Large-screen logistics data dynamic display method, system and device and storage medium

Abstract

The invention relates to the technical field of visualization, and particularly provides a large-screen logistics data dynamic display method, system and device and a storage medium, and the method comprises the steps: obtaining logistics track data, and carrying out the orthogonal decoupling of the logistics track data, and obtaining the value sets of a plurality of fields; based on the value set of each field, calculating an information entropy value of the field, and based on the information entropy value, determining a contribution degree of the field to a visual decision; performing anomaly analysis on the logistics track data to determine an abnormal event; and converting the corresponding value set into a display parameter of the three-dimensional logistics topology according to the contribution degree of the field to the visual decision, and marking an abnormal event in the three-dimensional logistics topology. According to the method, the global visualization effect of the key logistics indexes and the abnormal events is improved while the information redundancy is reduced, and efficient support is provided for real-time decision making.

Description

Technical Field

[0001] The present invention belongs to the field of visualization technology, and specifically relates to a large-screen logistics data dynamic display method, system, device and storage medium. Background Art

[0002] With the rapid development of the logistics industry, dynamic display technology for logistics data has become an important means to improve transportation efficiency and decision-making capabilities. Existing logistics data visualization methods mainly rely on the following two types of technologies: Two-dimensional visualization techniques: These techniques provide static or simple dynamic displays of logistics trajectories through line charts, heat maps, or geographic information systems (GIS). While these techniques can represent basic logistics routes, they are limited by the information-carrying capacity of a two-dimensional surface and struggle to effectively present the dynamic correlations of multi-dimensional data (such as time, transportation status, cargo type, and node load). This results in redundant data overwhelming critical decision-making information.

[0003] ‌3D-based Logistics Topology Technology‌: Some technologies attempt to construct logistics networks through 3D modeling, but they typically employ fixed field mapping rules (such as directly binding latitude and longitude coordinates or transport volume parameters) and lack intelligent filtering mechanisms for data fields. For example, existing methods fail to consider the varying contributions of different fields to decision-making, resulting in low-information fields occupying excessive visualization resources while high-value information is not highlighted. Summary of the Invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a large-screen logistics data dynamic display method, system, device and storage medium to solve the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a method for dynamically displaying logistics data on a large screen, comprising: Obtain logistics trajectory data and perform orthogonal decoupling on the logistics trajectory data to obtain the value sets of multiple fields; Based on the value set of each field, the information entropy value of the field is calculated, and the contribution of the field to the visualization decision is determined based on the information entropy value; Performing anomaly analysis on the logistics trajectory data to determine abnormal events; According to the contribution of the field to the visualization decision, the corresponding value set is converted into display parameters of the three-dimensional logistics topology, and abnormal events are marked in the three-dimensional logistics topology.

[0006] In an optional embodiment, logistics trajectory data is obtained and orthogonal decoupling is performed on the logistics trajectory data to obtain value sets for multiple fields, including: Acquiring logistics trajectory data, wherein the logistics trajectory data is three-dimensional data with temporal and spatial correlation; The Tucker tensor decomposition algorithm is used to perform orthogonal decoupling on the logistics trajectory data to obtain value sets of multiple fields, including timestamp, longitude and latitude, and cargo volume.

[0007] In an optional embodiment, based on the value set of each field, calculating the information entropy value of the field, and determining the contribution of the field to the visualization decision based on the information entropy value include: For each field value set, calculate its information entropy value:

[0008] in, represents the i-th field, X is The set of all values ​​of the field, is the distribution probability of the field value x in the set X, that is, , is the number of times the field value x appears in the field, and N is the total number of samples in the field; The information entropy value of each field is normalized to obtain the contribution coefficient.

