Logistics data processing method and device, equipment and storage medium

Abstract

The invention relates to the technical field of logistics data processing, and discloses a logistics data processing method, which comprises the following steps of: acquiring an entry and exit timestamp data stream of a logistics node in real time, and processing the time data stream in real time; detecting a logistics delay event, and detecting the logistics delay event in real time; performing distribution permission verification, performing position verification through a geo-fence system and a dynamic permission attenuation model, and granting a distribution access permission; logistics delay analysis: when delay abnormity is detected, calculating contribution weight of each level factor to delay and generating an analysis report; and performing compliance judgment, dynamically calculating a theoretical outbound time threshold according to the multi-source timestamp data of cargo inbound and outbound, and generating a compliance judgment result. According to the invention, data timeliness can be ensured, and the logistics delay mode can be identified in real time; delicacy management of distribution permissions is carried out; delay analysis is accurate; compliance judgment can be automatically carried out, and a closed loop is realized; the human intervention demand is obviously reduced; and the logistics efficiency is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics data processing, and particularly relates to a logistics data processing method, device, equipment and storage medium. BACKGROUND

[0002] The traditional logistics data permission management adopts a static configuration mode, and permission allocation is based on a fixed organizational structure and preset rules, and cannot be dynamically adjusted according to business needs. In a cross-regional, multi-level distribution scene, when the organizational structure is adjusted or the personnel role is changed, the system needs to manually reconfigure the permissions, resulting in low efficiency of cross-regional data sharing and collaboration. In addition, static permission management is difficult to adapt to temporary business needs, further exacerbating the complexity of cross-department collaboration.

[0003] The traditional ETL mode extracts data from multiple heterogeneous data sources through a timing batch task, and performs cleaning, conversion and aggregation calculation in an offline environment. This mode causes significant delay in index calculation, and cannot reflect the real-time state of logistics operation. Especially in a multi-level distribution scene, data needs to go through multiple layers of aggregation and transmission, further prolonging the index update period, making it difficult to support real-time decision-making.

[0004] At the same time, in the process of data storage and analysis, the spatial dimension and the time dimension are independent of each other, and there is a lack of unified spatio-temporal correlation modeling capability. This fragmentation leads to low efficiency of root cause analysis of abnormal events: on the one hand, spatial data and temporal data need to be stored and processed separately, increasing the complexity of data correlation; on the other hand, traditional analysis methods are difficult to capture dynamic correlation patterns in the spatio-temporal dimension, making it difficult to locate the root cause of the abnormal event, affecting the timeliness of problem solving.

[0005] Therefore, it is necessary to invent a logistics data statistical processing method capable of dynamically adapting to organizational structure changes, supporting real-time data processing and analysis, and realizing deep fusion of spatio-temporal dimensions, to solve the problems of cross-regional collaboration difficulties, index calculation delay and low efficiency of abnormal root cause analysis. SUMMARY

[0006] The present application provides a logistics data processing method, device, equipment and storage medium, which is a logistics data statistical processing method capable of dynamically adapting to organizational structure changes, supporting real-time data processing and analysis, and realizing deep fusion of spatio-temporal dimensions, to solve the problems of cross-regional collaboration difficulties, index calculation delay and low efficiency of abnormal root cause analysis.

[0007] The first aspect of the present application provides a logistics data processing method, which comprises: real-time collection of inbound and outbound timestamp data streams of logistics nodes, and real-time processing of the time data stream; Detecting a logistics delay event, detecting the logistics delay event in real time by constructing a dynamic CEP rule engine in Flink and deploying a CluStream stream clustering algorithm; Permission verification, location verification is performed through a geofencing system and a dynamic permission decay model, and access permission for distribution is granted; Logistics delay analysis, a multi-level reasoning network is constructed, when a delay anomaly is detected, the contribution weight of each level factor to the delay is calculated and an analysis report is generated; Compliance determination, dynamically calculate the theoretical outbound time threshold according to the multi-source timestamp data of goods entering and leaving the station, and generate compliance determination results by comparing the actual outbound time with the theoretical outbound time threshold.

