Logistics aging prediction method, device and equipment

Abstract

The invention discloses a logistics timeliness prediction method, device and equipment, and the method is applied to the technical field of logistics, and the method comprises the steps: collecting the multi-dimensional data flow of logistics vehicles and express parcels in a logistics network through an intelligent sensing equipment cluster; pre-processing the multi-dimensional data flow, and constructing a parcel full-link file of the logistics network; according to the parcel full-link file, obtaining a periodic decision parameter of the logistics vehicle; obtaining external environment data and internal logistics data of the logistics network, and obtaining comprehensive logistics data of the logistics network; according to the comprehensive logistics data of the logistics network, predicting a transport capacity demand prediction result of the logistics network in a future preset time period; determining the delay probability of the line in the logistics network according to the transport capacity demand prediction result of the logistics network in the future preset time period and the periodic decision parameter; the delay probability represents the logistics timeliness of the logistics network. According to the method, the logistics timeliness of the line in the logistics network can be quickly and accurately predicted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a logistics time limit prediction method, device and equipment. BACKGROUND

[0002] The current logistics industry has the following problems in the distribution link: delay rate statistics lag and batch loading decision rigidity. The traditional method relies on manual rule configuration and timed batch calculation, resulting in passive time limit management and low resource utilization. SUMMARY

[0003] The present application provides a logistics time limit prediction method, device and equipment, which can quickly and accurately predict the logistics time limit of the line in the logistics network, thereby facilitating time limit management.

[0004] In one aspect, the present application provides a logistics time limit prediction method, which comprises: Collecting multi-dimensional data streams of logistics vehicles and express packages in the logistics network through an intelligent sensing device cluster; and preprocessing the multi-dimensional data streams to construct a package full-link archive of the logistics network; According to the package full-link archive, periodically updating the batch loading weight threshold, batch loading volume threshold, path planning priority coefficient and early warning trigger critical value of the logistics vehicle to obtain the periodic decision parameters of the logistics vehicle; Obtaining external environment data and internal logistics data of the logistics network to obtain comprehensive logistics data of the logistics network; According to the comprehensive logistics data of the logistics network, predicting the number of loading and unloading workers, the number of vehicles and the temporary storage area required by the logistics network in a future preset period to obtain the transport capacity demand prediction result of the logistics network in the future preset period; According to the transport capacity demand prediction result of the logistics network in the future preset period and the periodic decision parameters, determining the delay probability of the line in the logistics network; the delay probability represents the logistics time limit of the logistics network.

[0005] In some embodiments, the obtaining of the external environment data and the internal logistics data of the logistics network to obtain the comprehensive logistics data of the logistics network comprises: Obtaining weather information, running time corresponding holidays and e-commerce platform promotion plans of the running area of the logistics vehicle in the logistics network in a future preset period as external environment data of the logistics network; Obtaining historical distribution peak data, average loading and unloading efficiency of each line, personnel scheduling table of the logistics network as internal logistics data of the logistics network; The external environment data and the internal logistics data corresponding to the logistics network point are taken as comprehensive logistics data of the logistics network point.

[0006] In some embodiments, before the determining the delay probability of the line in the logistics network point, the method further comprises: According to the periodic decision parameters of the logistics vehicle, a plurality of preset risk level respectively corresponding to the preset warning parameter range is constructed, and a level parameter relationship library is obtained; The corresponding relationship between the plurality of preset risk levels and the plurality of preset warning strategies is determined, and the corresponding relationship is stored in the preset level strategy relationship library; each preset risk level corresponds to a preset warning strategy; After the determining the delay probability of the line in the logistics network point, the method further comprises: According to the level parameter relationship library and the line delay probability in the logistics network point, the target risk level of the line is determined; According to the preset level strategy relationship library, the target warning strategy corresponding to the target risk level is determined.

[0007] In some embodiments, the determining the corresponding relationship between the plurality of preset risk levels and the plurality of preset warning strategies comprises: For the express package of the highest risk level in the plurality of preset risk levels, it is judged whether the express package is an abnormal package; If the express package is not an abnormal package, the first distribution level of the express package and the first warning strategy of the dynamic adjustment of the handover single are constructed; If the express package is an abnormal package, the express package is automatically intercepted and distributed; According to the low risk level in the plurality of preset risk levels, the second warning strategy corresponding to the second distribution level of the express package is constructed; the priority of the first distribution level is higher than that of the second distribution level.

[0008] In some embodiments, the constructing the first distribution level of the express package and the first warning strategy of the dynamic adjustment of the handover single comprises: A target express package with a delay probability greater than a target probability threshold is obtained, and the priority of the target express package in the distribution queue is raised to the highest level to obtain a first distribution level; The conveyor belt and the platform resource used for ordinary express packages are taken as the distribution resource of the target express package, and a resource preemption strategy is constructed; When it is detected that the main single of the logistics network point is distributed across a plurality of carriage areas, the main single is automatically split into a plurality of handover singles and associated with a parent waybill number, and a dynamically adjusted handover single is constructed; According to the first allocation level, the resource preemption strategy and the dynamic adjustment handover sheet, the first early warning strategy is constructed.

[0009] In some embodiments, the logistics network points are multiple, and after the logistics network point's capacity demand prediction result in the future preset period is obtained, the method further comprises: According to the capacity demand prediction result of each logistics network point, a visual heat map is constructed; The cumulative demand duration of each capacity resource in the capacity demand prediction result is obtained; The period with a cumulative demand duration greater than a preset duration threshold is determined as a target period, and the target period is marked in the heat map.

[0010] In some embodiments, the multi-dimensional data stream is preprocessed to construct a package full-link archive of the logistics network point, comprising: The multi-dimensional data stream is subjected to abnormal data filtering processing to eliminate null values generated by sensor disconnection and abnormal values exceeding physical limits to obtain filtered data; The respective scanning time stamps of the filtered data are uniformly calibrated to a central clock to obtain spatio-temporal alignment data; The RFID data, weighbridge data and vehicle trajectory data in the spatio-temporal alignment data are associated and fused through waybill numbers to construct a package full-link archive of the logistics network point.

