Logistics transportation data optimization method and device, equipment and storage medium

Abstract

The invention relates to the technical field of logistics data processing, and discloses a logistics transportation data optimization method, which comprises the following steps: acquiring transportation vehicle data, acquiring vehicle positioning data through a multimode positioning terminal, calculating a container loading space utilization rate, and acquiring vehicle dynamic load data; the environment of the distribution center is sensed, a monitoring system is used for recognizing goods stacking violation behaviors of the distribution center and tracking goods, and temperature and humidity environment data of the distribution center are collected; performing standardized processing on multi-source data, cleaning abnormal data based on a rule engine, and constructing a main data management system; performing hybrid calculation and anomaly monitoring, calculating a core index, performing correlation analysis on an abnormal event by adopting a complex event processing technology, and monitoring a condition that data deviates from a threshold value through an anomaly detection model; and intelligently deciding and generating a scheme. According to the method, data version control and historical archiving are realized, accurate back calculation and deep analysis of core indexes can be realized, the decision is more scientific, and the refined management and control and efficiency of the whole transportation process are effectively improved.

Description

TECHNICAL FIELD

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

[0002] The current transportation data management system has two core problems: data collection fragmentation and calculation processing lag, which seriously restricts the digital decision-making ability of the whole transportation process.

[0003] Transportation vehicles and distribution center equipment have not yet built a unified data collection standard and Internet of Things sensing network. Transportation vehicle positioning relies on a single system, and vehicle cargo box loading status, temperature and humidity, and other transportation environment parameters cannot be transmitted in real time. The key data of the loading and unloading operation of the distribution center also lack accurate collection means. This data island phenomenon leads to fragmentation of transportation process information, making it difficult to form a complete transportation business view and decision basis.

[0004] In the face of massive transportation data, the existing system faces double challenges: on the one hand, real-time dynamic indicators such as vehicle in-transit abnormalities and loading and unloading delays have obvious lag, and transportation risks cannot be identified in a timely manner; on the other hand, the processing efficiency of historical data is low, and it is difficult to support accurate backtracking analysis and multidimensional mining of core indicators. These two aspects lead to slow response to transportation abnormalities, lack of data support for optimization strategies, and serious impact on transportation efficiency and cost control.

[0005] Therefore, the prior art still needs to be improved and developed. SUMMARY

[0006] The present application provides a logistics transportation data optimization method, device, equipment and storage medium, which is used for realizing data version control and historical archiving, and can realize accurate calculation and deep analysis of core indicators, form a complete business view and decision basis.

[0007] The first aspect of the present application provides a logistics transportation data optimization method, which comprises: Obtaining transportation vehicle data, collecting vehicle positioning data through a multi-mode positioning terminal, calculating cargo box loading space utilization, and collecting vehicle dynamic load data; Sensing the environment of the distribution center, using a monitoring system to identify illegal behavior of the distribution center and track the movement of the goods, and collecting temperature and humidity environment data of the distribution center; Standardizing processing of multi-source data, converting heterogeneous data by analyzing industrial communication protocols, cleaning abnormal data based on a rule engine, and building a master data management system; Hybrid computing and anomaly monitoring, calculating core indicators through a real-time stream processing framework, correlating and analyzing abnormal events using complex event processing technology, and monitoring data deviation from threshold values through an anomaly detection model; Intelligent decision-making and generation scheme, based on deep reinforcement learning algorithm training multi-objective optimization model, generating decision matrix, dynamically recommending transportation scheme.

[0008] Optionally, in the first implementation manner of the first aspect, the acquisition of the transportation vehicle data comprises: collecting vehicle positioning data through a multi-mode positioning terminal, calculating a loading space utilization rate of the container, and collecting dynamic load data of the vehicle, and the method comprises: The vehicle positioning data is collected through a multi-mode positioning terminal supporting multi-system positioning, and the multi-mode positioning terminal is directly connected with a vehicle electronic control unit through a preset communication interface; The loading space utilization rate of the container is calculated based on point cloud data generated by scanning a surface of the container of the vehicle through a three-dimensional laser scanning device; The dynamic load data of the vehicle is collected through a dynamic load sensor, and the dynamic load sensor dynamically compensates a load measurement result in combination with vehicle driving state data.