[0008] Optionally, in the first implementation manner of the first aspect of the present application, the real-time collection of the inbound and outbound timestamp data stream of the logistics node, the real-time processing of the time data stream comprises: Collecting the inbound and outbound timestamp data stream of the logistics node in real time through an Internet of Things device; Real-time analysis of the timestamp data stream by using an abnormality detection algorithm that fuses space-time weights, dynamically adjusting the abnormality determination threshold, and identifying abnormal events in the timestamp sequence; Windowing processing of the timestamp data stream by a stream processing engine, dividing time windows based on event time semantics, and triggering aggregation calculation when the window is closed, and outputting the time efficiency statistical result of the logistics node.

[0009] Optionally, in the second implementation manner of the first aspect of the present application, the detecting of the logistics delay event, the real-time detection of the logistics delay event by constructing a dynamic CEP rule engine in Flink and deploying a CluStream stream clustering algorithm, comprises: Deploying a dynamic CEP rule engine in a stream processing engine, constructing a multi-level rule system, including a basic rule layer, an adaptive adjustment layer and a pattern discovery layer, and matching the delay pattern in the logistics event stream in real time; Real-time micro-cluster maintenance of the logistics event stream by using an online-offline two-stage stream clustering algorithm, and representing different delay types through dynamic micro-clusters; Identifying new delay events based on space-time feature dissimilarity.

[0010] Optionally, in the third implementation manner of the first aspect of the present application, the permission verification for distribution, the location verification is performed through a geofencing system and a dynamic permission decay model, and the access permission for distribution is granted, comprising: Obtaining the coordinates of the user equipment through positioning technology, and judging whether the user is in the authorized area based on the preset geofencing boundary; According to the relationship between the user organization level and the current position, the permission strength is dynamically calculated, and the permission strength decays with the increase of the spatial distance; Based on the position verification result and the permission strength, an access token is generated, and the access token includes an operable function and a valid period; When the user position deviates from the authorized area or the permission is insufficient, a hierarchical response operation is triggered, and an audit log is recorded.

[0011] Optionally, in the fourth implementation manner of the first aspect of the present application, the logistics delay analysis constructs a multi-level inference network, calculates the contribution weight of each level factor to the delay when detecting the delay anomaly, and generates an analysis report, including: A multi-level inference network including an input layer, an intermediate layer and an output layer is constructed; Based on the output of the multi-level inference network, a weight analysis model is used to calculate the contribution weight of each level factor to the delay, and the weight analysis model integrates subjective weighting method and objective data driven method to dynamically adjust the weight distribution of each factor; According to the delay type, the contribution weight and the comparison result of the historical data, a multi-dimensional report including root cause analysis, risk prediction and optimization suggestion is automatically generated.

[0012] Optionally, in the sixth implementation manner of the first aspect of the present application, the compliance determination dynamically calculates a theoretical outbound time threshold value according to multi-source timestamp data of goods entering and leaving the station, and generates a compliance determination result by comparing the actual outbound time with the theoretical outbound time threshold value, including: Multi-source timestamp data in the process of goods entering and leaving the station is obtained; Based on historical outbound time data and real-time operation parameters, a theoretical outbound time threshold value is dynamically calculated through a time series prediction model; The actual outbound time is compared with the theoretical outbound time threshold value, if the actual time exceeds the threshold value range, it is marked as an abnormal event, and a determination result including delay level and root cause classification is generated.

[0013] Optionally, in the seventh implementation manner of the first aspect of the present application, the compliance determination dynamically calculates a theoretical outbound time threshold value according to multi-source timestamp data of goods entering and leaving the station, and generates a compliance determination result by comparing the actual outbound time with the theoretical outbound time threshold value, and further includes: The determination result is fed back to the historical database, the prediction model parameters are optimized through an online learning mechanism, and a warning signal is triggered to the dispatching system to dynamically adjust the transportation plan.

[0014] The second aspect of the present application provides a logistics data processing device, including: A data stream processing module is used to collect the inbound and outbound timestamp data stream of the logistics node in real time, and the time data stream is processed in real time; detecting a logistics delay event module for detecting a logistics delay event in real time by constructing a dynamic CEP rule engine in Flink and deploying a CluStream streaming clustering algorithm; a distribution permission verification module for granting distribution access permission by verifying the location through a geofencing system and a dynamic permission decay model; a logistics delay analysis module for constructing a multi-level reasoning network, and when detecting a delay anomaly, calculating the contribution weight of each level factor to the delay and generating an analysis report; a compliance determination module for dynamically calculating a theoretical outbound time threshold according to multi-source timestamp data of goods entering and leaving a station, and generating a compliance determination result by comparing the actual outbound time with the theoretical outbound time threshold.