[0011] Another aspect provides a logistics time efficiency prediction device, comprising: A multi-dimensional data acquisition module is configured to acquire multi-dimensional data streams of logistics vehicles and express packages in a logistics network point through an intelligent sensing device cluster, and preprocess the multi-dimensional data streams to construct a package full-link archive of the logistics network point; A decision parameter determination module is configured to periodically update batch loading weight threshold, batch loading volume threshold, path planning priority coefficient and early warning trigger critical value of the logistics vehicle according to the package full-link archive to obtain periodic decision parameters of the logistics vehicle; A comprehensive logistics data acquisition module is configured to acquire external environment data and internal logistics data of the logistics network point to obtain comprehensive logistics data of the logistics network point; A capacity prediction module is configured to predict the number of loading and unloading workers, the number of vehicles and the temporary storage area required by the logistics network point in a future preset period according to the comprehensive logistics data of the logistics network point to obtain a capacity demand prediction result of the logistics network point in the future preset period; a delay probability determination module configured to determine a delay probability of a line in the logistics network point according to the predicted result of the transport capacity demand of the logistics network point in the future preset period and the periodic decision parameter, the delay probability representing a logistics timeliness of the logistics network point.

[0012] In some embodiments, the comprehensive logistics data acquisition module comprises: an environmental data acquisition unit configured to acquire weather information of a running area of a logistics vehicle in the logistics network point, a holiday corresponding to a running time, and a promotion plan of an e-commerce platform in a future preset period as external environmental data of the logistics network point; a logistics data acquisition unit configured to acquire historical distribution peak data, average loading and unloading efficiency of each line, and a personnel scheduling table of the logistics network point as internal logistics data of the logistics network point; a comprehensive data determination unit configured to determine the external environmental data and the internal logistics data corresponding to the logistics network point as comprehensive logistics data of the logistics network point.

[0013] In some embodiments, the device further comprises: a grade parameter relationship library construction module configured to construct a preset warning parameter range corresponding to each of a plurality of preset risk grades according to the periodic decision parameter of the logistics vehicle, and obtain a grade parameter relationship library; a strategy relationship library construction module configured to determine a corresponding relationship between a plurality of preset risk grades and a plurality of preset warning strategies, and store the corresponding relationship in a preset grade strategy relationship library; each preset risk grade corresponds to a preset warning strategy; a target risk grade determination module configured to determine a target risk grade of the line according to the grade parameter relationship library and the delay probability of the line in the logistics network point; a target strategy determination module configured to determine a target warning strategy corresponding to the target risk grade according to the preset grade strategy relationship library.

[0014] In some embodiments, the strategy relationship library construction module comprises: a judgment unit configured to judge whether a courier package of a highest risk grade in the plurality of preset risk grades is an abnormal package; a first strategy construction unit configured to construct a first distribution grade of the courier package and a first warning strategy of a handover sheet if the courier package is not an abnormal package; an interception unit configured to automatically intercept and divert the courier package if the courier package is an abnormal package; The second strategy construction unit is configured to construct a second early warning strategy corresponding to a second distribution level of the express package according to a low risk level in a plurality of preset risk levels; and the first distribution level has a higher priority than the second distribution level.

[0015] In some embodiments, the first strategy construction unit comprises: The first distribution level determination subunit is configured to obtain a target express package whose delay probability is greater than a target probability threshold, and to raise the priority of the target express package in a distribution queue to the highest level to obtain a first distribution level. The resource preemption strategy construction subunit is configured to obtain a conveyor belt and a platform resource used for ordinary express packages as distribution resources of the target express package, and to construct a resource preemption strategy. The transfer sheet construction subunit is configured to, when detecting that the main sheet of the logistics site is distributed across a plurality of carriage areas, automatically split into a plurality of transfer sheets and associate a parent waybill number, and to construct a dynamically adjusted transfer sheet. The first strategy construction subunit is configured to construct the first early warning strategy according to the first distribution level, the resource preemption strategy, and the dynamically adjusted transfer sheet.

[0016] In some embodiments, the logistics sites are a plurality of logistics sites, and the device further comprises: The heat map construction module is configured to construct a visual heat map according to the transport capacity demand prediction results of each logistics site. The cumulative demand duration acquisition module is configured to obtain a cumulative demand duration of each transport capacity resource in the transport capacity demand prediction results. The time period labeling module is configured to determine a time period in which the cumulative demand duration is greater than a preset duration threshold as a target time period, and to label the target time period in the heat map.

[0017] In some embodiments, the multi-dimensional data acquisition module comprises: The filtering unit is configured to perform abnormal data filtering processing on the multi-dimensional data stream, and to eliminate null values generated by sensor disconnection and abnormal values exceeding physical limits to obtain filtered data. The alignment unit is configured to uniformly calibrate respective scanning time stamps of the filtered data to a central clock to obtain spatio-temporal alignment data. The fusion unit is configured to associate and fuse RFID data, weighbridge data, and vehicle trajectory data in the spatio-temporal alignment data through a waybill number to construct a package full-link archive of the logistics site.

[0018] The other aspect provides an electronic device, the device comprising a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the logistics time limit prediction method as described above.

[0019] The other aspect provides a computer storage medium, the computer storage medium storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by a processor to implement the logistics time limit prediction method as described above.

[0020] The other aspect provides a computer program product or a computer program, the computer program product or the computer program comprising computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to perform to implement the logistics time limit prediction method as described above.