[0009] Optionally, in the second implementation manner of the first aspect, the sensing of the environment of the distribution center comprises: identifying a stacking irregular behavior of goods in the distribution center and tracking movement of the goods by using a monitoring system, and collecting temperature and humidity environment data in the distribution center, and the method comprises: The stacking state of the goods in the distribution center is identified in real time by using an intelligent image analysis system, and a stacking behavior not conforming to a preset rule is automatically detected; The spatial movement track of the goods in the distribution center is tracked by using a multi-modal positioning technology, and a change in a position of the goods is continuously monitored; A distributed environment sensing device is deployed in the distribution center, and the temperature and humidity environment data in the distribution center are collected.

[0010] Optionally, in the third implementation manner of the first aspect, the standardized processing of the multi-source data comprises: analyzing an industrial communication protocol to convert heterogeneous data, cleaning abnormal data based on a rule engine, and constructing a master data management system, and the method comprises: The multi-modal positioning technology is tracked by using a multi-modal positioning technology, and a change in a position of the goods is continuously monitored; Data anomalies are detected and cleaned based on a pre-defined rule engine, and data noise and errors are eliminated; A master data management platform is constructed, a unified data coding system is established, and core business data of logistics is centrally managed and traced.

[0011] Optionally, in the fourth implementation manner of the first aspect, the hybrid computing and anomaly monitoring comprise: calculating core indexes through a real-time stream processing framework, correlating and analyzing abnormal events by using a complex event processing technology, and monitoring a situation that data deviates from a threshold value through an anomaly detection model, and the method comprises: The logistics transportation data is dynamically calculated through a distributed real-time stream processing framework to generate the on-time rate and loading rate reflecting the transportation efficiency. The complex event processing technology is adopted to correlate and analyze the multi-source asynchronous events in the logistics transportation process to identify abnormal event patterns. The abnormal detection model constructed based on the machine learning algorithm monitors the logistics data features in real time to identify abnormal conditions deviating from the normal range.

[0012] Optionally, in the fifth implementation manner of the first aspect of the present application, the intelligent decision-making and generation scheme comprises the following steps of: The multi-objective optimization model is trained based on the reinforcement learning algorithm to learn the transportation decision-making strategy through historical logistics data; According to the trained multi-objective optimization model, a decision matrix containing the trade-off of multiple optimization objectives is generated; The transportation scheme is dynamically generated and recommended in combination with the real-time logistics data and the decision matrix.

[0013] Optionally, in the sixth implementation manner of the first aspect of the present application, the construction of the master data management platform comprises the following steps of: A centralized storage hub is established to access and clean the data of waybills, vehicles and network points; A data coding system is designed to assign an identifier containing business attributes to each type of business entity and map cross-platform data; A data bloodline map is constructed based on the coding system to record the whole-link conversion process of business data from the collection source to the application terminal, and support multi-dimensional backtracking analysis of the influence range of data changes.

[0014] The second aspect of the present application provides a logistics transportation data optimization device, which comprises: A transportation vehicle data acquisition module is configured to collect vehicle positioning data through a multi-mode positioning terminal, calculate the loading space utilization rate of a cargo box, and collect dynamic load data of the vehicle; A perception distribution center environment module is configured to use a monitoring system to identify illegal behaviors of goods stacking in a distribution center and track the movement of goods, and collect temperature and humidity environment data of the distribution center; A standardized processing multi-source data module is configured to parse industrial communication protocols to convert heterogeneous data, clean abnormal data based on a rule engine, and construct a master data management system; A hybrid computing and anomaly monitoring module is configured to calculate core indicators through a real-time stream processing framework, correlate and analyze abnormal events using complex event processing technology, and monitor data deviation from a threshold value through an anomaly detection model; The intelligent decision-making and scheme generation module is configured to train a multi-objective optimization model based on a deep reinforcement learning algorithm, generate a decision matrix, and dynamically recommend a transportation scheme.

