An AI-based multi-dimensional logistics information supervision and early warning system and method

Abstract

The present application provides a multi-dimensional logistics information supervision and early warning system and method based on artificial intelligence, which relates to the technical field of logistics management. It obtains the logistics transportation track information in the logistics supply chain network in real time; conducts compensation inspection on the chain record of cargo right change to obtain the transportation attribute indicators in the logistics transportation process, and determines the track interaction period when the logistics object conducts track tracking on the transportation line according to the transportation attribute indicators; analyzes the risk characteristics of the transfer path information to obtain the logistics node risk data when the logistics object is in transportation, and determines the risk situation level in the logistics transportation process according to the logistics node risk data and the logistics transportation track information; warns the dynamic logistics supervision blind area in the logistics intermodal transportation process based on the track interaction period and the risk situation level. The present application can build an accurate risk situation assessment mechanism under the logistics information fusion supervision mode to improve the accuracy of logistics information supervision.

Description

Technical Field

[0001] The present application relates to the technical field of logistics management. More specifically, the present application relates to a multi-dimensional logistics information supervision and early warning system and method based on artificial intelligence. Background Art

[0002] Logistics management refers to the whole process of organizing, coordinating, controlling, and optimizing the material flow and transportation process in the supply chain, covering the storage, transportation, distribution, information transmission of goods, and the reasonable allocation of its related resources. With the acceleration of global trade and the rapid development of information technology, logistics management has gradually changed from traditional manual operations to modern management methods based on informatization and intelligence. The goal of logistics management is to improve the efficiency of the supply chain, reduce operating costs, ensure that goods arrive at the destination on time and safely, and through the effective supervision of each link, ensure the visualization, controllability, and accuracy of the entire logistics process.

[0003] However, in the existing multi-dimensional logistics information supervision and early warning methods and systems based on artificial intelligence, relying on static information flows, it is impossible to obtain information in distributed logistics nodes in real time, resulting in inaccurate and untimely monitoring of the status of goods in the logistics process, and failure to effectively integrate various heterogeneous data sources. Especially in the risk identification and risk situation assessment of dynamic logistics nodes, there are lags and insufficient accuracy, and it is unable to effectively respond to emergencies or complex risk changes in the logistics link, resulting in the failure to timely identify and warn the logistics supervision blind spots. Therefore, how to build an accurate risk situation assessment mechanism in the logistics information fusion supervision mode to improve the accuracy of logistics information supervision is a problem faced by the industry. Summary of the Invention

[0004] The present application provides a multi-dimensional logistics information supervision and early warning system and method based on artificial intelligence, which can build an accurate risk situation assessment mechanism in the logistics information fusion supervision mode to improve the accuracy of logistics information supervision.

[0005] In a first aspect, the present application provides a multi-dimensional logistics information supervision and early warning method based on artificial intelligence. The supervision and early warning method includes the following steps:

[0006] Collect the chain records of the change of goods ownership in the logistics supply chain network from distributed logistics nodes, and obtain the logistics transportation track information in the logistics supply chain network in real time;

[0007] Under the logistics information fusion supervision mode, conduct compensation inspection on the chain records of the change of goods ownership to obtain the transportation attribute indicators in the logistics transportation process, and determine the trajectory interaction period when the logistics object conducts trajectory tracking on the transportation line according to the transportation attribute indicators;

[0008] Obtain the transfer path information during the operation of the logistics network, analyze the risk characteristics of the transfer path information to obtain the logistics node risk data of the logistics object during transportation, and determine the risk situation level during the logistics transportation process according to the logistics node risk data and the logistics transportation trajectory information;

[0009] Based on the trajectory interaction period and the risk situation level, give an early warning of the dynamic logistics supervision blind area during the logistics intermodal transportation process.

[0010] In this embodiment, the chain record of cargo right change refers to a continuous data chain in the logistics supply chain network that records the time, location, participating parties and associated transaction information of the change of cargo ownership.

[0011] In this embodiment, the logistics transportation trajectory information represents the geographical location, timestamp, transportation tool and transportation status information passed by the logistics object during transportation.

[0012] In this embodiment, determining the trajectory interaction period when the logistics object performs trajectory tracking on the transportation route according to the transportation attribute index specifically includes:

[0013] Determine the spatio-temporal constraint model of the logistics object in the transportation network according to the transportation attribute index;

[0014] Output the tracking cooperation boundary of dynamic trajectory tracking from the spatio-temporal constraint model;

[0015] Determine the trajectory interaction period when the logistics object performs trajectory tracking on the transportation route from the tracking cooperation boundary.

[0016] In this embodiment, obtaining the transfer path information during the operation of the logistics network specifically includes:

[0017] Real-time collect the waybill status information between transportation nodes;

[0018] Determine the core transfer path in the logistics process according to the waybill status information;

[0019] Determine the transfer path information during the operation of the logistics network through the core transfer path.

[0020] In this embodiment, analyzing the risk characteristics of the transfer path information to obtain the logistics node risk data of the logistics object during transportation specifically includes:

[0021] Construct a spatio-temporal graph association model of the dynamic behavior of logistics nodes and historical risk events based on the transfer path information;

[0022] Output the risk coupling intensity of the logistics object during transportation through the spatio-temporal association model;

[0023] Determine the risk impact characteristics of each logistics node in the transportation network based on the risk coupling intensity;

[0024] Determine the logistics node risk data of the logistics object during transportation according to the risk impact characteristics.