[0021] The logistics time limit prediction method, device and equipment provided by the application have the following technical effects: The application collects multi-dimensional data streams of logistics vehicles and express packages in a logistics network point through an intelligent sensing device cluster; and pre-processes the multi-dimensional data streams to construct a package full-link archive of the logistics network point; periodically updates batch loading weight thresholds, batch loading volume thresholds, path planning priority coefficients and early warning trigger critical values of the logistics vehicles according to the package full-link archive to obtain periodic decision parameters of the logistics vehicles; thereby realizing dynamic adjustment of the decision parameters; obtains external environment data and internal logistics data of the logistics network point to obtain comprehensive logistics data of the logistics network point; predicts the number of loading and unloading workers, the number of vehicles and the temporary storage area required by the logistics network point in a future preset time period according to the comprehensive logistics data of the logistics network point to obtain an operation capacity demand prediction result of the logistics network point in the future preset time period; thereby accurately predicting the operation capacity demand in the future time period; and finally determines a delay probability of a line in the logistics network point according to the operation capacity demand prediction result of the logistics network point in the future preset time period and the periodic decision parameters; the delay probability represents the logistics time limit of the logistics network point; thereby the logistics time limit of the line in the logistics network point can be quickly and accurately predicted. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present specification or the prior art and the advantages thereof, the drawings required to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present specification, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0023] Figure 1 is a schematic diagram of a logistics timeliness prediction system provided by an embodiment of the present specification; Figure 2 is a flowchart of a logistics timeliness prediction method provided by an embodiment of the present specification; Figure 3 is a flowchart of a method for preprocessing the multidimensional data stream and constructing a package full-link archive of the logistics network point provided by an embodiment of the present specification; Figure 4 is a flowchart of a method for obtaining external environment data and internal logistics data of the logistics network point to obtain comprehensive logistics data of the logistics network point provided by an embodiment of the present specification; Figure 5 is a flowchart of a method for determining the correspondence between a plurality of preset risk levels and a plurality of preset early warning strategies provided by an embodiment of the present specification; Figure 6 is a structural schematic diagram of a logistics timeliness prediction device provided by an embodiment of the present specification; Figure 7 is a structural schematic diagram of a server provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present specification will be described clearly and completely in combination with the drawings in the embodiments of the present specification. Obviously, the described embodiments are only some of the embodiments of the present specification, rather than all the embodiments. Based on the embodiments in the present specification, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present specification.

[0025] It should be noted that the terms "first", "second", and the like in the description and claims of the application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] Referring to Figure 1 , Figure 1 is a schematic diagram of a logistics time limit prediction system provided by an embodiment of the present specification, as Figure 1 shown, the logistics time limit prediction system can at least include a server 01 and a client 02.

[0027] Specifically, in the embodiments of the present specification, the server 01 can include a standalone server, or a distributed server, or a server cluster composed of multiple servers, and can also be a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms. The server 01 can include a network communication unit, a processor, a memory and the like. Specifically, the server 01 can be used to build a package full-link archive of the logistics point and determine the delay probability of the line in the logistics point.

[0028] Specifically, in the embodiments of the present specification, the client 02 can include entity devices such as smart phones, desktop computers, tablet computers, notebook computers, digital assistants, smart wearable devices, smart speakers, vehicle terminals, smart televisions, and the like. It can also include software running in entity devices, such as web pages provided by some service providers to users, and can also be applications provided by these service providers to users. Specifically, the client 02 can be used to query the delay probability of the line in the logistics point at future time online.

[0029] A logistics time limit prediction method is introduced below, Figure 2is a flowchart of a logistics time limit prediction method provided by an embodiment of the present specification. The present specification provides method operation steps as described in the embodiments or flowcharts, but more or fewer operation steps can be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is only one of the many execution orders, and does not represent the only execution order. In actual system or server product execution, the method order shown in the embodiments or the drawings can be executed in sequence or in parallel (for example, in a parallel processor or multi-thread processing environment). Specifically as shown in Figure 2 The method can include the following steps: S201: Collecting multi-dimensional data streams of logistics vehicles and express packages in a logistics network point by a smart sensing device cluster; and preprocessing the multi-dimensional data streams to construct a package full-link archive of the logistics network point. In an embodiment of the present specification, the smart sensing device cluster can include the following devices: RFID electronic tag collection device: wherein the RFID electronic tag is embedded on the surface of the package, and real-time collection of goods ID, category, priority label (such as urgent / ordinary), packaging specifications (length, width, height); wherein RFID (Radio Frequency Identification) refers to radio frequency identification; Intelligent load cell system: integrating pressure sensors and AI vision measurement modules, synchronously obtaining goods weight (precision ±0.1 kg) and three-dimensional volume data; Vehicle-mounted IoT terminal: tracking vehicle position through GPS / Beidou dual-mode positioning, combining gyroscope to monitor load balance state, and real-time uploading of environmental data such as vibration frequency, temperature and humidity; Intelligent camera in distribution center: deployed at key nodes such as loading and unloading ports and conveyors, automatically counting inventory stacking height and worker trajectory through image recognition technology. Then, after filtering, data fusion and other preprocessing of the multi-dimensional data streams, a package full-link archive of the logistics network point is constructed.

[0030] S203: According to the package full-link archive, periodically updating the batch loading weight threshold, batch loading volume threshold, path planning priority coefficient, and early warning trigger critical value of the logistics vehicle to obtain periodic decision parameters of the logistics vehicle.

[0031] In an embodiment of the present specification, the dynamic rule engine: updates decision parameters every 5 minutes, including: batch loading weight / volume threshold, path planning priority coefficient, and early warning trigger critical value; Parameter update mechanism Dynamic adjustment of batch loading threshold: Weight threshold: based on the current available vehicle's remaining load capacity (e.g. if the average remaining space of a certain route is 2 tons, automatically adjust the threshold to 1.8 tons to improve loading rate) Volume threshold: dynamically adjustable according to the utilization rate of the three-dimensional space of the carriage (calculated in real time by camera + point cloud modeling), when the waste space of the top of the carriage is detected to be >15%, the volume limit is relaxed.

[0032] Path planning priority coefficient: Congestion factor: access to real-time traffic API of Gaode / Baidu, weight calculation of congestion index (0-10 level) on the way to highway Time urgency: according to the promised delivery time of goods, automatically give 3 times of path priority weight to urgent goods (remaining time <12 hours) Early warning critical value self-adaptation: Historical baseline comparison: compare the same period data in the past 7 days, if the current delay rate exceeds the baseline by 20%, trigger orange warning, and if it exceeds 50%, trigger red warning Dynamic learning mechanism: when the system continuously warns for 3 times without actual delay, automatically adjust the critical value threshold of this line by 5%.

