of the temperature control interval, the length of the merging interval, and the difference in temperature sensitivity of the dishes, so it can evaluate their similarity in temperature control.

[0064] The multiple dish delivery tasks are combined and enumerated. This process arranges different dish delivery tasks in different combinations to form different task combinations. The dishes in each combination may have similar or different temperature control requirements. For each combination, the temperature sensitivity correlation degree is calculated based on the temperature control requirements of each pair of dishes (including temperature interval, temperature sensitivity weight, etc.). By analyzing the overlap and differences in temperature control of each group of dishes, the temperature sensitivity correlation degree is calculated for each task group. Finally, multiple sets of temperature sensitivity correlation degrees for multiple dish delivery tasks are output. Each correlation degree represents the similarity in temperature control requirements of the dishes in a specific task combination. These correlation degree values provide the basis for subsequent task grouping, ensuring that the dishes in each task group can be delivered in a reasonable temperature control environment.

[0065] Based on multiple groups of temperature sensitivity correlation degree, dishes with similar temperature control requirements are divided into the same group, and the dishes in each group will share similar temperature requirements and time limit requirements during delivery, thereby simplifying the delivery scheduling and optimizing the temperature control management. Specifically, first, dishes with high temperature sensitivity correlation degree are divided into the same group, which means that the temperature control requirements of these dishes are relatively close and suitable for common delivery in the same delivery task. For dishes with low temperature sensitivity correlation degree, they are divided into different groups to ensure that the dishes in each group can meet the specific temperature control requirements. Through temperature sensitivity correlation analysis, all dish delivery tasks are finally divided into P groups of tasks, and the dishes in each group have similar temperature control requirements and time limit requirements, ensuring that the delivery of each group of tasks can be carried out under the most suitable temperature control conditions, avoiding the decline of delivery quality due to inconsistent temperature control.

[0066] Further, based on the first overlap interval length, the first merging interval length, and the first temperature sensitivity weight ratio, a first temperature sensitivity correlation degree is calculated, and the method comprises:

[0067] The first overlap interval length, the first merging interval length, and the first temperature sensitivity weight ratio are substituted into the temperature interval similarity formula to calculate and output the first temperature similarity. The first temperature sensitivity weight and the second temperature sensitivity weight are subjected to cosine similarity calculation to output the first temperature sensitivity. The first temperature similarity and the first temperature sensitivity are added based on the preset weight configuration to output the first temperature sensitivity correlation degree.

[0068] The first overlap interval length, the first merging interval length, and the first temperature sensitivity weight ratio are substituted into the temperature interval similarity formula to calculate the first temperature similarity. The temperature interval similarity formula is as follows: temperature similarity=(overlap interval length / merging interval length)*temperature sensitivity weight. The longer the overlap interval, the shorter the merging interval, and the greater the temperature sensitivity weight, indicating that the similarity of the two dishes in temperature control is higher. The calculated first temperature similarity is used to measure the similarity of the two dishes in temperature requirements.

[0069] Cosine similarity calculation is performed on the first temperature sensitivity weight and the second temperature sensitivity weight. Cosine similarity is used to measure the similarity of two vectors. For temperature sensitivity weight, the cosine similarity formula is as follows: wherein, S W (i,j) represents temperature sensitivity similarity, W i represents the i-th temperature sensitivity weight, W j represents the j-th temperature sensitivity weight. The result of cosine similarity is a value between-1 and 1, representing the similarity between the temperature sensitivity weights of the two dishes. The closer the value is to 1, the more similar their temperature sensitivity is. The closer the value is to 0, the greater the difference in temperature sensitivity. Through cosine similarity calculation, the similarity of the temperature sensitivity of the two dishes to a certain extent can be determined.

[0070] To make temperature similarity and temperature sensitivity similarity play different roles in the calculation of temperature sensitivity correlation, the two are weighted and summed according to a preset weight configuration. Generally, the weight configuration can be adjusted based on the actual delivery task requirements. For example, if the delivery task requires higher accuracy of temperature control, a higher weight is given to the first temperature sensitivity similarity. Through weighted summation, the first temperature sensitivity correlation is obtained, which measures the overall correlation between two dishes in terms of temperature control requirements, including their temperature control similarity and temperature sensitivity similarity.