[0025] In this embodiment, determining the risk situation level during the logistics transportation process based on the logistics node risk data and the logistics transportation trajectory information specifically includes:

[0026] Determine the risk association constraint of the logistics during the logistics transportation process according to the logistics node risk data;

[0027] Determine the abnormal coupling granularity of the logistics during the logistics transportation process through the logistics transportation trajectory information;

[0028] Determine the risk situation level during the logistics transportation process according to the risk association constraint and the abnormal coupling granularity.

[0029] In this embodiment, warning the dynamic logistics supervision blind area during the logistics intermodal transportation process based on the trajectory interaction period and the risk situation level specifically includes:

[0030] Determine the elastic monitoring quantity during the logistics intermodal transportation process according to the trajectory interaction period;

[0031] Determine the blind area risk exposure index in the dynamic logistics supervision blind area according to the risk situation level;

[0032] Match the elastic monitoring quantity and the blind area risk exposure index with the warning rules to generate a dynamically adjustable logistics supervision blind area warning map.

[0033] In this embodiment, under the logistics information fusion supervision mode, compensating and checking the chain record of the change of goods ownership to obtain the transportation attribute index during the logistics transportation process specifically includes:

[0034] Under the logistics information fusion supervision mode, determine the ownership transfer path of the logistics transportation link according to the chain record of the change of goods ownership;

[0035] Perform probability compensation on the missing goods ownership handover nodes in the chain record of the change of goods ownership to generate a complete logistics event sequence;

[0036] Perform feature aggregation on the logistics event sequence to obtain the risk entropy value information during the logistics transportation process;

[0037] Determine the transportation attribute index during the logistics transportation process from the risk entropy value information.

[0038] In a second aspect, the present application provides a multi-dimensional logistics information supervision and early warning system based on artificial intelligence for implementing a multi-dimensional logistics information supervision and early warning method based on artificial intelligence. The supervision and early warning system includes:

[0039] A data acquisition module for collecting the chain records of cargo right changes in the logistics supply chain network from distributed logistics nodes and real-time obtaining the logistics transportation trajectory information in the logistics supply chain network;

[0040] An association processing module for compensating and checking the chain records of cargo right changes in the logistics information fusion supervision mode to obtain the transportation attribute indicators in the logistics transportation process, and determining the trajectory interaction period when the logistics object performs trajectory tracking on the transportation line according to the transportation attribute indicators;

[0041] A risk determination module for obtaining the transfer path information during the operation of the logistics network, analyzing the risk characteristics of the transfer path information to obtain the logistics node risk data when the logistics object is in transportation, and determining the risk situation level in the logistics transportation process according to the logistics node risk data and the logistics transportation trajectory information;

[0042] A risk early warning module for warning the dynamic logistics supervision blind area in the logistics intermodal transportation process according to the trajectory interaction period and the risk situation level.

[0043] The technical solution provided by the embodiments disclosed in the present application has the following beneficial effects:

[0044] Collecting the chain records of cargo right changes in the logistics supply chain network from distributed logistics nodes and real-time obtaining the logistics transportation trajectory information in the logistics supply chain network; compensating and checking the chain records of cargo right changes in the logistics information fusion supervision mode to obtain the transportation attribute indicators in the logistics transportation process, and determining the trajectory interaction period when the logistics object performs trajectory tracking on the transportation line according to the transportation attribute indicators; obtaining the transfer path information during the operation of the logistics network, analyzing the risk characteristics of the transfer path information to obtain the logistics node risk data when the logistics object is in transportation, and determining the risk situation level in the logistics transportation process according to the logistics node risk data and the logistics transportation trajectory information; warning the dynamic logistics supervision blind area in the logistics intermodal transportation process according to the trajectory interaction period and the risk situation level.

[0045] It can be seen that in this application, multi-dimensional logistics information in each link of the logistics supply chain can be dynamically supervised and warned; among them, by collecting real-time the chain records of cargo right changes and logistics transportation trajectory information in distributed logistics nodes, the whole process can be made transparent and real-time monitored, reducing information lag, and improving the visualization and information circulation efficiency of the logistics supply chain; by compensating and checking the chain records of cargo right changes, the integrity and accuracy of logistics event data can be ensured, further calculating transportation attribute indicators, and dynamically monitoring according to the trajectory interaction period to provide real-time analysis of the transportation process; by obtaining and parsing the transfer path information in real time and dynamically evaluating in combination with the risk data of logistics nodes, the risk situation existing in the logistics transportation process can be accurately identified and predicted; by combining the trajectory interaction period and the risk situation level, the supervision blind spots in the logistics intermodal transportation process can be identified, and timely warnings can be given through the dynamic warning mechanism, reducing the exposure of blind spot risks in logistics management, improving the initiative and intelligent level of supervision, and ensuring the safety and efficiency in the logistics process.