[0009] In an optional embodiment, performing an abnormality analysis on the logistics trajectory data to determine abnormal events includes: The STL method is used to decompose the logistics trajectory data into trend terms, periodic terms and residual terms to capture the periodicity of the data; Establishing a dynamic threshold calculation model , where The mean of the trend term, is the residual standard deviation, k is the confidence coefficient; Generate time series dynamic threshold using dynamic threshold calculation model; Use spatial density clustering algorithm to identify the abnormal hotspot distribution characteristics of logistics trajectory data in space; Based on the abnormal hotspot distribution characteristics and the time series dynamic threshold, respectively generating corresponding dynamic thresholds for multiple abnormal hotspot distribution areas to obtain a dynamic threshold matrix; Calculating a dynamic threshold using the dynamic threshold calculation model, and determining abnormal data points from the logistics trajectory data based on the dynamic threshold; Construct a causal relationship inference model based on a graph neural network, input the abnormal data point into the causal relationship inference model, obtain the propagation chain of the abnormal data point, and save the abnormal data point and the corresponding propagation chain as an abnormal event.

[0010] In an optional embodiment, a causal relationship inference model based on a graph neural network is constructed, and the abnormal data point is input into the causal relationship inference model to obtain a propagation chain of the abnormal data point, including: Modeling logistics equipment failure chains and supply chain relationships as heterogeneous knowledge graphs; Quantify the propagation intensity of abnormal data points in the knowledge graph through the improved PageRank algorithm; A propagation chain of the abnormal data point is determined based on the propagation strength.

[0011] In an optional embodiment, the corresponding value set is converted into display parameters of the three-dimensional logistics topology according to the contribution of the field to the visualization decision, and abnormal events are marked in the three-dimensional logistics topology, including: For highly contributing latitude and longitude fields, their values ​​are directly mapped to spatial coordinates in the three-dimensional logistics topology. For cargo quantity fields, the volume or color depth of the cargo in the three-dimensional logistics topology is adjusted based on their values. For timestamp fields, the changing process of the logistics trajectory is displayed in the form of a dynamic timeline. In the three-dimensional logistics topology, identified abnormal events are marked and highlighted using different colors, icons or animation effects.

[0012] In an optional embodiment, the method further comprises: A large-screen spatial coordinate system is constructed based on the ORB-SLAM2 algorithm to synchronize gesture operations with the spatial posture of the three-dimensional data model.

[0013] In a second aspect, the present invention provides a large-screen logistics data dynamic display system, comprising: The first processing module is used to obtain logistics trajectory data and perform orthogonal decoupling on the logistics trajectory data to obtain a value set for each of the multiple fields; The second processing module is used to calculate the information entropy value of each field based on the value set of each field, and determine the contribution of the field to the visualization decision based on the information entropy value; A third processing module is used to perform anomaly analysis on the logistics trajectory data to determine abnormal events; The fourth processing module is used to convert the corresponding value set into display parameters of the three-dimensional logistics topology according to the contribution of the field to the visualization decision, and mark abnormal events in the three-dimensional logistics topology.

[0014] According to a third aspect, a device is provided, comprising: Memory, used to store large-screen logistics data dynamic display program; A processor is used to implement the steps of the large-screen logistics data dynamic display method provided in the first aspect when executing the large-screen logistics data dynamic display program.

[0015] In a fourth aspect, a computer-readable storage medium is provided, on which a large-screen logistics data dynamic display program is stored. When the large-screen logistics data dynamic display program is executed by a processor, the steps of the large-screen logistics data dynamic display method provided in the first aspect are implemented.

[0016] The beneficial effect of the present invention is that the large-screen logistics data dynamic display method, system, equipment and storage medium provided by the present invention extract a multi-field value set through orthogonal decoupling, and combine information entropy to quantify the contribution of the field to decision-making, thereby realizing dynamic screening of high-value data; further mapping the field contribution into three-dimensional topological parameters (such as node density, path width, color gradient), and synchronously marking the spatiotemporal impact domain of abnormal events, thereby reducing information redundancy while improving the global visualization effect of key logistics indicators and abnormal events, providing efficient support for real-time decision-making.

[0017] In addition, the present invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0020] Figure 2 FIG. 4 is a schematic block diagram of a system according to an embodiment of the present invention.

[0021] Figure 3 A schematic structural diagram of a device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0024] The large-screen logistics data dynamic display method provided by the embodiment of the present invention is executed by a computer device, and accordingly, the large-screen logistics data dynamic display system runs in the computer device.