[0015] Optionally, in the first implementation manner of the second aspect of the present application, the vehicle data acquisition module comprises: a first acquisition unit configured to acquire vehicle positioning data through a multi-mode positioning terminal supporting multi-system positioning, the multi-mode positioning terminal being directly connected to a vehicle electronic control unit through a preset communication interface; a first calculation unit configured to generate point cloud data based on scanning of a vehicle container surface by a three-dimensional laser scanning device and calculate a container loading space utilization rate based on a preset algorithm; and a second acquisition unit configured to acquire vehicle dynamic load data through a dynamic load sensor, the dynamic load sensor dynamically compensating load measurement results in combination with vehicle driving state data.

[0016] Optionally, in the second implementation manner of the second aspect of the present application, the environment perception module of the distribution center comprises: a first identification unit configured to use an intelligent image analysis system to perform real-time identification on a cargo stacking state in the distribution center and automatically detect stacking behaviors that do not conform to preset rules; a tracking unit configured to track a spatial movement trajectory of the cargo in the distribution center through multi-modal positioning technology and continuously monitor changes in the cargo position; and a third acquisition unit configured to deploy a distributed environment sensing device inside the distribution center and acquire internal temperature and humidity environment data of the distribution center.

[0017] Optionally, in the third implementation manner of the second aspect of the present application, the standardized processing of multi-source data module comprises: an analysis unit configured to analyze multiple industrial communication protocols through protocol conversion middleware, convert and uniformly access formats of heterogeneous logistics data; a cleaning unit configured to detect and clean data abnormalities based on a pre-defined rule engine, and eliminate data noise and errors; and a construction unit configured to construct a master data management platform, establish a unified data coding system, and centrally manage and trace core logistics business data.

[0018] Optionally, in the fourth implementation manner of the second aspect of the present application, the hybrid computing and anomaly monitoring module comprises: a second calculation unit configured to dynamically calculate logistics transportation data through a distributed real-time stream processing framework and generate on-time rate and loading rate reflecting transportation efficiency; a second identification unit configured to use complex event processing technology to perform correlation analysis on multi-source asynchronous events in the logistics transportation process and identify abnormal event patterns; and a third identification unit configured to use an anomaly detection model constructed based on a machine learning algorithm to monitor logistics data features in real time and identify abnormal conditions deviating from a normal range.

[0019] Optionally, in a fifth implementation form of the second aspect of the present application, the intelligent decision-making and generation scheme module comprises: a training unit configured to train a multi-objective optimization model based on a reinforcement learning algorithm to learn a transportation decision-making strategy through historical logistics data; a generation unit configured to generate a decision matrix containing a trade-off of multiple optimization objectives according to the trained multi-objective optimization model; and a recommendation unit configured to dynamically generate and recommend a transportation scheme in combination with real-time logistics data and the decision matrix.

[0020] The third aspect of the present application provides a logistics transportation data optimization 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 transportation data optimization 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 transportation data optimization method as described above.

[0022] In the technical solution provided by the present application, by integrating vehicle dynamic data, distribution center environment monitoring, multi-source data standardization, real-time anomaly detection and intelligent decision-making generation, the optimization of transportation efficiency and resource utilization is realized, data version control and historical archiving are realized, precise back calculation and deep analysis of core indicators are realized, data integration and anomaly detection accuracy are improved, decision-making is more scientific, system scalability and scene adaptability are high, and the fine management and control and efficiency of the whole logistics transportation process are effectively improved. BRIEF DESCRIPTION OF DRAWINGS

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

[0024] The present application provides a logistics transportation data optimization method, device, equipment and storage medium, which is used for deep analysis and processing of logistics business data, and improves the efficiency and accuracy of logistics business management.