[0046] In summary, the technical solution adopted in this application can construct an accurate risk situation assessment mechanism in the logistics information fusion supervision mode to improve the accuracy of logistics information supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0048] Figure 1 is a flowchart of a multi-dimensional logistics information supervision and warning method based on artificial intelligence provided by the present application;

[0049] Figure 2 is a schematic flow diagram for determining transportation attribute indicators provided by the present application;

[0050] Figure 3 is a schematic flow diagram for determining the risk data of logistics nodes provided by the present application;

[0051] Figure 4 is a module structure diagram of a multi-dimensional logistics information supervision and warning system based on artificial intelligence provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making any creative efforts belong to the scope of protection of the present application.

[0053] The embodiment of the present application provides a multi-dimensional logistics information supervision and early warning system and method based on artificial intelligence. The core is to collect the chain records of the change of goods ownership in the logistics supply chain network from distributed logistics nodes and obtain the logistics transportation track information in the logistics supply chain network in real time; in the logistics information fusion supervision mode, conduct compensation inspection on the chain records of the change of goods ownership to obtain the transportation attribute indicators in the logistics transportation process, and determine the trajectory interaction period when the logistics object conducts trajectory tracking on the transportation line according to the transportation attribute indicators; obtain the transfer path information in the operation process of the logistics network, analyze the risk characteristics of the transfer path information to obtain the logistics node risk data when the logistics object is transported, and determine the risk situation level in the logistics transportation process according to the logistics node risk data and the logistics transportation track information; give an early warning of the dynamic logistics supervision blind area in the logistics intermodal transportation process based on the trajectory interaction period and the risk situation level.

[0054] Embodiment 1. To better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners. Refer to Figure 1 As shown in the figure, which is an exemplary flowchart of the multi-dimensional logistics information supervision and early warning method based on artificial intelligence according to this embodiment of the present application, the supervision and early warning method includes the following steps:

[0055] In step S1, collect the chain records of the change of goods ownership in the logistics supply chain network from distributed logistics nodes and obtain the logistics transportation track information in the logistics supply chain network in real time.

[0056] Specifically, collecting the chain records of the change of goods ownership in the logistics supply chain network from distributed logistics nodes can be implemented in the following way: deploy blockchain nodes in each distributed logistics node, and use the smart contract of the blockchain to define the rules for the change of goods ownership. Whenever the ownership of the goods changes, such as warehouse receipt, agency transfer, terminal distribution, etc., the smart contract will automatically record the change information and synchronously update it on all blockchain nodes to ensure data consistency and immutability. At the same time, combine the Internet of Things sensing devices to automatically identify the goods status, upload it to the blockchain network, and read the chain records of the change of goods ownership from the blockchain network.

[0057] It should be noted that in this application, a distributed logistics node represents an independently operated storage, transportation, and distribution link in the logistics supply chain; a logistics supply chain network represents the flow relationship of goods between logistics nodes, including the connection and cooperation structure of transportation, warehousing, and distribution links; a chain record of cargo right change refers to a continuous data chain in the logistics supply chain network that records the time, location, participants, and associated transaction information of the change in the ownership of goods.

[0058] In addition, in specific implementation, the real-time acquisition of logistics transportation trajectory information in the logistics supply chain network can be achieved by the following methods, that is: install GPS terminals or Beidou positioning devices on transportation vehicles, containers, or the goods themselves to collect location information in real time, and send the data to the cloud server through 5G networks or LoRa Internet of Things communication protocols. Use a high-precision GIS geographic information system to analyze the location information, and combine electronic waybills to record key data such as transportation time and loading / unloading locations. When the goods pass through logistics transfer stations, warehouses, and distribution points, use RFID or NFC reading and writing devices to automatically collect logistics node information, and use this logistics node information as the logistics transportation trajectory information and synchronize it to the supply chain management system.

[0059] It should be noted that in this application, logistics transportation trajectory information represents the geographical location, timestamp, transportation tool, and transportation status information passed by a logistics object during transportation.

[0060] In step S2, in the logistics information fusion supervision mode, perform a compensatory inspection on the chain record of cargo right change to obtain the transportation attribute indicators during the logistics transportation process, and determine the trajectory interaction period when tracking the trajectory of the logistics object on the transportation route according to the transportation attribute indicators.

[0061] Preferably, in this embodiment, in the logistics information fusion supervision mode, perform a compensatory inspection on the chain record of cargo right change to obtain the transportation attribute indicators during the logistics transportation process, referring to Figure 2 As shown, this figure is a schematic flowchart of determining transportation attribute indicators in some embodiments of this application. The determination of transportation attribute indicators in this embodiment can be achieved by the following steps:

[0062] In step S21, in the logistics information fusion supervision mode, determine the ownership transfer path of the logistics transportation link according to the chain record of cargo right change;

[0063] In step S22, perform probability compensation on the missing cargo right handover nodes in the chain record of cargo right change to generate a complete logistics event sequence;

[0064] In step S23, perform feature aggregation on the logistics event sequence to obtain the risk entropy value information during the logistics transportation process;

[0065] In step S24, a transportation attribute index during the logistics transportation process is determined from the risk entropy value information.