[0015] Optionally, in the first implementation manner of the second aspect of the present application, the data stream processing module comprises: a collection unit for collecting timestamp data streams of a logistics node in real time through an Internet of Things device; a first recognition unit for performing real-time analysis on the timestamp data streams by using an abnormality detection algorithm that fuses time and space weights, dynamically adjusting an abnormality determination threshold, and recognizing abnormal events in the timestamp sequence; and a processing unit for performing windowing processing on the timestamp data streams through a stream processing engine, dividing time windows based on event time semantics, and triggering aggregation calculation when a window is closed to output time efficiency statistical results of the logistics node.

[0016] Optionally, in the second implementation manner of the second aspect of the present application, the detecting a logistics delay event module comprises: a first construction unit for deploying a dynamic CEP rule engine in a stream processing engine, constructing a multi-level rule system including a basic rule layer, an adaptive adjustment layer and a pattern discovery layer, and matching delay patterns in a logistics event stream in real time; a representation unit for performing real-time micro-cluster maintenance on the logistics event stream by using an online-offline two-stage streaming clustering algorithm, and representing different delay types through dynamic micro-clusters; and a second recognition unit for recognizing new delay events based on spatial and temporal feature dissimilarity.

[0017] Optionally, in the third implementation manner of the second aspect of the present application, the distribution permission verification module comprises: a first acquisition unit for acquiring a user device coordinate through positioning technology, and judging whether the user is in an authorized area based on a preset geofencing boundary; a first calculation unit for dynamically calculating a permission strength according to the relationship between the user organization level and the current location, the permission strength decaying with the increase of spatial distance; a first generation unit for generating an access token based on the location verification result and the permission strength, the access token containing an operable function and a validity period; and a triggering unit for triggering a hierarchical response operation and recording an audit log when the user location deviates from the authorized area or the permission is insufficient.

[0018] Optionally, in the fourth implementation form of the second aspect of the present application, the logistics delay analysis module comprises: a second construction unit configured to construct a multi-level inference network comprising an input layer, an intermediate layer and an output layer; an adjustment unit configured to calculate the contribution weight of each level factor to the delay based on the output of the multi-level inference network, using a weight analysis model that integrates subjective weighting method and objective data-driven method to dynamically adjust the weight distribution of each factor; and a second generation unit configured to automatically generate a multi-dimensional report comprising root cause analysis, risk prediction and optimization suggestions according to the delay type, the contribution weight and the comparison result of the historical data.

[0019] Optionally, in the fifth implementation form of the second aspect of the present application, the compliance determination module comprises: a second acquisition unit configured to acquire multi-source timestamp data in the process of goods entering and leaving the station; a second calculation unit configured to dynamically calculate a theoretical outbound time threshold value through a time series prediction model based on historical outbound time data and real-time operation parameters; and a comparison unit configured to compare the actual outbound time with the theoretical outbound time threshold value, and if the actual time exceeds the threshold range, mark it as an abnormal event and generate a determination result comprising a delay level and a root cause classification.

[0020] The third aspect of the present application provides a logistics data processing device comprising a memory and at least one processor, wherein the memory stores computer readable instructions; The at least one processor invokes the computer readable instructions in the memory to perform the steps of the logistics data processing method as described above.

[0021] The fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer readable instructions, and the computer readable instructions are executed by a processor to implement the steps of the logistics data processing method as described above.

[0022] In the technical solution provided by the present application, the timestamp data stream of the logistics node is obtained in real time through the Internet of Things device and the distributed system, which solves the delay problem caused by traditional manual recording or batch processing and ensures the timeliness of the data; the logistics delay mode can be identified in real time; the distribution authority is finely managed to ensure safety; the delay analysis is accurate and has interpretability; the compliance determination can be automatically performed and a closed loop is realized; the need for human intervention is significantly reduced; and the logistics efficiency is effectively improved and the violation cost is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 The first flowchart of the logistics data processing method provided by the embodiments of the present application; Figure 2 The second flowchart of the logistics data processing method provided by the embodiments of the present application; Figure 3 A third flowchart of a logistics data processing method provided by an embodiment of the present application is shown in FIG. 8; Figure 4 A fourth flowchart of a logistics data processing method provided by an embodiment of the present application is shown in FIG. 9; Figure 5 A fifth flowchart of a logistics data processing method provided by an embodiment of the present application is shown in FIG. 10; Figure 6 A sixth flowchart of a logistics data processing method provided by an embodiment of the present application is shown in FIG. 11; Figure 7 A structural schematic diagram of a logistics data processing device provided by an embodiment of the present application is shown in FIG. 12; Figure 8 A structural schematic diagram of a logistics data processing device provided by an embodiment of the present application is shown in FIG. 12; DETAILED DESCRIPTION