[0025] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject can be a large-screen logistics data dynamic display system. According to different needs, the order of the steps in the flowchart can be changed, and some can be omitted.

[0026] like Figure 1 As shown, the method includes: S1. Obtain logistics trajectory data and perform orthogonal decoupling on the logistics trajectory data to obtain the value sets of multiple fields; S2. Based on the value set of each field, calculate the information entropy value of the field, and determine the contribution of the field to the visualization decision based on the information entropy value; S3. Perform anomaly analysis on the logistics trajectory data to determine abnormal events; S4. Convert the corresponding value set into display parameters of the three-dimensional logistics topology according to the contribution of the field to the visualization decision, and mark abnormal events in the three-dimensional logistics topology.

[0027] In an embodiment of the present invention, based on step S1, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0028] S101. Obtain logistics trajectory data, where the logistics trajectory data is three-dimensional data with spatiotemporal correlation.

[0029] Data source selection: Logistics trajectory data may come from multiple sources, such as GPS devices, logistics management systems, smart sensors, etc. These data sources will record the location, time, and quantity of goods in real time or periodically.

[0030] Data Collection: For GPS devices, you can use serial communication, Bluetooth, or a network interface to obtain the latitude and longitude information sent by the device, while also recording the current timestamp. Logistics management systems typically provide APIs that can be used to obtain relevant information about the shipment, including quantity, transit time, and location.

[0031] Data preprocessing: Data cleaning: Remove invalid data, such as incorrect longitude and latitude recorded when GPS signal is lost, abnormal timestamps, or data with negative cargo volume. Data format unification: Unify the data formats of different data sources, such as converting timestamps to a unified date and time format, and converting longitude and latitude to decimal format. Data organization: Organize the cleaned and unified data into a three-dimensional tensor. Assuming there are N time points, M geographical locations, and K cargo volume levels, then the three-dimensional tensor Represents logistics trajectory data. Among them, represents the observation value at the i-th time point, the j-th geographical location and the k-th cargo level.

[0032] S102. Use the Tucker tensor decomposition algorithm to perform orthogonal decoupling on the logistics trajectory data to obtain a value set of each of multiple fields, where the multiple fields include timestamp, longitude and latitude, and cargo volume.

[0033] Tucker tensor decomposition principle: Tucker decomposition decomposes a high-order tensor into the product of a core tensor and multiple factor matrices. For a three-dimensional tensor, Tucker decomposition is expressed as:

[0034] in, is the core tensor, 、 and is a factor matrix, × n Represents n-mode product.

[0035] Calculation of factor matrix and core tensor: Alternating least squares (ALS) is usually used to solve the factor matrix and core tensor in Tucker decomposition. The specific steps are as follows: Initialization: Randomly initialize the factor matrices A, B, and C.

[0036] Iterative updates: Update the core tensor g:

[0037] Update the factor matrix A:

[0038] Update factor matrix B:

[0039] Update the factor matrix C:

[0040] Among them, g + Represents the Moore-Penrose pseudoinverse of the core tensor g.

[0041] Convergence judgment: Repeat the above iterative steps until the objective function (such as reconstruction error) converges or the maximum number of iterations is reached.

[0042] Obtaining a value set: The column vectors of the factor matrices A, B, and C correspond to the value sets of timestamp, longitude and latitude, and cargo volume, respectively. For example, each column of A represents a time pattern, each column of B represents a geographic location pattern, and each column of C represents a cargo volume pattern.

[0043] In an embodiment of the present invention, based on step S2, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0044] S201. For each field value set, calculate its information entropy value:

[0045] in, represents the i-th field, X is The set of all values ​​of the field, is the distribution probability of the field value x in the set X, that is, , is the number of times the field value x appears in the field, and N is the total number of samples in the field; S202. Normalize the information entropy value of each field obtained by calculation to obtain a contribution coefficient.

[0046] This step can effectively identify key fields such as timestamps and geographic coordinates, reducing the workload of unnecessary data cleaning.