[0025] The terms "first", "second", "third", "fourth" and the like in the description, claims, and drawings of the present application, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of these terms herein is to be construed as interchangeable in order to distinguish between the similar objects. It is also to be understood that the terms "comprising", "having", "including" and "containing" are to be construed as open-ended terms (i.e., meaning "including, but not limited to,") unless otherwise noted to have a closed- ended meaning. Thus, use of such terms is not intended to preclude the addition of further steps or elements to those described herein.

[0026] For the convenience of understanding, the specific flow of the embodiment of the present application is described below, please refer to Figure 1 The first embodiment of a logistics transportation data optimization method in the embodiment of the present application includes: S101, acquiring transportation vehicle data, collecting vehicle positioning data through a multi-mode positioning terminal, calculating the utilization rate of the loading space of the container, and collecting dynamic load data of the vehicle; S102, perceiving the environment of the distribution center, using a monitoring system to identify illegal behaviors of goods stacking in the distribution center and tracking the movement of goods, and collecting temperature and humidity environment data of the distribution center; S103, standardizing processing of multi-source data, analyzing industrial communication protocols to convert heterogeneous data, cleaning abnormal data based on a rule engine, and constructing a master data management system; S104, hybrid computing and anomaly monitoring, calculating core indicators through a real-time stream processing framework, using complex event processing technology for correlation analysis of abnormal events, and monitoring data deviation from threshold values through an anomaly detection model; S105, intelligent decision-making and scheme generation, training a multi-objective optimization model based on a deep reinforcement learning algorithm, generating a decision matrix, and dynamically recommending a transportation scheme.

[0027] The technical scheme provided by the application realizes optimization of transportation efficiency and resource utilization rate, realizes data version control and historical archiving, can accurately calculate and deeply analyze core indexes, improves data integration and abnormality monitoring accuracy, the decision is more scientific, the system expansion and scene adaptability are high, and the fine management and control and efficiency of the whole logistics transportation process are effectively improved.

[0028] Please refer to Figure 2 In the second embodiment of the logistics transportation data optimization method in the embodiment of the application, the transportation vehicle data is acquired, vehicle positioning data is collected through a multi-mode positioning terminal, a cargo box loading space utilization rate is calculated, and vehicle dynamic load data is collected, including: S201, vehicle positioning data is collected through a multi-mode positioning terminal supporting multi-system positioning, and the multi-mode positioning terminal is directly connected with a vehicle electronic control unit through a preset communication interface; S202, point cloud data is generated according to scanning of a vehicle cargo box surface by a three-dimensional laser scanning device, and a cargo box loading space utilization rate is calculated based on a preset algorithm; S203, vehicle dynamic load data is collected through a dynamic load sensor, and the dynamic load sensor dynamically compensates load measurement results in combination with vehicle driving state data.

[0029] The application effectively reduces positioning errors through multi-system positioning, is directly connected with a vehicle electronic control unit, synchronizes vehicle speed data in real time, avoids data delay or loss, effectively improves vehicle trajectory tracking accuracy, models a cargo box three-dimensional form in real time through high-density point cloud data, can identify cargo stacking gaps, improves space utilization rate, monitors overload risks in real time, triggers early warning and links vehicle speed limiting systems, avoids illegal fines and safety accidents, reduces operation costs through accurate data driving, and improves safety and service quality.

[0030] Please refer to Figure 3 In the third embodiment of the logistics transportation data optimization method in the embodiment of the application, the environment of the distribution center is perceived, a monitoring system is used to identify distribution center cargo stacking violation behaviors and track cargo movement, and distribution center temperature and humidity environment data is collected, including: S301, an intelligent image analysis system is used to identify a cargo stacking state in a distribution center in real time, and automatically detect stacking behaviors that do not conform to preset rules; S302, a multi-modal positioning technology is used to track a spatial movement trajectory of the cargo in the distribution center, and continuously monitor cargo position changes; S303, a distributed environment sensing device is deployed in the distribution center, and distribution center internal temperature and humidity environment data is collected.