[0066] When specifically implemented, first, a blockchain smart contract is used to parse the chain record of the change of goods ownership, extract the transfer relationship of goods ownership between logistics nodes, where the logistics nodes include warehouses, transfer centers, and distribution points. A goods ownership transfer path is constructed by sorting with timestamps, and this goods ownership transfer path is used as the ownership transfer path. Combining with the electronic waybill and RFID scanning logs, the integrity of the path is verified. If there is a discontinuous situation in a certain link, it is recorded as a potential missing node. Then, a Markov chain model or a hidden Markov model is adopted to calculate the most likely occurrence location and time of the missing node based on the historical goods ownership transfer pattern. For each possible compensation point, its occurrence probability is calculated, and the path with the maximum probability is selected as the compensation result. An anomaly detection algorithm is combined to identify possible miscompensated nodes, and cross-verification is performed through the historical records of the supply chain management system. The results of the cross-verification are sorted in chronological order to obtain a logistics event sequence. Then, the TF-IDF weighting method is used to extract features of the logistics events, analyze the importance of different types of events in the event sequence, where different types of events include delays and abnormal handovers. The uncertainty of different logistics paths is calculated based on Shannon entropy, and the calculated uncertainty of different logistics paths is used as the risk entropy value information during the logistics transportation process. Finally, based on the risk entropy value information, the average transportation time of the goods from the starting point to the ending point is calculated as the transportation timeliness; the timeliness fluctuation of the same transportation path is measured based on the standard deviation as the transportation stability; the proportion of abnormal handover events is statistically calculated as the abnormal handover rate; the proportion of high-entropy value logistics paths in the overall transportation chain is calculated as the high-risk path ratio. These results are subjected to multivariate regression analysis, where the multivariate regression analysis can adopt a linear regression algorithm, and the results of the multivariate regression analysis are used as the transportation attribute index during the logistics transportation process.

[0067] It should be noted that in this application, the logistics information fusion supervision mode means using multi-source data integration, intelligent analysis, and real-time monitoring technologies to achieve collaborative supervision of the entire logistics process, improving the transparency of the supply chain and the risk control ability; the ownership transfer path means the time-sequence chain of the transfer of the ownership of goods from one node to another during the logistics process; the goods ownership handover node refers to the specific time and location where the goods are handed over between different owners during the logistics process; the logistics event sequence refers to the logistics transportation events arranged in chronological order, including key nodes such as goods handover, transportation, and storage; the risk entropy value information refers to the measure of uncertainty during the logistics transportation process; the transportation attribute index means the information for measuring the important characteristics of the logistics transportation process.

[0068] In this embodiment, the trajectory interaction period when the logistics object performs trajectory tracking on the transportation route can be implemented according to the following steps based on the transportation attribute index:

[0069] Determine the spatio-temporal constraint model of the logistics object in the transportation network according to the transportation attribute indicators;

[0070] Output the tracking cooperation boundary for dynamic trajectory tracking from the spatio-temporal constraint model;

[0071] Determine the trajectory interaction period of the logistics object during trajectory tracking on the transportation line according to the tracking cooperation boundary.

[0072] In specific implementation, first, combine the transportation timeliness, transportation stability, and abnormal handover rate indicators to determine the spatio-temporal behavior pattern of the logistics object in the transportation network. Use Kalman filtering or particle filtering to smooth the historical trajectory, eliminate abnormal deviations, and obtain the steady-state trajectory distribution of the logistics object. Then, adopt the spatio-temporal path modeling method to calculate the possible stop points and path distribution of the logistics object on different transportation lines based on the GIS geographical information system, and form the spatio-temporal constraint model of the logistics object. Next, calculate the movement mode of the logistics object in the transportation network, where the movement mode includes acceleration, speed change points, and stop points. Use the density-based clustering method to identify different transportation states, where different transportation states include normal driving, stagnation, and abnormal deviation. Then, combine the characteristics of the transportation line and adopt the dynamic time warping technology to compare different transportation trajectories to determine the trajectory change boundary of the logistics object under similar transportation conditions. Also, according to the historical transportation data, use the Bayesian optimal interval estimation method to calculate the reasonable tracking time interval between different transportation nodes of the logistics object to form the tracking cooperation boundary. Finally, based on the tracking cooperation boundary, define the reasonable trajectory interaction period range under different transportation modes. Different transportation modes include high-speed driving, low-speed transportation, and warehousing stops. Then, adopt the Markov decision process to select the optimal trajectory tracking interval according to the current transportation state. For example, if the logistics object is in a high-speed transportation state, increase the acquisition interval; if it enters a high-risk area, shorten the acquisition interval. Use the adaptive sampling algorithm to dynamically adjust the sampling frequency in the GPS trajectory data stream to ensure the accuracy of trajectory tracking and the data transmission efficiency, and use the adjusted sampling frequency as the trajectory interaction period of the logistics object during trajectory tracking on the transportation line.

[0073] It should be noted that in this application, the spatio-temporal constraint model represents the constraint conditions for trajectory tracking based on the time and space characteristics of the logistics object; the tracking cooperation boundary represents the reasonable tracking frequency range of the logistics object in different transportation stages; the trajectory interaction period represents the time interval of the logistics object during trajectory tracking on the transportation line.

[0074] In step S3, obtain the transfer path information during the operation of the logistics network, analyze the risk characteristics of the transfer path information to obtain the logistics node risk data of the logistics object during transportation, and determine the risk situation level during the logistics transportation process according to the logistics node risk data and the logistics transportation trajectory information.