[0071] Further, the plurality of dish delivery tasks are grouped according to the plurality of temperature sensitivity correlations, and P groups of dish delivery tasks are obtained. The method comprises:

[0072] The plurality of dish delivery tasks are taken as a plurality of topological nodes, and the topological link distance is quantified based on the plurality of temperature sensitivity correlations to construct a temperature sensitivity correlation topology. A temperature sensitivity correlation threshold is preset. The temperature sensitivity correlation threshold is used to traverse the temperature sensitivity correlation topology to make a topological link elimination judgment, and an updated correlation topology is obtained, wherein the updated correlation topology comprises P isolated topologies. The dish delivery tasks of the P isolated topologies are extracted to obtain the P groups of dish delivery tasks.

[0073] The plurality of dish delivery tasks are taken as a plurality of topological nodes, which represent dish tasks that need to be delivered. By calculating the temperature sensitivity correlation (such as the temperature sensitivity correlation calculated in the previous step) of each pair of dish delivery tasks, the link distance between each pair of dishes can be quantified. Specifically, the link distance between dishes with high temperature sensitivity correlation (i.e., dishes with similar temperature intervals and temperature sensitivities) is short, while the link distance between dishes with low temperature sensitivity correlation (i.e., dishes with large differences in temperature control and temperature sensitivity) is long.

[0074] According to the temperature sensitivity correlation between dish delivery tasks, these tasks are organized into a temperature sensitivity correlation topology structure. In the topology structure, each dish task is a node, and the link between nodes represents the correlation strength (i.e., the weight of the link) between them in terms of temperature control and temperature sensitivity. A shorter topological link distance indicates that the temperature control requirements of the tasks are more similar, while a longer link indicates that the temperature control difference is larger.

[0075] According to the actual delivery requirements, a temperature sensitivity correlation threshold is preset, which is used to judge the correlation between two dish delivery tasks in terms of temperature control and temperature sensitivity in the subsequent steps. If the temperature sensitivity correlation of the two tasks is higher than the threshold, they can be considered as similar tasks and can be grouped into the same group. Conversely, if the temperature sensitivity correlation of the two tasks is lower than the threshold, it means that the two tasks have large differences in temperature control requirements and should be grouped into different groups.

[0076] According to the preset temperature-sensitive correlation threshold, all nodes in the temperature-sensitive correlation topology are traversed, and the connection between each pair of nodes, i.e., the temperature-sensitive correlation degree, is compared with the temperature-sensitive correlation threshold respectively. If the temperature-sensitive correlation degree between two tasks is lower than the threshold, the connection between the two tasks is removed, i.e., they no longer belong to the similar group. In this way, the originally connected nodes will no longer be connected, forming multiple independent topology branches. After the removal judgment, a new updated correlation topology is obtained. This structure contains P isolated topologies, and each isolated topology represents a group of meal delivery tasks with similar temperature-sensitive requirements, which have high similarity in temperature control and temperature sensitivity requirements.

[0077] From the P isolated topologies, tasks are extracted, and each isolated topology is regarded as an independent delivery task group. Finally, P groups of meal delivery tasks are obtained, each group containing meal tasks with similar temperature control requirements.

[0078] In summary, the logistics work order management method of big data adaptive analysis provided by the embodiments has the following technical effects:

[0079] Through multi-modal data collection, meal characteristics information and logistics demand information can be collected from multiple sources. After big data processing, comprehensive analysis and accurate grouping of complex delivery tasks can be realized. Multi-modal data collection enables the system to process data from different sources and effectively integrate and apply them. Based on the temperature control characteristics of meals, the big data analysis is used to group multiple delivery tasks according to temperature-sensitive requirements, so that meals with similar temperature control requirements can be reasonably allocated to the same group. This grouping method makes the delivery path planning and resource allocation more targeted, reducing unnecessary resource waste. According to the results of temperature-sensitive demand grouping, the spatio-temporal path merging is performed in combination with multiple logistics demand information. This process optimizes the delivery route and combines temperature control and timeliness requirements to generate an initial task sequence, providing effective path planning for subsequent task scheduling. Through big data processing technology, the matching of meals and logistics boxes is analyzed, and potential loading conflicts are identified. This analysis result provides data support for subsequent cross-box collaborative analysis, further optimizing the task sequence and resource allocation, and improving the utilization of logistics resources. Based on the optimization results of the target task sequence, the logistics work order is intelligently constructed, and the delivery is performed in combination with the scheduling requirements of temperature-sensitive logistics boxes. Big data processing makes the generation of logistics work orders more efficient, and can dynamically adjust the scheduling scheme according to the characteristics of meals and delivery requirements, thereby improving the execution efficiency of delivery tasks.

[0080] Embodiment two, based on the same inventive concept as the logistics work order management method of big data adaptive analysis in the preceding embodiments, as shown in Figure 2 The system provided by the embodiments of the present application includes:

[0081] a data collection module 10, configured to obtain a plurality of meal characteristic information and a plurality of logistics demand information of a plurality of meal delivery tasks by performing multi-modal data collection at a meal task center.

[0082] a demand grouping module 20, configured to perform temperature-sensitive demand grouping on the plurality of meal delivery tasks according to the plurality of meal characteristic information, to obtain P groups of meal delivery tasks.

[0083] a space-time path merging module 30, configured to perform space-time path merging according to the plurality of logistics demand information, with the P groups of meal delivery tasks as constraints, to output K initial task sequences.

[0084] a loading conflict analysis module 40, configured to locally call logistics box volume features, and perform loading conflict analysis on the K initial task sequences according to the logistics box volume features and the plurality of meal characteristic information, to output K loading conflict information.

[0085] an initial task updating module 50, configured to perform cross-box collaborative analysis according to the K loading conflict information, and update the K initial task sequences according to an analysis result, to obtain W target task sequences, where W is a positive integer greater than K.

[0086] a delivery module 60, configured to construct logistics work orders based on the W target task sequences, to schedule temperature-sensitive logistics box delivery of the plurality of meal delivery tasks.

[0087] Further, the data collection module 10 is configured to perform the following operation steps:

[0088] At the meal task center, multi-dimensional temperature-sensitive parameter mapping is performed according to a task type of a first meal delivery task, to obtain a first preservation temperature interval, a first temperature sensitivity weight, a first meal volume model, and a first time tolerance, where the first preservation temperature interval, the first temperature sensitivity weight, and the first meal volume model constitute first meal characteristic information; a first task order of the first meal delivery task is parsed to obtain a first baseline transportation time limit and first start-end point coordinates; a first transportation time limit threshold is calculated according to the first time tolerance and the first baseline transportation time limit, where the first transportation time limit threshold and the first start-end point coordinates constitute first logistics demand information.

[0089] Further, the space-time path merging module 30 is configured to perform the following operation steps:

[0090] extracting a first set of logistics demand information corresponding to a first set of meal delivery tasks from the plurality of meal delivery tasks, wherein the first set of meal delivery tasks comprises T meal delivery tasks; presetting a high-sensitivity task feature, traversing a first set of meal characteristics information of the first set of meal delivery tasks using the high-sensitivity task feature, and locating N seed delivery tasks, wherein the high-sensitivity task feature comprises a temperature interval scale and a temperature sensitivity weight scale; decomposing the first logistics demand information to obtain N logistics demand information of the N seed delivery tasks and T-N logistics demand information of T-N meal delivery tasks; extracting N start and end point coordinates from the N logistics demand information to construct N reference delivery paths; taking T transportation time limit thresholds as constraints, performing path filling fitting on the T-N logistics demand information in the N reference delivery paths to obtain a first set of initial task sequences; and iteratively obtaining P sets of initial task sequences, removing group division of the P sets of initial task sequences, and obtaining the K initial task sequences.