[0024] The embodiments of the present application provide a logistics data processing method, device, equipment and storage medium, which are used for deep analysis and processing of logistics business data, and improve the efficiency and accuracy of logistics business management.

[0025] The terms "first", "second", "third", "fourth" and the like (if any) in the description, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a particular order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited 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] For the convenience of understanding, the specific flow of the embodiments of the present application is described below. Please refer to Figure 1 The first embodiment of a logistics data processing method in the embodiments of the present application includes: S101, collecting real-time inbound and outbound timestamp data streams of logistics nodes, and processing the time data streams in real time; S102, detecting a logistics delay event, and detecting the logistics delay event in real time by constructing a dynamic CEP rule engine and deploying a CluStream streaming clustering algorithm in Flink; S103, distribution authority verification, verifying the location by a geo-fencing system and a dynamic authority decay model, and granting distribution access authority; S104, logistics delay analysis, constructing a multi-level reasoning network, when detecting delay anomalies, calculating the contribution weight of each level factor to the delay and generating an analysis report; S105, compliance determination, dynamically calculating the theoretical outbound time threshold according to the multi-source timestamp data of the inbound and outbound stations of the goods, and generating a compliance determination result by comparing the actual outbound time with the theoretical outbound time threshold.

[0027] In the technical solution provided by the application, the timestamp data stream of the logistics node is acquired in real time through the Internet of Things device and the distributed system, the delay problem caused by traditional manual recording or batch processing is solved, the data timeliness is ensured, the logistics delay mode can be identified in real time, the distribution authority is fine management, the safety is ensured, the delay analysis is accurate and has interpretability, the compliance determination can be automatically performed and closed loop is realized, the human intervention demand is significantly reduced, and the logistics efficiency is effectively improved and the violation cost is reduced.

[0028] Please refer to Figure 2 In the second embodiment of the logistics data processing method in the embodiment of the application, the inbound and outbound timestamp data stream of the logistics node is collected in real time, and the time data stream is processed in real time, including: S201, the inbound and outbound timestamp data stream of the logistics node is collected in real time through the Internet of Things device; S202, the timestamp data stream is analyzed in real time by using an abnormality detection algorithm fusing space-time weight, the abnormality determination threshold is dynamically adjusted, and the abnormal events in the timestamp sequence are identified; S203, the timestamp data stream is windowed by a stream processing engine, the time window is divided based on event time semantics, and the aggregation calculation is triggered when the window is closed, and the timeliness statistical result of the logistics node is output.

[0029] In the embodiment of the application, the inbound and outbound timestamps of the logistics node are acquired in real time through RFID, GPS and other devices, the delay problem of traditional manual recording or batch transmission is solved, the data timeliness can be improved to the millisecond level, the sliding window is divided based on event time semantics, the error when processing out-of-order data is effectively avoided, the aggregation calculation is triggered when the window is closed, the abnormal types such as offset, loss and repetition in the timestamp sequence can be identified, the classification accuracy is high, the generation speed of the logistics timeliness analysis report is greatly improved, and the decision response time is greatly shortened.

[0030] Please refer to Figure 3 In the third embodiment of the logistics data processing method in the embodiment of the application, the logistics delay event is detected, a dynamic CEP rule engine is constructed in Flink, and a CluStream stream clustering algorithm is deployed, the logistics delay event is detected in real time, including: S301, deploying a dynamic CEP rule engine in a stream processing engine, constructing a multi-level rule system including a basic rule layer, an adaptive adjustment layer and a pattern discovery layer, and matching a delay pattern in a logistics event stream in real time; S302, adopting an online-offline two-stage stream clustering algorithm to perform real-time micro-cluster maintenance on the logistics event stream, and representing different delay types through dynamic micro-clusters; S303, identifying a new delay event based on spatiotemporal feature dissimilarity.