[0075] In this embodiment, the acquisition of the transfer path information during the operation of the logistics network can be implemented by the following steps:

[0076] Real-time collect the waybill status information between transportation nodes;

[0077] Determine the core transfer path in the logistics process according to the waybill status information;

[0078] Determine the transfer path information during the operation of the logistics network through the core transfer path.

[0079] Specifically, first, deploy IoT device GPS terminals on logistics transportation nodes, such as origin warehouses, transfer centers, and distribution stations, to obtain the real-time changes in the waybill status of goods. Use the Message Queuing Telemetry Transport (MQTT) protocol to transmit the collected waybill status data to the cloud logistics management platform. Combine blockchain evidence storage technology to ensure the immutability of the waybill status data, and use the blockchain evidence storage result as the waybill status information. Then, use a graph database to store the waybill transfer information. Regard the logistics nodes as vertices in the graph and the waybill transfer relationship as edges in the graph to construct a logistics network topology structure. Calculate the node traffic weights, and use the weighted shortest path algorithm to identify the high-frequency and high-weight transfer paths in the logistics network, and screen out the core transfer paths. Finally, based on the core transfer path, combine the historical waybill data, and use the K-Means clustering algorithm to classify similar transfer patterns to form the transfer path information of different logistics networks, that is, the transfer path information during the operation of the logistics network. Then, visualize the transfer path information through a Geographic Information System (GIS) to monitor the operation status of the logistics network in real time.

[0080] It should be noted that in this application, the waybill status information refers to the cargo status data recorded by different transportation nodes during the process of cargo flow; the core transfer path refers to the main circulation direction describing the cargo transfer; the transfer path information refers to the cargo circulation relationship between various transportation nodes in the logistics network.

[0081] Preferably, in this embodiment, to analyze the risk characteristics of the transfer path information to obtain the logistics node risk data of the logistics object during transportation, refer to Figure 3 As shown, this figure is a schematic flow chart for determining the logistics node risk data in some embodiments of this application. In this embodiment, the determination of the logistics node risk data can be implemented by the following steps:

[0082] In step S31, a spatio-temporal graph association model of the dynamic behavior of logistics nodes and historical risk events is constructed based on the transfer path information;

[0083] In step S32, the risk coupling intensity of the logistics object during transportation is output through the spatio-temporal association model;

[0084] In step S33, the risk impact characteristics of each logistics node in the transportation network are determined through the risk coupling intensity;

[0085] In step S34, the logistics node risk data of the logistics object during transportation is determined according to the risk impact characteristics.

[0086] In specific implementation, first, construct a spatio-temporal graph of logistics node risks. Use logistics nodes (warehouses, distribution centers, transportation hubs) as the vertices of the graph, cargo transfer paths (vehicle transportation routes, air freight routes, railway lines) as the edges of the graph, and historical risk events (cargo damage, delays, theft, policy restrictions) as the attribute information of the graph. Use a temporal graph neural network to learn the risk propagation pattern of logistics nodes. The training data sources include historical waybill data, logistics node operation data, and external environment data. Calculate the temporal risk impact weights of each logistics node using time weighting, and then combine the long short-term memory network to analyze the changing trend of historical risk events over time. Output the analysis results as a spatio-temporal graph association model of the dynamic behavior of logistics nodes and historical risk events. Next, calculate the spatio-temporal contact frequency between the logistics object and high-risk nodes. Use trajectory similarity calculation to analyze the matching degree between the current transportation path and the paths of historical high-risk events. Use the distance formula to calculate the spatial distance between the current trajectory of the logistics object and high-risk logistics nodes. Use time window analysis to count the residence time of the logistics object in high-risk areas; evaluate the coupling strength of the logistics object under different risk factors. Use a multi-factor weighted scoring model to comprehensively consider factors such as cargo type, transportation mode, and historical default records to quantify the risk exposure of the logistics object. Use Bayesian risk inference to calculate the risk accumulation value of the logistics object in the current transportation network, and use this risk accumulation value as the risk coupling strength of the logistics object during transportation. Then, calculate the risk propagation of logistics nodes. Use a random walk model to analyze the risk diffusion ability of high-risk nodes to surrounding nodes, and use flow-weighted influence analysis to calculate the dynamic risk impact generated by changes in logistics flow at the nodes; then evaluate the cumulative risk degree of logistics nodes. Combine the kernel density estimation method to analyze whether a logistics node has been a high-frequency risk occurrence location in history, and use an anomaly detection algorithm to identify abnormally high-risk logistics nodes. Use the evaluated cumulative risk degree of logistics nodes as the risk impact characteristics of each logistics node in the transportation network. Finally, use the analytic hierarchy process to calculate the risk level of the logistics object on a specific transportation route in combination with historical data. Use a risk index calculation model to assign a risk level to each logistics node according to the risk impact characteristics and quantify each risk level. Among them, the quantification process can use normalization processing, and use the quantification result as the logistics node risk data of the logistics object during transportation.

[0087] It should be noted that in this application, the spatio-temporal graph association model represents a risk assessment model of logistics nodes that includes time, space, and association relationships, which is constructed based on dynamic transportation behaviors and historical risk events in the logistics network and is used to identify high-risk nodes in the logistics network; historical risk events refer to the recorded risk events that occur during the logistics transportation process, such as damaged goods, delays, thefts, or transportation accidents; the risk coupling intensity represents the degree of association between the driving path of the logistics object during transportation and the risk logistics nodes; the risk impact feature represents the degree of influence of the logistics node on the risk level of the logistics object; the logistics node risk data refers to the risk impact data suffered by the logistics object when passing through different logistics nodes.