[0033] S205: Obtain external environment data and internal logistics data of the logistics network point, and obtain comprehensive logistics data of the logistics network point.

[0034] In the embodiments of the present specification, the external environment data can include weather data; the internal logistics data can include historical distribution peak value data, average loading and unloading efficiency of each line, distribution center personnel scheduling table, etc.

[0035] S207: According to the comprehensive logistics data of the logistics network point, predict the number of loading and unloading workers, the number of vehicles and the temporary storage area required by the logistics network point in a future preset period, and obtain the transport capacity demand prediction result of the logistics network point in the future preset period.

[0036] In the embodiments of the present specification, the number of loading and unloading workers, the number of vehicles and the temporary storage area required by the logistics network point in a future preset period can be predicted through the comprehensive logistics data of the logistics network point, and the transport capacity demand prediction result of the logistics network point in the future preset period can be obtained.

[0037] S209: According to the transport capacity demand prediction result of the logistics network point in the future preset period and the periodic decision parameter, determine the delay probability of the line in the logistics network point; the delay probability represents the logistics time limit of the logistics network point.

[0038] In the implementation of the present specification, the higher the delay probability of the line, the slower the logistics timeliness; if multiple lines are included in the logistics network point, the delay probability of each line can be calculated, and then the sum of the weighted delay probabilities of each route is calculated as the delay probability of the logistics network point.

[0039] In the embodiments of the present specification, the multi-dimensional data stream of the logistics vehicle and the express package in the logistics network point is collected by the intelligent sensing device cluster; and the multi-dimensional data stream is preprocessed to construct a package full-link archive of the logistics network point; the batch loading weight threshold, the batch loading volume threshold, the path planning priority coefficient and the early warning trigger critical value of the logistics vehicle are periodically updated according to the package full-link archive, to obtain the periodic decision parameters of the logistics vehicle; thereby realizing dynamic adjustment of the decision parameters; the external environment data and the internal logistics data of the logistics network point are obtained to obtain the comprehensive logistics data of the logistics network point; the number of loading and unloading workers, the number of vehicles and the temporary storage area required by the logistics network point in a future preset period are predicted according to the comprehensive logistics data of the logistics network point, to obtain the transport capacity demand prediction result of the logistics network point in the future preset period; thereby the transport capacity demand in the future period is accurately predicted; finally, the delay probability of the line in the logistics network point is determined according to the transport capacity demand prediction result of the logistics network point in the future preset period and the periodic decision parameters; the delay probability represents the logistics timeliness of the logistics network point; thereby the logistics timeliness of the line in the logistics network point can be quickly and accurately predicted In the embodiments of the present specification, as shown in Figure 3 The preprocessing of the multi-dimensional data stream includes: S301: Abnormal data filtering processing is performed on the multi-dimensional data stream to eliminate null values generated by sensor disconnection and abnormal values exceeding the physical limit to obtain filtered data; S303: The respective scanning time stamps of the filtered data are uniformly calibrated to a central clock to obtain space-time aligned data; S305: The RFID data, the weighbridge data and the vehicle trajectory data in the space-time aligned data are associated and fused through the waybill number to construct a package full-link archive of the logistics network point.

[0040] In the embodiments of the present specification, the data preprocessing process can include: (1) Abnormal data filtering: automatically eliminate null values generated by sensor disconnection and abnormal values exceeding the physical limit (such as single piece of goods weight > 10 tons). (2) Space-time alignment: uniformly calibrate the scattered scanning time stamps to the central clock to compensate for the time sequence disorder caused by network transmission delay; (3) Data fusion: associate RFID data, weighbridge data, vehicle trajectory data through waybill number to construct a complete goods full-link archive.

[0041] In the embodiments of the present application, the logistics network points are multiple, and after the logistics network point operation capacity demand prediction result in the future preset period is obtained, the method further comprises: According to the operation capacity demand prediction result of each logistics network point, a visual heat map is constructed; The cumulative demand duration of each operation capacity resource in the operation capacity demand prediction result is obtained; The period in which the cumulative demand duration is greater than a preset duration threshold is determined as a target period, and the target period is marked in the heat map.

[0042] In the embodiments of the present application, when the target period is marked in the heat map, the corresponding operation capacity resource demand data can also be marked; the future preset period can be set according to actual conditions, for example, it can be set to 24 hours. The number of loading and unloading workers, the number of forklifts, and the temporary storage area required by each distribution center in the next 24 hours are predicted in hourly granularity; a visual heat map can be output, and the time period in which the resource gap exceeds 30% (for example, 14:00-16:00 requires an additional 5 operators) is marked.

[0043] In the embodiments of the present application, as shown in Figure 4 The external environment data and the internal logistics data of the logistics network point are obtained to obtain comprehensive logistics data of the logistics network point, which comprises: S401: Obtain the weather information of the running area of the logistics vehicle in the logistics network point within the future preset period, the holiday corresponding to the running time, and the promotion plan of the e-commerce platform as the external environment data of the logistics network point; S403: Obtain the historical distribution peak data, the average loading and unloading efficiency of each line, and the personnel shift schedule of the logistics network point as the internal logistics data of the logistics network point; S405: Take the external environment data and the internal logistics data corresponding to the logistics network point as the comprehensive logistics data of the logistics network point.

[0044] In the embodiments of the present application, the weather information of the running area of the logistics vehicle in the logistics network point within the future preset period, the holiday corresponding to the running time, and the promotion plan of the e-commerce platform can be obtained; for example, the future 48-hour weather forecast (rainfall, wind speed), holiday calendar, and e-commerce platform promotion plan can be obtained as the external environment data of the logistics network point. The historical distribution peak data, the average loading and unloading efficiency of each line, and the personnel shift schedule of the logistics network point are obtained as the internal logistics data of the logistics network point; thereby, the rich comprehensive logistics data of the logistics network point is constructed according to the external environment data and the internal logistics data corresponding to the logistics network point, and the diversity and accuracy of the comprehensive logistics data are improved.