[0031] According to the embodiment of the present application, the rule threshold can be dynamically adjusted according to real-time data, so that misjudgment can be avoided; the CluStream algorithm can update the micro-cluster center and radius in real time, so that the delay type can be dynamically represented in real time, and the identification speed is fast; the delay root cause classification accuracy is high, the system expansion cost is reduced, and the new scene adaptation period is effectively shortened; through the lightweight architecture and the adaptive algorithm, high-precision monitoring is realized at a low cost.

[0032] Referring to Figure 4 In the fourth embodiment of the logistics data processing method in the embodiment of the present application, the distribution authority verification is performed through a geographic fence system and a dynamic authority attenuation model to grant a distribution access authority, which comprises the following steps: S401, obtaining a user equipment coordinate through a positioning technology, and judging whether the user is in an authorized area based on a preset geographic fence boundary; S402, dynamically calculating an authority strength according to the relationship between the user organization level and the current position, the authority strength being attenuated with the increase of the spatial distance; S403, generating an access token based on the position verification result and the authority strength, the access token comprising an operable function and a validity period; S404, triggering a hierarchical response operation and recording an audit log when the user position deviates from the authorized area or the authority is insufficient.

[0033] In the embodiment, the GPS drift problem is solved through the combination of the static geographic fence and the dynamic trajectory prediction, the position verification accuracy is high; the authority strength is calculated according to the spatial distance between the user and the target distribution and the time length of leaving the authorized area, so that the risk of exceeding the authority caused by the authority is effectively fixed; the hierarchical operation can be triggered for the abnormal access, and the audit log is recorded through the blockchain, so that the after-the-fact traceability and compliance review are supported.

[0034] Referring to Figure 5 In the fifth embodiment of the logistics data processing method in the embodiment of the present application, the logistics delay analysis comprises the following steps: S501, constructing a multi-level reasoning network comprising an input layer, an intermediate layer and an output layer; S502, based on the output of the multi-level reasoning network, a weight analysis model is used to calculate the contribution weight of each level factor to the delay, the weight analysis model fuses subjective weighting method and objective data driven method, and dynamically adjusts the weight distribution of each factor; S503, according to the delay type, the contribution weight and the comparison result of the historical data, a multi-dimensional report including root cause analysis, risk prediction and optimization suggestion is automatically generated.

[0035] In the embodiment of the application, through the design of the multi-level reasoning network, the accuracy of delay root cause identification is greatly improved, and the misjudgment rate is effectively reduced; the report automatically records the analysis logic and data source, and can recommend path adjustment or resource allocation scheme combined with network structure characteristics; the operation cost is significantly reduced through preventive analysis and resource optimization.

[0036] Please refer to Figure 6 In the sixth embodiment of the logistics data processing method in the embodiment of the application, the compliance determination dynamically calculates a theoretical outbound time threshold value according to multi-source timestamp data of goods entering and leaving a station, and generates a compliance determination result by comparing an actual outbound time with the theoretical outbound time threshold value, including: S601, acquiring multi-source timestamp data in the process of goods entering and leaving a station; S602, based on historical outbound time data and real-time operation parameters, dynamically calculating a theoretical outbound time threshold value through a time series prediction model; S603, comparing the actual outbound time with the theoretical outbound time threshold value, if the actual time exceeds the threshold value range, marking it as an abnormal event, and generating a determination result including a delay level and a root cause classification.

[0037] In the embodiment, multi-source time data such as transportation vehicle entering station scanning time and sorting completion time are integrated, the single data source deviation problem is solved, the time synchronization degree is high; the actual and theoretical time are compared in real time, the abnormal marking is automatically triggered, and the root cause classification is associated; the determination result directly generates a visual report, including a delay trend chart, a responsibility node positioning and improvement suggestions, etc.; according to the delay level, a differentiated response is triggered to avoid risk diffusion.

[0038] The above describes the logistics data processing method in the embodiment of the application, and the device in the embodiment of the application is described below, please refer to Figure 7 The embodiment of the logistics data processing device in the embodiment of the application includes: The data stream processing module 701 is used for real-time acquisition of the entering and leaving station timestamp data stream of the logistics node, and real-time processing of the time data stream; The logistics delay event detection module 702 is configured to detect logistics delay events in real time by constructing a dynamic CEP rule engine in Flink and deploying a CluStream stream clustering algorithm. The distribution permission verification module 703 is configured to verify the location by a geofencing system and a dynamic permission attenuation model, and grant distribution access permission. The logistics delay analysis module 704 is configured to construct a multi-level reasoning network, and calculate the contribution weight of each level factor to the delay and generate an analysis report when detecting a delay anomaly. The compliance determination module 705 is configured to dynamically calculate a theoretical outbound time threshold according to multi-source timestamp data of goods entering and leaving a station, and generate a compliance determination result by comparing an actual outbound time with the theoretical outbound time threshold.