[0088] In this embodiment, determining the risk situation level during the logistics transportation process based on the logistics node risk data and the logistics transportation trajectory information can be achieved by the following steps:

[0089] Determine the risk association constraint of the logistics during the logistics transportation process according to the logistics node risk data;

[0090] Determine the abnormal coupling granularity of the logistics during the logistics transportation process through the logistics transportation trajectory information;

[0091] Determine the risk situation level during the logistics transportation process according to the risk association constraint and the abnormal coupling granularity.

[0092] In specific implementation, first, risk data is obtained from each logistics node, including historical risk events, influencing factors such as the traffic flow, weather, and public security of the node. Using graph algorithms, each node in the logistics network is taken as the vertex of the graph, and the cargo transfer path is taken as the edge to construct a logistics risk network. The association rule mining technology is used to mine the risk correlation degree between different logistics nodes, identify that the risk transfer relationship between nodes is relatively strong, and then Bayesian network analysis is adopted to calculate the conditional probability and influencing factors of each node in the risk transfer process. The conditional probability and influencing factors are used as the risk association constraints between nodes. Then, based on real-time collection of transportation trajectories such as GPS and sensor data, combined with the transportation modes, which include road, railway, and waterway, the actual path of the logistics object during transportation is obtained. Using spatio-temporal analysis technology, the trajectory data is matched with historical risk events to identify the contact frequency and residence time of the logistics object with high-risk nodes. The K-means clustering algorithm is used to cluster the transportation trajectories and risk nodes according to their contact intensity, divide areas with different risk levels, and combined with the dynamic time warping technology, calculate the spatio-temporal contact degree between the logistics object trajectory and high-risk nodes, evaluate the abnormal coupling granularity, and then based on the coupling relationship between the trajectory and risk nodes, use the risk index model to assign risk weights to each trajectory point, and finally obtain the abnormal coupling granularity, that is, the abnormal coupling granularity of the logistics during the logistics transportation process. Finally, the risk association between nodes, the abnormal coupling granularity, and the occurrence frequency of historical risk events are combined according to weights through the weighted scoring method, and fuzzy logic reasoning is used. Based on the input risk data, different thresholds are set for classification, so as to determine the overall risk situation during transportation; according to the weighted scoring results, the analytic hierarchy process is used to determine the risk situation of each logistics node, and the risk model is used to simulate different risk scenarios, where the risk scenarios include high-risk weather, emergencies, etc., to determine the situation level under different risk conditions, and finally the output risk situation level, that is, the risk situation level during the logistics transportation process.

[0093] It should be noted that in this application, the risk association constraint represents the mutual propagation path and restriction relationship of risks during transportation; the abnormal coupling granularity represents the association intensity and granularity between the logistics object trajectory and high-risk nodes or high-risk events during transportation; the risk situation level is an indicator of the overall risk level during the logistics transportation process.

[0094] In step S4, early warning is given to the dynamic logistics supervision blind area during the logistics intermodal transportation process according to the trajectory interaction period and the risk situation level.

[0095] In this embodiment, the early warning of the dynamic logistics supervision blind area during the logistics intermodal transportation process according to the trajectory interaction period and the risk situation level can be realized by the following steps:

[0096] Determine the elastic monitoring quantity in the process of logistics intermodal transportation according to the trajectory interaction period;

[0097] Determine the blind area risk exposure index in the dynamic logistics supervision blind area according to the risk situation level;

[0098] Match the elastic monitoring quantity and the blind area risk exposure index with the warning rules to generate a dynamically adjustable logistics supervision blind area warning map.

[0099] When specifically implemented, first, through the spatio-temporal data of the logistics transportation path, calculate the trajectory interaction period of each transportation node and path point, that is, the interaction frequency and residence duration of the logistics object with a certain node. Based on the frequency-time distribution model, analyze the trajectory interaction period of the logistics object and calibrate the time window of the key transportation nodes; adopt an adaptive monitoring method, dynamically adjust the distribution of monitoring points according to the change of the trajectory interaction period. For example, nodes with a shorter trajectory interaction period can be set with a higher monitoring frequency, and the monitoring frequency of nodes with a longer trajectory interaction period can be appropriately reduced. Then, combine K-means clustering to cluster different interaction periods to generate a dynamically adjusted monitoring area, and use the data in the monitoring area as the elastic monitoring quantity in the process of logistics intermodal transportation. Then, based on the risk situation level, combine the transportation flow and historical risk data in the blind area to evaluate the risk exposure index of the blind area. Use the exposure-sensitivity model to analyze the occurrence probability and influence range of potential risk events occurring in the blind area. For each blind area, establish the relationship between the risk exposure index and its external factors using linear regression to determine the high-risk exposure points of the blind area, and use the high-risk exposure points of the blind area as the blind area risk exposure index in the dynamic logistics supervision blind area. Finally, adopt a multi-dimensional matching algorithm, such as the weighted average method and the matching learning algorithm, to match the elastic monitoring quantity with the blind area risk exposure index, judge the risk exposure degree and monitoring requirements of each supervision blind area, use the dynamic threshold model to dynamically adjust the matching rule between the blind area risk exposure index and the elastic monitoring quantity according to the real-time monitoring data; use the data visualization tool to generate a real-time updated logistics supervision blind area warning map, dynamically display the risk status of each blind area, based on the real-time data stream, update the monitoring quantity and the risk exposure index in real time, and visualize them in the form of a map, and promptly display the potential high-risk areas and their monitoring status. Combine with the automatic alarm system. When the risk exposure index of a certain blind area exceeds the set threshold, automatically trigger an alarm and adjust the monitoring strategy.