[0091] Further, the space-time path merging module 30 is configured to perform the following operation steps:

[0092] extracting T-N start and end point coordinates from the T-N logistics demand information to perform feasible path fitting, and outputting T-N sets of accompanying delivery paths; taking path overlap expansion as a constraint, merging the T-N sets of accompanying delivery paths into the N reference delivery paths, and outputting N sets of expanded delivery paths; combining and enumerating the N sets of expanded delivery paths to obtain a plurality of expanded delivery path group sets; performing delivery task complete search on the plurality of expanded delivery path group sets based on the T meal delivery tasks to obtain O expanded delivery path group sets; performing delivery time limit calculation on the O expanded delivery path group sets, and performing time limit adaptability judgment using the T transportation time limit thresholds to obtain a target delivery path group set; extracting N initial task sequences from N target delivery paths in the target delivery path group set to form the first set of initial task sequences.

[0093] Further, the loading conflict analysis module 40 is configured to perform the following operation steps:

[0094] According to the K initial task sequences, extracting K meal volume model sequences from the plurality of meal characteristics information; constructing a logistics box volume model according to the logistics box volume feature; and dynamically superimposing the K meal volume model sequences on the logistics box volume model according to the task parallel relationship of the K initial task sequences to locate K loading conflict node sequences, thereby forming the K loading conflict information.

[0095] Further, the demand grouping module 20 is configured to perform the following operation steps:

[0096] extract a second preservation temperature interval and a second temperature sensitivity weight of a second meal delivery task from the plurality of meal characteristic information; solve a first overlap interval length and a first merged interval length by overlapping the first preservation temperature interval and the second preservation temperature interval; calculate a first temperature sensitivity weight ratio according to the first temperature sensitivity weight and the second temperature sensitivity weight; calculate and output a first temperature sensitivity correlation degree based on the first overlap interval length, the first merged interval length, and the first temperature sensitivity weight ratio; and iteratively combine and enumerate the plurality of meal delivery tasks, and perform temperature sensitivity correlation analysis based on the plurality of meal characteristic information to output a plurality of groups of temperature sensitivity correlation degrees of the plurality of meal delivery tasks; and group the plurality of meal delivery tasks according to the plurality of groups of temperature sensitivity correlation degrees to obtain the P groups of meal delivery tasks.

[0097] Further, the demand grouping module 20 is configured to perform the following operation steps:

[0098] substitute the first overlap interval length, the first merged interval length, and the first temperature sensitivity weight ratio into a temperature interval similarity formula to calculate and output a first temperature similarity; perform cosine similarity calculation on the first temperature sensitivity weight and the second temperature sensitivity weight to output a first temperature sensitivity similarity; and add the first temperature similarity and the first temperature sensitivity similarity based on a preset weight configuration to output the first temperature sensitivity correlation degree.

[0099] Further, the demand grouping module 20 is configured to perform the following operation steps:

[0100] construct a temperature sensitivity correlation topology based on the plurality of groups of temperature sensitivity correlation degrees by taking the plurality of meal delivery tasks as a plurality of topology nodes and quantifying topology link distances; preset a temperature sensitivity correlation threshold; perform topology link elimination judgment on the temperature sensitivity correlation topology by using the temperature sensitivity correlation threshold to obtain an updated correlation topology, wherein the updated correlation topology includes P isolated topologies; and extract meal delivery tasks of the P isolated topologies to obtain the P groups of meal delivery tasks.

[0101] Through the foregoing detailed description of the method for managing logistics work orders through big data adaptive analysis, those skilled in the art can clearly understand the system for managing logistics work orders through big data adaptive analysis in the embodiments. Since the system corresponds to the method disclosed in the embodiments, the system is described simply, and the relevant parts are described in the method part.

[0102] In embodiment three, a storage medium is provided, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of any one of the embodiments are implemented.

[0103] Any combination of the technical features of the above embodiments can be made, and for the sake of brevity, not all possible combinations are described, however, it is to be understood that the scope of protection includes all possible combinations of the technical features described herein.