[0039] In some embodiments, the data stream processing module 701 comprises: The acquisition unit 7011 is configured to acquire, in real time, timestamp data streams of inbound and outbound logistics nodes by Internet of Things devices. The first identification unit 7012 is configured to analyze the timestamp data streams in real time by using an abnormality detection algorithm fusing space-time weights, dynamically adjust an abnormality determination threshold, and identify abnormal events in the timestamp sequence. The processing unit 7013 is configured to perform windowing processing on the timestamp data streams by a stream processing engine, divide time windows based on event time semantics, trigger aggregation calculation when the window is closed, and output time efficiency statistical results of the logistics nodes.

[0040] The present application solves the delay problem of traditional manual recording or batch transmission by acquiring inbound and outbound timestamps of logistics nodes in real time by RFID, GPS and other devices, and improves the data timeliness to the millisecond level. The sliding window is divided based on event time semantics, which effectively avoids errors when processing out-of-order data, and triggers aggregation calculation when the window is closed. The application can also identify abnormal types such as offset, missing and repetition in the timestamp sequence, and has high classification accuracy. The generation speed of the logistics time efficiency analysis report is greatly improved, and the decision response time is greatly shortened.

[0041] In some embodiments, the logistics delay event detection module 702 comprises: The first construction unit 7021 is configured to deploy a dynamic CEP rule engine in a stream processing engine, construct a multi-level rule system including a basic rule layer, an adaptive adjustment layer and a pattern discovery layer, and match delay patterns in the logistics event stream in real time. The representation unit 7022 is configured to maintain real-time micro-clusters of the logistics event stream by using an online-offline two-stage stream clustering algorithm, and represent different delay types by dynamic micro-clusters. The second identification unit 7023 is configured to identify the new delay event based on the spatiotemporal feature dissimilarity.

[0042] The application can dynamically adjust the rule threshold according to real-time data to avoid misjudgment; the CluStream algorithm updates the micro-cluster center and radius in real time, dynamically represents the delay type in real time, and has high identification speed; the delay root cause classification has high accuracy, the system expansion cost is reduced, the new scene adaptation period is effectively shortened; through the lightweight architecture and the adaptive algorithm, high-precision monitoring is realized at a low cost.

[0043] In some embodiments, the distribution authority verification module 703 includes: The first acquisition unit 7031 is configured to acquire the user equipment coordinates through positioning technology, and determine whether the user is in the authorized area based on the preset geofence boundary; The first calculation unit 7032 is configured to dynamically calculate the authority strength according to the relationship between the user organization level and the current position, and the authority strength decays with the increase of the spatial distance; The first generation unit 7033 is configured to generate an access token based on the position verification result and the authority strength, and the access token includes an operable function and a validity period; The triggering unit 7034 is configured to trigger a hierarchical response operation and record an audit log when the user position deviates from the authorized area or the authority is insufficient.

[0044] In this embodiment, the static geofence and dynamic trajectory prediction are combined to solve the GPS drift problem, and the position verification accuracy is high; the authority strength is calculated according to the spatial distance between the user and the target distribution and the time length of leaving the authorized area, which effectively fixes the risk of exceeding authority caused by authority; the hierarchical operation can be triggered for abnormal access, and the audit log is recorded through the blockchain, which supports post-tracing and compliance review.

[0045] In some embodiments, the logistics delay analysis module 704 includes: The second construction unit 7041 is configured to construct a multi-level reasoning network including an input layer, an intermediate layer and an output layer; The adjustment unit 7042 is configured to calculate the contribution weight of each level factor to the delay based on the output of the multi-level reasoning network by using a weight analysis model, and the weight analysis model fuses a subjective weighting method and an objective data driven method to dynamically adjust the weight distribution of each factor; The second generation unit 7043 is configured to automatically generate a multi-dimensional report including root cause analysis, risk prediction and optimization suggestions according to the delay type, the contribution weight and the historical data comparison result.