[0045] In the embodiments of the present specification, before the determining of the delay probability of the line in the logistics network point, the method further comprises: According to the periodic decision parameters of the logistics vehicle, a plurality of preset risk level respectively corresponding preset warning parameter range is constructed, and a level parameter relationship library is obtained; The corresponding relationship between the plurality of preset risk levels and the plurality of preset warning strategies is determined, and the corresponding relationship is stored in the preset level strategy relationship library; each preset risk level corresponds to a preset warning strategy; Correspondingly, after the determining of the delay probability of the line in the logistics network point, the method further comprises: According to the level parameter relationship library and the delay probability of the line in the logistics network point, the target risk level of the line is determined; According to the preset level strategy relationship library, the target warning strategy corresponding to the target risk level is determined.

[0046] In the embodiments of the present specification, the level parameter relationship library can be constructed according to the plurality of preset risk level respectively corresponding preset warning parameter range. The corresponding relationship between the plurality of preset risk levels and the plurality of preset warning strategies is determined, and the corresponding relationship is stored in the preset level strategy relationship library. Then, the corresponding target risk level can be found in the level parameter relationship library according to the delay probability of the line in the logistics network point. Then, the target warning strategy corresponding to the target risk level is queried in the preset level strategy relationship library. Thus, the warning strategy of the logistics network point can be quickly determined, and the strategy is executed to avoid delay in the future period.

[0047] The delay probability distribution of each line in the future 6 hours can be calculated based on the Bayesian network (for example, the delay probability of A line rises to 67% under the condition of rainfall); a hierarchical response suggestion is generated (yellow warning: increase 1 spare vehicle; red warning: start adjacent distribution coordination operation).

[0048] In the embodiments of the present specification, as shown in Figure 5 The determining of the corresponding relationship between the plurality of preset risk levels and the plurality of preset warning strategies comprises: S501: For the express package of the highest risk level in the plurality of preset risk levels, it is judged whether the express package is an abnormal package; S503: If the express package is not an abnormal package, a first distribution level of the express package and a first warning strategy of the dynamic adjustment of the handover sheet are constructed; S505: If the express package is an abnormal package, the express package is automatically intercepted and distributed; S507: According to the low risk level in the plurality of preset risk levels, a second early warning strategy corresponding to a second distribution level of the express package is constructed; the priority of the first distribution level is higher than that of the second distribution level.

[0049] In the embodiments of the present specification, the abnormal package can be identified through multi-modal recognition: through sudden weight increase (weighing data), abnormal shape (3D camera detection), comprehensive judgment of damage / leakage risk; automatic routing: guide the abnormal package to the independent security channel, notify the quality inspection personnel synchronously and keep the video segment evidence at the time point of the incident. According to the real-time state, the following actions are automatically triggered: priority distribution of high delay risk goods, dynamic adjustment of delivery order generation strategy, automatic interception and shunting of abnormal packages. High delay risk goods processing: intelligent queuing mechanism: when the delay probability of a batch of goods is > 70%, the priority of the goods in the distribution queue is automatically raised to the highest level.

[0050] In the embodiments of the present specification, the first early warning strategy for constructing the first distribution level of the express package and dynamically adjusting the delivery order comprises: Obtaining a target express package with a delay probability greater than a target probability threshold, and raising the priority of the target express package in the distribution queue to the highest level to obtain a first distribution level; Obtaining a conveyor belt and a platform resource for ordinary express packages as distribution resources of the target express package, and constructing a resource preemption strategy; When it is detected that the main single sub-single distribution of the logistics network point spans multiple carriage areas, the main single sub-single distribution is automatically split into multiple delivery orders and associated with the parent waybill number, and a dynamically adjusted delivery order is constructed; According to the first distribution level, the resource preemption strategy, and the dynamically adjusted delivery order, the first early warning strategy is constructed.

[0051] In the embodiments of the present specification, high delay risk goods processing: intelligent queuing mechanism: when the delay probability of a batch of goods is > 70%, the priority of the goods in the distribution queue is automatically raised to the highest level; resource preemption strategy: temporarily requisitioning the conveyor belt and platform resources originally planned for ordinary goods to prioritize processing of high-risk batches.

[0052] Dynamic generation of delivery order: intelligent order splitting: when it is detected that the main single sub-single distribution spans multiple carriage areas, the main single sub-single distribution is automatically split into multiple delivery orders and associated with the parent waybill number.

[0053] Compliance verification: when generating the delivery order, it is automatically checked whether the weight / volume conforms to the current dynamic threshold, and the re-stowage process is triggered if the rule is violated In the embodiments of the present specification, it can be judged whether the main single is batched and stowed: 1. First, it is judged whether the batched and stowed is pre-batched: The pre-batch allocation needs to meet three conditions: ① The number of loading scanning of the main single is less than the number of inventory; ② The actual weight of the inventory of the main single is less than or equal to 1T; ③ The volume of the inventory is less than or equal to 5F; The number of loading scanning: the number of loading scanning of the sub-single corresponding to the main single.

[0054] The number of inventory: inventory = warehouse-in + warehouse-out (other site scanning or loading scanning at the current site) Warehouse-in: a. The current site has no loading after unloading scanning; b. There is no other site scanning record after unloading scanning time; and c. The unloading scanning time is before the departure confirmation time.

[0055] Warehouse-out: the current site has loading scanning after unloading scanning time (the sub-single loading scanning is before the departure confirmation, and the transfer single departs), or has loading scanning, or other sites have scanning records (only the main node, 02 departure, 03 arrival, 04 delivery, 10 receipt, 18 loading, and 19 unloading).

[0056] The sub-single under the same scanning site is scanned at different transfer single A and transfer single B loading times. The departure confirmation times of transfer single A and transfer single B are compared. If the departure time of transfer single A is later than that of transfer single B, the inventory of transfer single B contains the inventory of transfer single A when transfer single B departs.

[0057] When judging the number of the current scanning time, whether there is the same scanning type and deletion mark data at the same site. If yes, delete the data; if no, count the data. (The number of unloading scanning of the same sub-single at the same distribution center is 1.)

[0058] 2. When the pre-judgment of whether to batch is "no", the main single is not batched.