[0100] It should be noted that in this application, the elastic monitoring quantity represents a dynamic monitoring index adapted to different logistics transportation conditions; the risk exposure index refers to the exposure degree of the risk area that is not effectively supervised during the logistics transportation process; the logistics supervision blind area warning map refers to a monitoring map that shows the risk situation and warning status of each supervision blind area in real time.

[0101] It can be seen that in this application, multi-dimensional logistics information in each link of the logistics supply chain can be dynamically supervised and warned; among them, by collecting the chain records of cargo right changes and logistics transportation track information in distributed logistics nodes in real time, the whole process can be made transparent and real-time monitored, reducing information lag and improving the visualization and information circulation efficiency of the logistics supply chain; by compensating and checking the chain records of cargo right changes, the integrity and accuracy of logistics event data can be ensured, further calculating the transportation attribute indicators, and dynamically monitoring according to the track interaction period to provide real-time transportation process analysis; by obtaining and parsing the transfer path information in real time and dynamically evaluating in combination with the risk data of logistics nodes, the risk situation existing in the logistics transportation process can be accurately identified and predicted; by combining the track interaction period and the risk situation level, the supervision blind areas in the logistics intermodal transportation process can be identified, and timely warnings can be given through the dynamic warning mechanism, reducing the exposure of blind area risks in logistics management, improving the initiative and intelligent level of supervision, and ensuring the safety and efficiency in the logistics process.

[0102] In summary, the technical solution adopted in this application can construct an accurate risk situation assessment mechanism under the logistics information fusion supervision mode to improve the accuracy of logistics information supervision.

[0103] Embodiment 2. This application provides a multi-dimensional logistics information supervision and warning system based on artificial intelligence. Refer to Figure 4 As shown in the figure, which is a module structure diagram of the multi-dimensional logistics information supervision and warning system based on artificial intelligence according to this embodiment of this application, the supervision and warning system includes:

[0104] A data acquisition module 100, which is used to collect the chain records of cargo right changes in the logistics supply chain network from distributed logistics nodes and obtain the logistics transportation track information in the logistics supply chain network in real time;

[0105] An association processing module 200, which is used to compensate and check the chain records of cargo right changes in the logistics information fusion supervision mode to obtain the transportation attribute indicators in the logistics transportation process, and determine the track interaction period when the logistics object conducts track tracking on the transportation line according to the transportation attribute indicators;

[0106] A risk determination module 300, which is used to obtain the transfer path information during the operation of the logistics network, analyze the risk characteristics of the transfer path information to obtain the risk data of logistics nodes when the logistics object is transporting, and determine the risk situation level in the logistics transportation process according to the logistics node risk data and the logistics transportation track information;

[0107] A risk warning module 400, which is used to warn the dynamic logistics supervision blind areas in the logistics intermodal transportation process according to the track interaction period and the risk situation level.

[0108] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0109] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0110] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of another identical element in the process, method, commodity or device comprising the element.