[0046] In the embodiment of the present application, the design of the multi-level inference network greatly improves the accuracy of delay root cause identification and effectively reduces the misjudgment rate. The report automatically records and analyzes the logic and data sources, and can recommend path adjustment or resource allocation scheme combined with the network structure characteristics. The preventive analysis and resource optimization significantly reduce the operating cost.

[0047] In some embodiments, the compliance determination module 705 includes: The second acquisition unit 7051 is configured to acquire multi-source timestamp data in the process of goods entering and leaving the station. The second calculation unit 7052 is configured to dynamically calculate a theoretical outbound time threshold value based on historical outbound time data and real-time operation parameters through a time series prediction model. The comparison unit 7053 is configured to compare the actual outbound time with the theoretical outbound time threshold value, and if the actual time exceeds the threshold value range, mark it as an abnormal event, and generate a determination result including delay level and root cause classification.

[0048] In the embodiment, the multi-source time data of the transportation equipment (such as the scanning time of the transportation vehicle entering the station and the sorting completion time) is integrated, the single data source deviation problem is solved, the time synchronization degree is high, the actual and theoretical time are compared in real time, the abnormal marking is automatically triggered, and the root cause classification is associated. The determination result directly generates a visual report including delay trend chart, responsibility node positioning and improvement suggestion, etc. According to the delay level, a differentiated response is triggered to avoid risk diffusion.

[0049] Figure 7 The structure of the logistics data processing apparatus shown does not constitute a limitation on the logistics data processing apparatus, and can realize the steps of the logistics data processing method provided by each method embodiment.

[0050] The above Figure 7 The logistics data processing apparatus in the embodiment of the present application is described in detail from the perspective of modular functional entities, and the logistics data processing apparatus in the embodiment of the present application is described in detail from the perspective of hardware processing.

[0051] Figure 8is a structural schematic diagram of a logistics data processing device provided by an embodiment of the present application. The device 800 can have great differences due to different configurations or performances, and can include one or more central processing units (CPUs) 810 (for example, one or more processors) and a memory 820, one or more storage media 830 (for example, one or more mass storage devices) storing application programs 833 or data 832. The memory 820 and the storage media 830 can be temporary storage or persistent storage. The programs stored in the storage media 830 can include one or more modules (not shown in the figure), and each module can include a series of instruction operations in the device 800. Furthermore, the processor 810 can be configured to communicate with the storage media 830 and execute the series of instruction operations in the storage media on the device 800.

[0052] The device 800 can also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input / output interfaces 860, and / or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

[0053] The embodiment of the present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium or a volatile computer readable storage medium. The computer readable storage medium stores instructions, and when the instructions are run on a computer, the computer executes the steps of the logistics data processing method.

[0054] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system or device, unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0055] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0056] The above-described embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the same; even though the present application has been described in detail with reference to the foregoing embodiments, those ordinarily skilled in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some of the technical features; and these modifications or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A logistics data processing method characterized by, The logistics data processing method comprises: Real-time collection of inbound and outbound timestamp data streams of logistics nodes, real-time processing of time data streams; Detecting logistics delay events, real-time detection of logistics delay events by constructing a dynamic CEP rule engine in Flink and deploying a CluStream streaming clustering algorithm; Distribution authority verification, location verification by a geofencing system and a dynamic permission decay model, and granting of distribution access permissions; Logistics delay analysis, constructing a multi-level reasoning network, calculating the contribution weight of each level factor to the delay when detecting delay anomalies, and generating an analysis report; Compliance determination, dynamically calculating a theoretical outbound time threshold based on multi-source timestamp data of inbound and outbound cargo, and generating a compliance determination result by comparing the actual outbound time with the theoretical outbound time threshold.

2. The logistics data processing method according to claim 1, characterized in that, The real-time collection of inbound and outbound timestamp data streams of logistics nodes, and the real-time processing of time data streams, comprise: Real-time collection of inbound and outbound timestamp data streams of logistics nodes by Internet of Things devices; Real-time analysis of timestamp data streams using an anomaly detection algorithm that fuses spatiotemporal weights, dynamic adjustment of anomaly determination thresholds, and identification of abnormal events in timestamp sequences; Windowing processing of timestamp data streams by a stream processing engine, division of time windows based on event time semantics, and triggering of aggregation calculation when the window is closed, and output of time efficiency statistics of logistics nodes.