[0104] The above description of disclosed embodiments allows a person skilled in the art to implement or use the application. Numerous modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the application is not to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A logistics work order management method for big data adaptive analysis, characterized by, The method comprises: By executing multi-modal data acquisition in the meal task center, obtain multiple meal characteristics information and multiple logistics demand information of multiple meal delivery tasks; According to the multiple meal characteristics information, group the multiple meal delivery tasks according to temperature-sensitive demand, and obtain P groups of meal delivery tasks; With the P groups of meal delivery tasks as constraints, combine the space-time paths according to the multiple logistics demand information, and output K initial task sequences; Locally call the logistics box volume characteristics, and analyze the K initial task sequences according to the logistics box volume characteristics and the multiple meal characteristics information, and output K loading conflict information; According to the K loading conflict information, perform cross-box collaborative analysis, and update the K initial task sequences according to the analysis result, and obtain W target task sequences, wherein W is a positive integer greater than K; Based on the W target task sequences, construct a logistics work order to dispatch temperature-sensitive logistics boxes to deliver the multiple meal delivery tasks; By executing multi-modal data acquisition in the meal task center, obtain multiple meal characteristics information and multiple logistics demand information of multiple meal delivery tasks, the method comprises: In the meal task center, according to the task type of the first meal delivery task, perform multi-dimensional temperature-sensitive parameter mapping to obtain a first preservation temperature interval, a first temperature sensitivity weight, a first meal volume model and a first time tolerance, wherein the first preservation temperature interval, the first temperature sensitivity weight and the first meal volume model constitute the first meal characteristics information; Parse the first task order of the first meal delivery task to obtain a first baseline transportation time limit and first start-end point coordinates; According to the first time tolerance and the first baseline transportation time limit, calculate a first transportation time limit threshold, wherein the first transportation time limit threshold and the first start-end point coordinates constitute the first logistics demand information; According to the multiple meal characteristics information, group the multiple meal delivery tasks according to temperature-sensitive demand, and obtain P groups of meal delivery tasks, the method comprises: Extract the second preservation temperature interval and the second temperature sensitivity weight of the second meal delivery task from the multiple meal characteristics information; By overlapping the first preservation temperature interval and the second preservation temperature interval, solve and output a first overlap interval length and a first combined interval length; According to the first temperature sensitivity weight and the second temperature sensitivity weight, calculate a first temperature sensitivity weight ratio; Based on the first overlap interval length, the first combined interval length and the first temperature sensitivity weight ratio, calculate and output a first temperature-sensitive correlation degree; By analogy, after combining and enumerating the multiple meal delivery tasks, perform temperature-sensitive correlation analysis based on the multiple meal characteristics information, and output multiple groups of temperature-sensitive correlation degrees of the multiple meal delivery tasks; According to the multiple groups of temperature-sensitive correlation degrees, group the multiple meal delivery tasks according to temperature-sensitive demand, and obtain the P groups of meal delivery tasks; Based on the first overlap interval length, the first combined interval length and the first temperature sensitivity weight ratio, calculate and output a first temperature-sensitive correlation degree, the method comprises: The first overlap interval length, the first merge interval length, and the first temperature sensitivity weight are substituted into the temperature interval similarity formula to calculate and output a first temperature similarity; The first temperature sensitivity weight and the second temperature sensitivity weight are subjected to cosine similarity calculation to output a first temperature sensitivity similarity; The first temperature similarity and the first temperature sensitivity similarity are added based on a preset weight configuration to output the first temperature sensitivity correlation degree; The multiple sets of temperature sensitivity correlation degrees are used to group the multiple meal delivery tasks according to temperature sensitivity requirements to obtain the P sets of meal delivery tasks, and the method comprises: The multiple meal delivery tasks are taken as multiple topological nodes, the topological connection distance is quantified based on the multiple sets of temperature sensitivity correlation degrees, and a temperature sensitivity correlation topology is constructed; A preset temperature sensitivity correlation threshold is set; The temperature sensitivity correlation threshold is used to traverse the temperature sensitivity correlation topology to perform topological connection elimination judgment, and an updated correlation topology is obtained, wherein the updated correlation topology comprises P isolated topologies; Meal delivery tasks of the P isolated topologies are extracted to obtain the P sets of meal delivery tasks.