[0031] The embodiment of the present application adopts a deep learning algorithm to identify the goods stacking state in real time, can detect illegal stacking behaviors, reduces the workload of manual inspection, and reduces the risk of goods collapse; combined with visual positioning technology, the tracking of the goods moving track is realized, and the blind area problem of traditional barcode scanning is solved; when the temperature and humidity exceed the standard, the environmental regulation equipment is automatically triggered, the goods storage conditions meet the standard, and the goods damage rate is effectively reduced.

[0032] Please refer to Figure 4 The fourth embodiment of the logistics transportation data optimization method in the embodiment of the present application, the standardized processing of multi-source data, the analysis of industrial communication protocol conversion heterogeneous data, the cleaning of abnormal data based on a rule engine and the construction of a master data management system, include: S401, a plurality of industrial communication protocols are analyzed through a protocol conversion middleware, and the formats of heterogeneous logistics data are converted and uniformly accessed; S402, based on a pre-defined rule engine, data anomalies are detected and cleaned, and data noise and errors are eliminated; S403, a master data management platform is constructed, a unified data coding system is established, and core business data of logistics is centrally managed and traced.

[0033] In the embodiment, heterogeneous data can be uniformly converted into a standard format, eliminating the data island problem caused by protocol differences; a unified data coding system is established to ensure that core business data of logistics is consistently referenced in multiple systems; the rule engine replaces manual data verification, effectively reducing labor costs and improving data processing speed.

[0034] In some embodiments, the construction of the master data management platform, the establishment of the unified data coding system, the centralized management and tracing of the core business data of logistics, include: A centralized storage hub is established to access and clean the data of the freight order, the vehicle and the network point; A data coding system is designed to assign an identifier containing business attributes to each type of business entity, and to map cross-platform data; Based on the coding system, a data bloodline map is constructed to record the whole-link conversion process of business data from the collection source to the application terminal, and support multi-dimensional backtracking analysis of the influence range of data changes.

[0035] Please refer to Figure 5 The fifth embodiment of the logistics transportation data optimization method in the embodiment of the present application, the mixed calculation and abnormal monitoring, the core indicators are calculated through a real-time stream processing framework, the abnormal events are analyzed by using a complex event processing technology, and the data deviation threshold is monitored by an abnormal detection model, including: S501, dynamically calculate the logistics transportation data through a distributed real-time stream processing framework, and generate on-time rate and loading rate reflecting transportation efficiency; S502, adopt complex event processing technology to correlate and analyze multi-source asynchronous events in the logistics transportation process, and identify abnormal event patterns; S503, an anomaly detection model constructed based on a machine learning algorithm monitors logistics data features in real time, and identifies abnormal conditions deviating from the normal range.

[0036] In this embodiment, the rule engine is used to correlate multi-source asynchronous events, which can identify complex abnormal patterns and shorten the response time from hours to minutes. The online learning mechanism is introduced, the model updates the threshold in real time according to new data, the abnormal detection rate is improved, the misjudgment rate is reduced, and the need for manual parameter adjustment is reduced. Real-time analysis and dynamic threshold adapt to complex logistics scenarios, which can effectively balance efficiency and risk control.

[0037] Referring to Figure 6 In the sixth embodiment of the logistics transportation data optimization method, the intelligent decision-making and generation scheme is based on a deep reinforcement learning algorithm to train a multi-objective optimization model, generate a decision matrix, and dynamically recommend a transportation scheme, including: S601, training a multi-objective optimization model based on a reinforcement learning algorithm, and learning transportation decision strategies through historical logistics data; S602, generating a decision matrix containing multiple optimization target trade-offs according to the trained multi-objective optimization model; S603, dynamically generating and recommending a transportation scheme in combination with real-time logistics data and the decision matrix.