3. The logistics data processing method according to claim 2, characterized in that, The detection of logistics delay events, real-time detection of logistics delay events by constructing a dynamic CEP rule engine in Flink and deploying a CluStream streaming clustering algorithm, comprises: Deploying a dynamic CEP rule engine in a stream processing engine, constructing a multi-level rule system including a basic rule layer, an adaptive adjustment layer, and a pattern discovery layer, and real-time matching of delay patterns in logistics event streams; Using an online-offline two-stage streaming clustering algorithm, real-time micro-cluster maintenance of logistics event streams, and dynamic micro-cluster representation of different delay types; Identification of new delay events based on spatiotemporal feature dissimilarity.

4. The logistics data processing method according to claim 3, characterized by, The distribution authority verification, location verification by a geofencing system and a dynamic permission decay model, and granting of distribution access permissions, comprise: Obtaining user device coordinates through positioning technology, and determining whether the user is in an authorized area based on a pre-set geofencing boundary; Dynamic calculation of permission strength based on the relationship between the user organization level and the current location, the permission strength decays with increasing spatial distance; Generating an access token based on the location verification result and the permission strength, the access token contains operable functions and a validity period; When the user's location deviates from the authorized area or the permission is insufficient, triggering a hierarchical response operation and recording an audit log.

5. The logistics data processing method according to claim 1, wherein The logistics delay analysis, constructing a multi-level reasoning network, calculating the contribution weight of each level factor to the delay when detecting delay anomalies, and generating an analysis report, comprises: Constructing a multi-level reasoning network comprising an input layer, an intermediate layer, and an output layer; Based on the output of the multi-level reasoning network, calculating the contribution weight of each level factor to the delay using a weight analysis model, the weight analysis model fuses subjective weighting method and objective data driven method, and dynamically adjusts the weight distribution of each factor; According to the delay type, the contribution weight and the comparison result of the historical data, a multi-dimensional report including root cause analysis, risk prediction and optimization suggestions is automatically generated.

6. The logistics data processing method according to claim 5, wherein, The compliance determination dynamically calculates a theoretical outbound time threshold value according to multi-source timestamp data of goods entering and leaving a station, generates a compliance determination result by comparing an actual outbound time with the theoretical outbound time threshold value, and includes the following: Obtaining multi-source timestamp data in the process of goods entering and leaving a station; Based on historical outbound time data and real-time operation parameters, a theoretical outbound time threshold value is dynamically calculated by a time series prediction model; Comparing the actual outbound time with the theoretical outbound time threshold value, if the actual time exceeds the threshold range, it is marked as an abnormal event, and a determination result including delay level and root cause classification is generated.

7. The logistics data processing method according to claim 6, characterized in that, The compliance determination dynamically calculates a theoretical outbound time threshold value according to multi-source timestamp data of goods entering and leaving a station, generates a compliance determination result by comparing an actual outbound time with the theoretical outbound time threshold value, and further includes the following: The determination result is fed back to a historical database, the prediction model parameters are optimized through an online learning mechanism, and a warning signal is triggered to a dispatching system to dynamically adjust a transportation plan.

8. A logistics data processing apparatus characterized by comprising: It includes: A data stream processing module for real-time collection of inbound and outbound timestamp data streams of a logistics node and real-time processing of the time data stream; A logistics delay event detection module for real-time detection of logistics delay events by constructing a dynamic CEP rule engine in Flink and deploying a CluStream streaming clustering algorithm; A distribution authority verification module for location verification through a geographic fence system and a dynamic permission attenuation model to grant distribution access rights; A logistics delay analysis module for building a multi-level reasoning network, calculating the contribution weight of each level factor to the delay when detecting delay anomalies, and generating an analysis report; A compliance determination module for dynamically calculating a theoretical outbound time threshold value according to multi-source timestamp data of goods entering and leaving a station, and generating a compliance determination result by comparing an actual outbound time with the theoretical outbound time threshold value.

9. A logistics data processing apparatus characterized by comprising: It includes a memory and at least one processor, and the memory stores computer readable instructions; The at least one processor invokes the computer readable instructions in the memory to perform the steps of the logistics data processing method according to any one of claims 1-7.

10. A computer-readable storage medium having stored thereon computer-readable instructions, wherein, The computer readable instructions are executed by the processor to implement the steps of the logistics data processing method according to any one of claims 1-7.

Images