[0059] When the pre-judgment of whether to batch is "yes", there is no unloading scanning, and the pre-judgment of whether to batch is the default judgment type. When the sub-single is scanned at the next transfer single A unloading record after the departure confirmation of the transfer single A of its main single, the next transfer single A unloading scanning number is less than the number of inventory of the responsible site, which belongs to batched allocation. When the next transfer single A unloading scanning number is greater than or equal to the number of inventory of the responsible site, it does not belong to batched. (The next station unloading scanning data includes 19 unloading scanning and 03 arrival scanning) An example provided by the embodiment is as follows: ① The sub-single 12345 in the inventory main single is scanned at the loading of the transfer single A at the current station, the sub-single 1234 is scanned at the loading of the transfer single A at the current station, the pre-judgment of whether to batch at the current station is "yes", the sub-single 12345 is scanned at the unloading of the transfer single A at the next station, and the pre-judgment of whether to batch at the current station is "no"; ②Sub-single 12345 in the inventory master, the station uses A transfer single to scan sub-single 1234, and displays whether the station judges in batches as "yes", the next station uses A transfer single to scan 2345, and displays whether the station is batched as "yes".

[0060] 3. When the "whether to batch" field is displayed as "yes", there is no unloading scanning, and the "whether to batch" judgment type is defaulted; after the sub-single in its master transfer single departs for 5 days, the next station has no unloading scanning record, and the "whether to batch" judgment type is defaulted.

[0061] The embodiment breaks through the limitation of the traditional fixed threshold, realizes real-time linkage of the rule parameters and the environmental state, and reduces the repeated transportation cost caused by batched loading and unloading.

[0062] As can be seen from the technical solutions provided by the above embodiments of the present specification, the embodiments of the present specification collect multi-dimensional data streams of logistics vehicles and express packages in a logistics network point through an intelligent sensing device cluster; and preprocess the multi-dimensional data streams to construct a package full-link archive of the logistics network point; periodically update the batched loading and unloading weight threshold, the batched loading and unloading volume threshold, the path planning priority coefficient, and the early warning trigger critical value of the logistics vehicle according to the package full-link archive, to obtain periodic decision parameters of the logistics vehicle; thereby realizing dynamic adjustment of the decision parameters; obtain external environmental data and internal logistics data of the logistics network point to obtain comprehensive logistics data of the logistics network point; predict the number of loading and unloading workers, the number of vehicles, and the temporary storage area required by the logistics network point in a future preset time period according to the comprehensive logistics data of the logistics network point, to obtain an operation capacity demand prediction result of the logistics network point in the future preset time period; thereby accurately predicting the operation capacity demand in the future time period; and finally determine a delay probability of a line in the logistics network point according to the operation capacity demand prediction result of the logistics network point in the future preset time period and the periodic decision parameters; the delay probability represents the logistics time efficiency of the logistics network point; thereby the logistics time efficiency of the line in the logistics network point can be quickly and accurately predicted.

[0063] The embodiments of the present specification also provide a logistics time efficiency prediction device, as shown in Figure 6 The device comprises: A multi-dimensional data acquisition module 610 is configured to collect multi-dimensional data streams of logistics vehicles and express packages in a logistics network point through an intelligent sensing device cluster; and preprocess the multi-dimensional data streams to construct a package full-link archive of the logistics network point. A decision parameter determination module 620 is configured to periodically update the batched loading and unloading weight threshold, the batched loading and unloading volume threshold, the path planning priority coefficient, and the early warning trigger critical value of the logistics vehicle according to the package full-link archive, to obtain periodic decision parameters of the logistics vehicle. The comprehensive logistics data acquisition module 630 is configured to acquire external environment data and internal logistics data of the logistics node, and obtain comprehensive logistics data of the logistics node. The transport capacity prediction module 640 is configured to predict, according to the comprehensive logistics data of the logistics node, a number of loading and unloading workers, a number of vehicles and a temporary storage area required by the logistics node in a future preset time period, and obtain a transport capacity demand prediction result of the logistics node in the future preset time period. The delay probability determination module 650 is configured to determine, according to the transport capacity demand prediction result of the logistics node in the future preset time period and the periodic decision parameter, a delay probability of a line in the logistics node; and the delay probability represents a logistics timeliness of the logistics node.

[0064] In some embodiments, the comprehensive logistics data acquisition module includes: The environment data acquisition unit is configured to acquire, as external environment data of the logistics node, weather information of a running area of a logistics vehicle in the logistics node in a future preset time period, a holiday corresponding to a running time and a promotion plan of an e-commerce platform. The logistics data acquisition unit is configured to acquire, as internal logistics data of the logistics node, historical distribution peak data of the logistics node, average loading and unloading efficiency of each line and a personnel scheduling table. The comprehensive data determination unit is configured to determine, as comprehensive logistics data of the logistics node, the external environment data and the internal logistics data corresponding to the logistics node.

[0065] In some embodiments, the device further includes: The grade parameter relationship library construction module is configured to construct, according to the periodic decision parameter of the logistics vehicle, a preset warning parameter range corresponding to each of a plurality of preset risk grades, and obtain a grade parameter relationship library. The strategy relationship library construction module is configured to determine a corresponding relationship between a plurality of preset risk grades and a plurality of preset warning strategies, and store the corresponding relationship in a preset grade strategy relationship library; each preset risk grade corresponds to a preset warning strategy. The target risk grade determination module is configured to determine, according to the grade parameter relationship library and the delay probability of the line in the logistics node, a target risk grade of the line. The target strategy determination module is configured to determine, according to the preset grade strategy relationship library, a target warning strategy corresponding to the target risk grade.

[0066] In some embodiments, the strategy relationship library construction module includes: A judgment unit is configured to judge whether a highest risk level express package among a plurality of preset risk levels is an abnormal package; A first strategy construction unit is configured to construct a first distribution level of the express package and a first early warning strategy of a dynamic adjustment transfer sheet if the express package is a normal package. An interception unit is configured to automatically intercept and divert the express package if the express package is an abnormal package. A second strategy construction unit is configured to construct a second early warning strategy corresponding to a second distribution level of the express package according to a low risk level among the plurality of preset risk levels; and the first distribution level has a higher priority than the second distribution level.