[0038] In this embodiment, the scheme is dynamically adjusted in combination with real-time traffic, weather, and order data, and the response time is effectively shortened. The multi-objective optimization model constructed based on deep reinforcement learning can optimize cost, timeliness, and other targets simultaneously, avoiding the limitations of traditional single-objective optimization. The model can capture complex nonlinear relationships by learning strategies from historical logistics data, and can improve decision accuracy.

[0039] The logistics transportation data optimization method in the embodiments of the present application is described above, and the device in the embodiments of the present application is described below. Referring to Figure 7 The implementation of the logistics transportation data optimization device in the embodiments of the present application includes: The transportation vehicle data acquisition module 701 is used to collect vehicle positioning data through a multi-mode positioning terminal, calculate the utilization rate of the loading space of the cargo box, and collect vehicle dynamic load data; The perception distribution center environment module 702 is used to identify the illegal behavior of goods stacking in the distribution center and track the movement of goods using a monitoring system, and collect temperature and humidity environment data of the distribution center; The standardized processing multi-source data module 703 is used for parsing industrial communication protocol conversion heterogeneous data, cleaning abnormal data based on a rule engine, and constructing a master data management system. The hybrid computing and abnormality monitoring module 704 is used for calculating core indexes through a real-time stream processing framework, correlating and analyzing abnormal events by using a complex event processing technology, and monitoring data deviation from a threshold value through an abnormality detection model. The intelligent decision-making and scheme generation module 705 is used for training a multi-objective optimization model based on a deep reinforcement learning algorithm, generating a decision matrix, and dynamically recommending a transportation scheme.

[0040] In some embodiments, the transportation vehicle data acquisition module 701 comprises: The first acquisition unit 7011 is configured to acquire vehicle positioning data through a multi-mode positioning terminal supporting multi-system positioning, and the multi-mode positioning terminal is directly connected with a vehicle electronic control unit through a preset communication interface. The first calculation unit 7012 is configured to generate point cloud data based on scanning of a vehicle container surface by a three-dimensional laser scanning device, and calculate a container loading space utilization rate based on a preset algorithm. The second acquisition unit 7013 is configured to acquire vehicle dynamic load data through a dynamic load sensor, and the dynamic load sensor dynamically compensates load measurement results in combination with vehicle driving state data.

[0041] The present application effectively reduces positioning errors through multi-system positioning, is directly connected with a vehicle electronic control unit, synchronizes vehicle speed data in real time, avoids data delay or loss, effectively improves vehicle trajectory tracking accuracy, models a container three-dimensional form in real time through high-density point cloud data, can identify gaps in stacked goods, improves space utilization rate, monitors overload risks in real time, triggers early warning and links vehicle speed limiting systems, avoids illegal fines and safety accidents, reduces operating costs through precise data driving, and improves safety and service quality.

[0042] In some embodiments, the perception distribution center environment module 702 comprises: The first identification unit 7021 is configured to use an intelligent image analysis system to identify the stacking state of goods in the distribution center in real time, and automatically detect stacking behaviors that do not conform to preset rules. The tracking unit 7022 is configured to track the spatial movement trajectory of the goods in the distribution center by using multi-modal positioning technology, and continuously monitor changes in the position of the goods. The third acquisition unit 7023 is configured to deploy distributed environment sensing devices inside the distribution center, and acquire temperature and humidity environment data inside the distribution center.

[0043] The embodiment of the present application adopts a deep learning algorithm to identify the stacking state of goods in real time, can detect illegal stacking behaviors, reduces the workload of manual inspection, and reduces the risk of goods collapse; combined with visual positioning technology, the tracking of the moving trajectory of the goods is realized, and the blind area problem of traditional barcode scanning is solved; when the temperature and humidity exceed the standard, the environmental regulation equipment is automatically triggered, so as to ensure that the storage conditions of the goods meet the standard and effectively reduce the damage rate.