2. The logistics work order management method for big data adaptive analysis as claimed in claim 1 wherein, The P sets of meal delivery tasks are taken as constraints, and the spatiotemporal path combination is performed according to the multiple logistics demand information to output K initial task sequences, and the method comprises: First group logistics demand information corresponding to the first group of meal delivery tasks is extracted from the multiple logistics demand information, wherein the first group of meal delivery tasks comprises T meal delivery tasks; A high sensitivity task feature is preset, the first group of meal characteristics information of the first group of meal delivery tasks is traversed using the high sensitivity task feature, and N seed delivery tasks are located, wherein the high sensitivity task feature comprises a temperature interval scale and a temperature sensitivity weight scale; The first logistics demand information is decomposed to obtain N logistics demand information of the N seed delivery tasks and T-N logistics demand information of the remaining T-N meal delivery tasks; N origin-destination point coordinates are extracted from the N logistics demand information to construct N reference delivery paths; T transportation time limit thresholds are taken as constraints, and the T-N logistics demand information is subjected to path filling fitting on the N reference delivery paths to obtain a first group of initial task sequences; By analogy, after obtaining the P groups of initial task sequences, the group division of the P groups of initial task sequences is removed to obtain the K initial task sequences.

3. The logistics work order management method for big data adaptive analysis as claimed in claim 2, wherein, T transportation time limit thresholds are taken as constraints, and the T-N logistics demand information is subjected to path filling fitting on the N reference delivery paths to obtain a first group of initial task sequences, and the method comprises: T-N origin-destination point coordinates are extracted from the T-N logistics demand information to perform feasible path fitting, and T-N groups of accompanying delivery paths are outputted; The T-N groups of accompanying delivery paths are merged into the N reference delivery paths as constraints of path overlap expansion to output N groups of expanded delivery paths; The N groups of expanded delivery paths are combined and enumerated to obtain multiple expanded delivery path group sets; Based on the T meal delivery tasks, the multiple expanded delivery path group sets are subjected to delivery task complete checking to obtain O expanded delivery path group sets. The O extended distribution path sets are subjected to distribution time limit calculation, and the T transportation time limit thresholds are used for time limit adaptability judgment to obtain a target distribution path set through screening; N target distribution paths in the target distribution path set are subjected to task extraction to obtain N initial task sequences, which constitute the first group of initial task sequences.

4. The logistics work order management method for big data adaptive analysis as claimed in claim 1 wherein, The local logistics box volume feature is called, and the K initial task sequences are subjected to loading conflict analysis according to the logistics box volume feature and the plurality of meal characteristic information, and K loading conflict information is outputted, and the method comprises: K meal volume model sequences are extracted from the plurality of meal characteristic information according to the K initial task sequences; A logistics box volume model is constructed according to the logistics box volume feature; K loading conflict node sequences are positioned by dynamically superimposing the K meal volume model sequences on the logistics box volume model according to the task parallel relationship of the K initial task sequences, and the K loading conflict information is constituted.

5. Logistics work order management system for big data adaptive analysis, characterized by, The logistics work order management method for implementing the big data adaptive analysis of any one of claims 1-4, the system comprises: A data acquisition module is configured to acquire a plurality of meal characteristic information and a plurality of logistics demand information of a plurality of meal delivery tasks by performing multi-modal data acquisition in a meal task center; A demand grouping module is configured to group temperature-sensitive demands according to the plurality of meal characteristic information to obtain P groups of meal delivery tasks; A space-time path merging module is configured to merge space-time paths according to the plurality of logistics demand information with the P groups of meal delivery tasks as constraints to output K initial task sequences; A loading conflict analysis module is configured to locally call a logistics box volume feature and perform loading conflict analysis on the K initial task sequences according to the logistics box volume feature and the plurality of meal characteristic information to output K loading conflict information; An initial task updating module is configured to perform cross-box collaborative analysis according to the K loading conflict information and update the K initial task sequences according to the analysis result to obtain W target task sequences, wherein W is a positive integer greater than K; A distribution module is configured to construct a logistics work order based on the W target task sequences to schedule temperature-sensitive logistics box delivery of the plurality of meal delivery tasks.

6. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to realize the steps of the logistics work order management method for big data adaptive analysis of any one of claims 1 to 4.

Images