[0067] In some embodiments, the first strategy construction unit comprises: A first distribution level determination subunit is configured to obtain a target express package with a delay probability greater than a target probability threshold, and to improve a priority of the target express package in a distribution queue to a highest level to obtain a first distribution level. A resource preemption strategy construction subunit is configured to obtain a conveyor belt and a platform resource for an ordinary express package as a distribution resource of the target express package, and to construct a resource preemption strategy. A transfer sheet construction subunit is configured to automatically split into a plurality of transfer sheets and associate a parent shipping order number when detecting that a main single sub-single distribution of the logistics network point spans a plurality of carriage areas, and to construct a dynamically adjusted transfer sheet. A first strategy construction subunit is configured to construct the first early warning strategy according to the first distribution level, the resource preemption strategy, and the dynamically adjusted transfer sheet.

[0068] In some embodiments, the logistics network points are a plurality, and the device further comprises: A heat map construction module is configured to construct a visual heat map according to a shipping capacity demand prediction result of each logistics network point. A cumulative demand duration acquisition module is configured to obtain a cumulative demand duration of each shipping capacity resource in the shipping capacity demand prediction result. A time period marking module is configured to determine a time period with a cumulative demand duration greater than a preset duration threshold as a target time period, and to mark the target time period in the heat map.

[0069] In some embodiments, the multi-dimensional data acquisition module comprises: A filtering unit is configured to perform abnormal data filtering processing on the multi-dimensional data stream, to eliminate null values generated by sensor disconnection and abnormal values exceeding physical limits, and to obtain filtered data. An alignment unit is configured to align respective scan time stamps of the filtered data to a central clock to obtain space-time aligned data. A fusion unit is configured to fuse RFID data, weighbridge data and vehicle trajectory data in the space-time aligned data by using a waybill number to construct a package full-link profile of the logistics node.

[0070] The device in the device embodiment and the method embodiment are based on the same inventive concept.

[0071] The electronic device provided in the embodiments of the present disclosure includes a processor and a memory. The memory stores at least one instruction or at least one program. The at least one instruction or at least one program is loaded and executed by the processor to implement the logistics time limit prediction method provided in the above method embodiments.

[0072] The embodiments of the present disclosure further provide a computer storage medium. The computer storage medium can be arranged in a terminal to store at least one instruction or at least one program related to the logistics time limit prediction method in the method embodiments. The at least one instruction or at least one program is loaded and executed by the processor to implement the logistics time limit prediction method provided in the above method embodiments.

[0073] The embodiments of the present disclosure further provide a computer program product or a computer program. The computer program product or the computer program includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium. The processor executes the computer instructions, so that the computer device performs the logistics time limit prediction method provided in the above method embodiments.

[0074] Optionally, in the embodiments of the present disclosure, the storage medium can be located in at least one of a plurality of network servers in a computer network. Optionally, in the embodiments, the storage medium can include, but is not limited to, a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0075] The memory of the embodiments of the present specification can be used to store software programs and modules. The processor performs various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store operating systems, application programs required for functions, etc.; and the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory can also include a memory controller to provide access for the processor to the memory.

[0076] The logistics time limit prediction method provided by the embodiments of the present specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking the case of running on a server, Figure 7 is a hardware structure block diagram of a server of a logistics time limit prediction method provided by the embodiments of the present specification. As Figure 7 shown, the server 700 can have a large difference due to different configurations or performances, and can include one or more central processing units (CPU) 710 (the central processing unit 710 can include but not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 730 for storing data, one or more storage media 720 (such as one or more mass storage devices) for storing application programs 723 or data 722. Among them, the memory 730 and the storage medium 720 can be temporary storage or persistent storage. The programs stored in the storage medium 720 can include one or more modules, each of which can include a series of instruction operations in the server. Further, the central processing unit 710 can be configured to communicate with the storage medium 720 to execute a series of instruction operations in the storage medium 720 on the server 700. The server 700 can also include one or more power supplies 760, one or more wired or wireless network interfaces 750, one or more input and output interfaces 740, and / or one or more operating systems 721, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0077] The input / output interface 740 can be configured to receive or transmit data via a network. The network can include a wireless network provided by a communication provider of the server 700. In an example, the input / output interface 740 includes a network interface controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet. In an example, the input / output interface 740 can be a radio frequency (RF) module that is configured to communicate with the Internet in a wireless manner.

[0078] Those skilled in the art can understand that, Figure 7 The structure shown is only schematic, and does not limit the structure of the electronic device described above. For example, the server 700 can further include more or fewer components than those shown, or have a different configuration of components than those shown. Figure 7 The structure shown is only schematic, and does not limit the structure of the electronic device described above. For example, the server 700 can further include more or fewer components than those shown, or have a different configuration of components than those shown. Figure 7 The structure shown is only schematic, and does not limit the structure of the electronic device described above. For example, the server 700 can further include more or fewer components than those shown, or have a different configuration of components than those shown.

[0079] As can be seen from the embodiments of the logistics time limit prediction method, device, electronic equipment and storage medium provided by the present application, the multi-dimensional data flow of the logistics vehicle and the express package in the logistics network point is collected by the intelligent sensing device cluster; the multi-dimensional data flow is preprocessed, and the package full-link archive of the logistics network point is constructed; the batch loading weight threshold, the batch loading volume threshold, the path planning priority coefficient and the early warning trigger critical value of the logistics vehicle are periodically updated according to the package full-link archive, and the periodic decision parameters of the logistics vehicle are obtained; thereby the dynamic adjustment of the decision parameters is realized; the external environment data and the internal logistics data of the logistics network point are obtained, and the comprehensive logistics data of the logistics network point is obtained; the number of loading and unloading workers, the number of vehicles and the temporary storage area required by the logistics network point in a future preset period are predicted according to the comprehensive logistics data of the logistics network point, and the transport capacity demand prediction result of the logistics network point in the future preset period is obtained; thereby the transport capacity demand in the future period is accurately predicted; finally, the delay probability of the line in the logistics network point is determined according to the transport capacity demand prediction result of the logistics network point in the future preset period and the periodic decision parameters; the delay probability represents the logistics time limit of the logistics network point; thereby the logistics time limit of the line in the logistics network point can be quickly and accurately predicted.