Claims

1. A multi-dimensional logistics information supervision and early warning method based on artificial intelligence, characterized in that The described supervision and early warning method includes the following steps: Collect the chain records of the change of cargo rights in the logistics supply chain network from distributed logistics nodes, and obtain the logistics transportation trajectory information in the logistics supply chain network in real time; Under the logistics information fusion supervision mode, conduct compensation inspection on the chain records of the change of cargo rights to obtain the transportation attribute indicators during the logistics transportation process, and determine the trajectory interaction period when the logistics object conducts trajectory tracking on the transportation line according to the transportation attribute indicators; Among them, the transportation attribute indicators represent the information for measuring the characteristics of the logistics transportation process; the trajectory interaction period represents the time interval for the logistics object to conduct trajectory tracking on the transportation line; Conducting compensation inspection on the chain records of the change of cargo rights to obtain the transportation attribute indicators during the logistics transportation process specifically includes: Under the logistics information fusion supervision mode, determine the ownership transfer path of the logistics transportation link according to the chain records of the change of cargo rights; Perform probability compensation on the missing cargo right handover nodes in the chain records of the change of cargo rights to generate a complete logistics event sequence; Conduct feature aggregation on the logistics event sequence to obtain the risk entropy value information during the logistics transportation process; Determine the transportation attribute indicators during the logistics transportation process from the risk entropy value information; Determining the trajectory interaction period when the logistics object conducts trajectory tracking on the transportation line according to the transportation attribute indicators specifically includes: Determine the spatio-temporal constraint model of the logistics object in the transportation network according to the transportation attribute indicators; Output the tracking cooperation boundary of dynamic trajectory tracking from the spatio-temporal constraint model; Determine the trajectory interaction period when the logistics object conducts trajectory tracking on the transportation line from the tracking cooperation boundary; Among them, the spatio-temporal constraint model represents the constraint conditions for trajectory tracking based on the time and space characteristics of the logistics object; the tracking cooperation boundary represents the reasonable tracking frequency range of the logistics object in different transportation stages; Obtain the transfer path information during the operation of the logistics network, conduct risk feature analysis on the transfer path information to obtain the logistics node risk data when the logistics object is in transportation, and determine the risk situation level during the logistics transportation process according to the logistics node risk data and the logistics transportation trajectory information; Among them, conducting risk feature analysis on the transfer path information to obtain the logistics node risk data when the logistics object is in transportation specifically includes: Construct a spatio-temporal graph association model of the dynamic behavior of logistics nodes and historical risk events based on the transfer path information; Output the risk coupling intensity of the logistics object during transportation through the spatio-temporal graph association model; Determine the risk impact characteristics of each logistics node in the transportation network through the risk coupling intensity; Determine the logistics node risk data when the logistics object is in transportation according to the risk impact characteristics; Among them, the risk coupling intensity represents the degree of association between the driving path of the logistics object during transportation and the risk logistics node; the risk impact characteristics represent the degree of influence of the logistics node on the risk level of the logistics object; Among them, determining the risk situation level during the logistics transportation process according to the logistics node risk data and the logistics transportation trajectory information specifically includes: Determine the risk association constraint of the logistics during the logistics transportation process according to the logistics node risk data; Determine the abnormal coupling granularity of the logistics during the logistics transportation process based on the logistics transportation trajectory information; Determine the risk situation level during the logistics transportation process according to the risk association constraint and the abnormal coupling granularity; Among them, the risk association constraint represents the mutual propagation path and restriction relationship of risks during the transportation process; the abnormal coupling granularity represents the association strength and granularity between the logistics object trajectory and high-risk nodes during the transportation process; Warn the dynamic logistics supervision blind area during the logistics intermodal transportation process based on the trajectory interaction period and the risk situation level; Among them, warning the dynamic logistics supervision blind area during the logistics intermodal transportation process based on the trajectory interaction period and the risk situation level specifically includes: Determine the elastic monitoring quantity during the logistics intermodal transportation process according to the trajectory interaction period; Determine the blind area risk exposure index in the dynamic logistics supervision blind area according to the risk situation level; Match the elastic monitoring quantity and the blind area risk exposure index with the warning rules to generate a dynamically adjustable logistics supervision blind area warning map; Among them, the elastic monitoring quantity represents the dynamic monitoring index adapted to different logistics transportation conditions.

2. The multi-dimensional logistics information supervision and early warning method based on artificial intelligence according to claim 1, wherein, The chain record of cargo right change refers to a continuous data chain in the logistics supply chain network that records the time, location, participating parties and related transaction information of the change of cargo ownership.

3. The multi-dimensional logistics information supervision and early warning method based on artificial intelligence according to claim 1, characterized in that, The logistics transportation trajectory information represents the geographical location, timestamp, transportation tool and transportation status information passed by the logistics object during the transportation process.

4. The multi-dimensional logistics information supervision and early warning method based on artificial intelligence according to claim 1, characterized in that Obtaining the transfer path information during the operation of the logistics network specifically includes: Real-time collect the waybill status information between transportation nodes; Determine the core transfer path in the logistics process according to the waybill status information; Determine the transfer path information during the operation of the logistics network through the core transfer path.

5. The multi-dimensional logistics information supervision and warning method based on artificial intelligence according to claim 1, characterized in that Under the logistics information fusion supervision mode, compensating and checking the chain record of cargo right change to obtain the transportation attribute index during the logistics transportation process specifically includes: Under the logistics information fusion supervision mode, determine the ownership transfer path of the logistics transportation link according to the chain record of cargo right change; Perform probability compensation on the missing cargo right handover nodes in the chain record of cargo right change to generate a complete logistics event sequence; Perform feature aggregation on the logistics event sequence to obtain the risk entropy value information during the logistics transportation process; Determine the transportation attribute index during the logistics transportation process from the risk entropy value information.

6. A multi-dimensional logistics information supervision and early warning system based on artificial intelligence, which is used to execute a multi-dimensional logistics information supervision and early warning method based on artificial intelligence as described in any one of claims 1 to 5, and is characterized in that, The supervision and warning system includes: A data acquisition module, used to collect the chain record of cargo right change in the logistics supply chain network from distributed logistics nodes, and to obtain the logistics transportation trajectory information in the logistics supply chain network in real time; An association processing module, used to compensate and check the chain record of cargo right change under the logistics information fusion supervision mode to obtain the transportation attribute index during the logistics transportation process, and to determine the trajectory interaction period when the logistics object performs trajectory tracking on the transportation line according to the transportation attribute index; A risk determination module, configured to obtain transfer path information during the operation of a logistics network, analyze risk characteristics of the transfer path information to obtain logistics node risk data of a logistics object during transportation, and determine a risk situation level during the logistics transportation process according to the logistics node risk data and the logistics transportation trajectory information; A risk warning module, configured to give a warning about a dynamic logistics supervision blind area during the logistics intermodal transportation process based on the trajectory interaction period and the risk situation level.

Images