[0044] In some embodiments, the standardized processing multi-source data module 703 comprises: The parsing unit 7031 is configured to parse multiple industrial communication protocols through protocol conversion middleware, convert and uniformly access the formats of heterogeneous logistics data; The cleaning unit 7032 is configured to detect and clean data anomalies based on a pre-defined rule engine, and eliminate data noise and errors; The construction unit 7033 is configured to construct a master data management platform, establish a unified data coding system, and centrally manage and trace the logistics core business data.

[0045] In the embodiment, heterogeneous data can be uniformly converted into a standard format, eliminating the data island problem caused by protocol differences; a unified data coding system is established to ensure consistent reference of logistics core business data in multiple systems; the rule engine replaces manual data verification, effectively reducing labor costs and improving data processing speed.

[0046] In some embodiments, the hybrid computing and anomaly monitoring module 704 comprises: The second computing unit 7041 is configured to dynamically calculate logistics transportation data through a distributed real-time stream processing framework, and generate on-time rate and loading rate reflecting transportation efficiency; The second identification unit 7042 is configured to use complex event processing technology to correlate and analyze multiple source asynchronous events in the logistics transportation process, and identify abnormal event patterns; The third identification unit 7043 is configured to use an anomaly detection model constructed based on a machine learning algorithm to monitor logistics data features in real time, and identify abnormal conditions deviating from the normal range.

[0047] In the embodiment, multiple source asynchronous events are correlated based on the rule engine, which can identify complex abnormal patterns and shorten the response time from hours to minutes; an online learning mechanism is introduced, the model updates the threshold value in real time according to new data, the anomaly detection rate is improved, the misjudgment rate is reduced, and the demand for manual parameter adjustment is reduced; real-time analysis and dynamic threshold adapt to complex logistics scenarios, which can effectively balance efficiency and risk control.

[0048] In some embodiments, the intelligent decision-making and scheme generation module 705 comprises: The training unit 7051 is configured to train the multi-objective optimization model based on a reinforcement learning algorithm, and learn a transportation decision strategy through historical logistics data; The generation unit 7052 is configured to generate a decision matrix containing trade-offs of multiple optimization objectives according to the trained multi-objective optimization model; The recommendation unit 7053 is configured to dynamically generate and recommend a transportation scheme by combining real-time logistics data and the decision matrix.

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

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

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

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

[0053] The embodiment of the present application also provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium or a volatile computer readable storage medium, and the computer readable storage medium stores instructions, and the instructions make a computer execute the steps of the logistics transportation data optimization method when the instructions run on the computer.

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

[0055] The integrated unit, if realized 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 essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the various embodiments of the present application. The foregoing 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 program code storage media.

[0056] The foregoing and the foregoing embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing logistics transportation data, characterized in that, The logistics transportation data optimization method comprises: Obtain transportation vehicle data, collect vehicle positioning data through a multi-mode positioning terminal, calculate cargo box loading space utilization, and collect vehicle dynamic load data; Sense the environment of the distribution center, identify the distribution center cargo stacking violation behavior using a monitoring system and track the movement of the cargo, and collect the temperature and humidity environment data of the distribution center; Standardize the multi-source data, parse the industrial communication protocol, convert the heterogeneous data, clean the abnormal data based on the rule engine, and build a master data management system; Hybrid computing and anomaly monitoring, calculate core indicators through a real-time stream processing framework, use complex event processing technology for correlation analysis of abnormal events, and monitor data deviation from threshold values through an anomaly detection model; Intelligent decision-making and scheme generation, train a multi-objective optimization model based on a deep reinforcement learning algorithm, generate a decision matrix, and dynamically recommend a transportation scheme.