[0080] It should be noted that the above-mentioned order of the embodiments of the specification is only for description, not representing the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of the specification are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be executed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0081] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. Especially, for the device, equipment, storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0082] A person of ordinary skill in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by program instructing relevant hardware to complete, and the program can be stored in a computer storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk.

[0083] The above-mentioned is only the preferred embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A logistics time limit prediction method, characterized in that, The method comprises: Collecting multi-dimensional data streams of logistics vehicles and express packages in a logistics site by an intelligent sensing device cluster; and preprocessing the multi-dimensional data streams to construct a package full-link archive of the logistics site; Periodically updating batch loading weight thresholds, batch loading volume thresholds, path planning priority coefficients, and early warning trigger critical values of the logistics vehicles according to the package full-link archive to obtain periodic decision parameters of the logistics vehicles; Obtaining external environment data and internal logistics data of the logistics site to obtain comprehensive logistics data of the logistics site; According to the comprehensive logistics data of the logistics site, predicting the number of loading and unloading workers, the number of vehicles, and the temporary storage area required by the logistics site in a future preset period to obtain an operation capacity demand prediction result of the logistics site in the future preset period; According to the operation capacity demand prediction result of the logistics site in the future preset period and the periodic decision parameters, determining a delay probability of a line in the logistics site; the delay probability represents the logistics time limit of the logistics site.

2. The method of claim 1, wherein, The method further comprises: According to the periodic decision parameters of the logistics vehicles, constructing a plurality of preset risk level each corresponding to a preset early warning parameter range to obtain a level parameter relationship library; Determining a corresponding relationship between a plurality of preset risk levels and a plurality of preset early warning strategies, and storing the corresponding relationship in a preset level strategy relationship library; each preset risk level corresponds to a preset early warning strategy; After determining the delay probability of the line in the logistics site, the method further comprises:

3. The method of claim 1, wherein, According to the level parameter relationship library and the delay probability of the line in the logistics site, determining a target risk level of the line; According to the preset level strategy relationship library, determining a target early warning strategy corresponding to the target risk level. The method further comprises: For the express packages of the highest risk level in the plurality of preset risk levels, determining whether the express packages are abnormal packages; If the express packages are not abnormal packages, constructing a first distribution level of the express packages and a first early warning strategy of dynamically adjusting a handover sheet; If the express packages are abnormal packages, automatically intercepting and shunting the express packages; 4. The method of claim 3, wherein, ​ ​ ​ ​ According to a low risk level in a plurality of preset risk levels, a second early warning strategy corresponding to a second distribution level of the express package is constructed; the first distribution level has a higher priority than the second distribution level.

5. The method of claim 4, wherein, The first distribution level of the express package and the first early warning strategy of the dynamic adjustment of the handover single are constructed, including: A target express package with a delay probability greater than a target probability threshold is obtained, and a priority of the target express package in a distribution queue is raised to the highest level to obtain a first distribution level; A conveyor belt and a platform resource for ordinary express packages are obtained as distribution resources of the target express package, and a resource preemption strategy is constructed; When it is detected that the main single of the logistics network point is distributed across a plurality of carriage areas, the main single is automatically split into a plurality of handover singles and associated with a parent operation single number, and a dynamically adjusted handover single is constructed; According to the first distribution level, the resource preemption strategy, and the dynamically adjusted handover single, the first early warning strategy is constructed.

6. The method of claim 1, wherein, The logistics network points are multiple, and after the operation capacity demand prediction result of the logistics network points in the future preset period is obtained, the method further includes: According to the operation capacity demand prediction result of each logistics network point, a visual heat map is constructed; An accumulated demand duration of each operation capacity resource in the operation capacity demand prediction result is obtained; A period with a cumulative demand duration greater than a preset duration threshold is determined as a target period, and the target period is marked in the heat map.

7. The method according to any one of claims 1 to 6, characterized in that, The preprocessing of the multi-dimensional data stream, the construction of the package full-link archive of the logistics network point, includes: The multi-dimensional data stream is subjected to abnormal data filtering processing, and null values generated by sensor disconnection and abnormal values exceeding physical limits are eliminated to obtain filtered data; The scanning time stamps of the filtered data are uniformly calibrated to a central clock to obtain space-time aligned data; The RFID data, the weighbridge data, and the vehicle trajectory data in the space-time aligned data are associated and fused through the operation single number to construct the package full-link archive of the logistics network point.

8. A logistics time limit prediction device characterized by comprising: The device includes: A multi-dimensional data acquisition module is configured to acquire multi-dimensional data streams of logistics vehicles and express packages in a logistics network point through an intelligent sensing device cluster, and to preprocess the multi-dimensional data streams to construct a package full-link archive of the logistics network point; A decision parameter determination module is configured to periodically update a batch loading weight threshold, a batch loading volume threshold, a path planning priority coefficient, and a warning trigger threshold of the logistics vehicles according to the package full-link archive to obtain periodic decision parameters of the logistics vehicles; A comprehensive logistics data acquisition module is configured to acquire external environment data and internal logistics data of the logistics network point to obtain comprehensive logistics data of the logistics network point; An operation capacity prediction module is configured to predict the number of loading and unloading workers, the number of vehicles, and the temporary storage area required by the logistics network point in a future preset period according to the comprehensive logistics data of the logistics network point to obtain an operation capacity demand prediction result of the logistics network point in the future preset period. The delay probability determination module is configured to determine a delay probability of a route in the logistics network point according to the capacity demand prediction result of the logistics network point in the future preset time period and the periodic decision parameter, and the delay probability represents a logistics time limit of the logistics network point.

9. An electronic device, comprising: The device comprises a processor and a memory, and the memory stores at least one instruction or at least one program, which is loaded and executed by the processor to realize the logistics time limit prediction method according to any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction or at least one program, which is loaded and executed by the processor to realize the logistics time limit prediction method according to any one of claims 1-7.

Images