2. The method of claim 1, wherein, The method comprises: Collecting vehicle positioning data through a multi-mode positioning terminal supporting multiple system positioning, wherein the multi-mode positioning terminal is directly connected to a vehicle electronic control unit through a pre-set communication interface; Generating point cloud data based on a three-dimensional laser scanning device scanning the surface of the vehicle cargo box, and calculating the cargo box loading space utilization based on a pre-set algorithm; Collecting vehicle dynamic load data through a dynamic load sensor, wherein the dynamic load sensor combines vehicle driving state data to dynamically compensate the load measurement results.

3. The method of claim 2, wherein, The method comprises: Using an intelligent image analysis system to identify the cargo stacking state in the distribution center in real time, and automatically detecting stacking behaviors that do not conform to pre-set rules; Tracking the spatial movement trajectory of the cargo in the distribution center through multi-modal positioning technology, and continuously monitoring the change in the cargo position; Deploying a distributed environment sensing device inside the distribution center to collect the temperature and humidity environment data inside the distribution center.

4. The method of claim 3, wherein, The method comprises: Analyzing multiple industrial communication protocols through a protocol conversion middleware to convert and uniformly access the format of heterogeneous logistics data; Detecting and cleaning data anomalies based on a pre-defined rule engine to eliminate data noise and errors; Building a master data management platform, establishing a unified data coding system, and centrally managing and tracing the core business data of logistics.

5. The method of claim 1, wherein, The method comprises: Generating on-time rate and loading rate reflecting transportation efficiency by dynamically calculating logistics transportation data through a distributed real-time stream processing framework; Using complex event processing technology to correlate and analyze multiple source asynchronous events in the logistics transportation process to identify abnormal event patterns; An anomaly detection model based on a machine learning algorithm monitors logistics data features in real time and identifies anomalies deviating from the normal range.

6. The method of claim 5, wherein, The intelligent decision-making and generation scheme trains a multi-objective optimization model based on a deep reinforcement learning algorithm, generates a decision matrix, and dynamically recommends a transportation scheme, including: Training a multi-objective optimization model based on a reinforcement learning algorithm to learn transportation decision strategies from historical logistics data; Generating a decision matrix containing multiple optimization target trade-offs based on the trained multi-objective optimization model; Combining real-time logistics data and the decision matrix to dynamically generate and recommend a transportation scheme.

7. The method of claim 4, wherein, The construction of the master data management platform establishes a unified data coding system for centralized management and traceability of logistics core business data, including: Establishing a centralized storage hub to access and clean up manifest, vehicle, and network data; Designing a data coding system to assign identifiers containing business attributes to each type of business entity and mapping cross-platform data; Building a data bloodline map based on the coding system to record the full-link conversion process of business data from the source to the terminal, supporting multi-dimensional backtracking analysis of data change impact scope.

8. A logistics transportation data optimization apparatus characterized by, Including: A transportation vehicle data acquisition module for collecting vehicle positioning data through a multi-mode positioning terminal, calculating the utilization rate of the cargo box loading space, and collecting dynamic load data of the vehicle; A perception distribution center environment module for identifying distribution center cargo stacking violations and tracking cargo movement using a monitoring system, and collecting distribution center temperature and humidity environment data; A standardized processing of multi-source data module for parsing industrial communication protocols to convert heterogeneous data, cleaning abnormal data based on a rule engine, and constructing a master data management system; A hybrid computing and anomaly monitoring module for calculating core indicators through a real-time stream processing framework, using complex event processing technology for correlation analysis of abnormal events, and monitoring data deviation from the threshold value through an anomaly detection model; An intelligent decision-making and generation scheme module for training a multi-objective optimization model based on a deep reinforcement learning algorithm, generating a decision matrix, and dynamically recommending a transportation scheme.

9. A logistics transportation data optimization device characterized by, A memory and at least one processor, the memory having computer readable instructions stored therein; The at least one processor invokes the computer readable instructions in the memory to perform the steps of the logistics transportation data optimization method of any one of claims 1-7.

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

Images