[0047] In an embodiment of the present invention, based on step S3, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0048] S301. Use the STL method to decompose the logistics trajectory data into trend terms, periodic terms and residual terms to capture the periodicity of the data.

[0049] Overview of STL method: STL (Seasonal-Trend decomposition using Loess) is a time series decomposition method based on local weighted regression (Loess), which can decompose the time series into trend terms, periodic terms and residual terms.

[0050] Data preparation: Ensure that the logistics trajectory data is a one-dimensional time series arranged in chronological order. If the data is multidimensional, you can first select appropriate indicators (such as cargo volume, number of transports, etc.) as needed to convert it into a one-dimensional series.

[0051] Parameter setting: You need to set the period length (such as days, weeks, months, etc.) and the Loess smoothing parameters (such as window size). These parameters will affect the decomposition effect.

[0052] Decomposition process: Perform preliminary smoothing on the data to remove noise.

[0053] The trend term is fitted by Loess regression to gradually approach the long-term trend of the data.

[0054] Subtracting the trend term from the original data yields a series containing periodic information and residuals.

[0055] Loess regression is used again to extract the periodic information and obtain the periodic term.

[0056] Finally, the trend term and cycle term are subtracted from the original data to obtain the residual term.

[0057] S302. Establishing a dynamic threshold calculation model , where The mean of the trend term, is the residual standard deviation, and k is the confidence coefficient.

[0058] S303. Generate a time series dynamic threshold using a dynamic threshold calculation model.

[0059] Sliding window method: You can use the sliding window method to calculate the dynamic threshold on the time series. For example, set a fixed-size window, and each time the window slides forward one time step, recalculate the mean of the trend item in the window. and the standard deviation of the residuals , and then obtain the dynamic threshold corresponding to the window.

[0060] Update frequency: Determine the update frequency of dynamic thresholds based on the frequency of data changes and business needs. If the data changes rapidly, you may need to update the threshold more frequently; if the data is relatively stable, you can appropriately reduce the update frequency.

[0061] S304. Use the spatial density clustering algorithm to identify the abnormal hotspot distribution characteristics of logistics trajectory data in space.

[0062] Spatial data preparation: Extract geographic location information (such as longitude and latitude) from logistics trajectory data to form a two-dimensional or three-dimensional spatial point set.

[0063] Select a spatial density clustering algorithm: Common algorithms include DBSCAN (Density - Based Spatial Clustering of Applications with Noise).

[0064] Parameter setting: For the DBSCAN algorithm, two key parameters need to be set: Neighborhood radius :Define the neighborhood range of a point, that is, the distance around a point is no more than All points of constitute its neighborhood.

[0065] Minimum number of points MinPts: A point’s neighborhood must contain at least MinPts points for it to be considered a core point.

[0066] Clustering process: Iterate over all points and count the number of points in the neighborhood of each point.

[0067] Mark core points, boundary points, and noise points. A core point is a point whose number of points in the neighborhood is not less than MinPts; a boundary point is a point whose number of points in the neighborhood is less than MinPts but is adjacent to a core point; a noise point is a point that is neither a core point nor a boundary point.

[0068] Merge adjacent core points and boundary points in their neighborhood into one cluster.

[0069] Abnormal hotspot identification: Noise points and some smaller clusters may be regarded as abnormal hotspots, which represent abnormal distribution areas of logistics trajectories in space.

[0070] S305. Based on the abnormal hotspot distribution characteristics and the time series dynamic threshold, respectively generate corresponding dynamic thresholds for multiple abnormal hotspot distribution areas to obtain a dynamic threshold matrix.

[0071] Region division: Based on the abnormal hotspot distribution characteristics identified in step S304, the logistics trajectory data is divided into multiple abnormal hotspot distribution regions.

[0072] Data screening: For each abnormal hotspot distribution area, filter out the logistics trajectory data within the area.

[0073] Threshold calculation: For the data in each region, repeat steps S301 to S303 to calculate the dynamic threshold corresponding to the region.

[0074] Matrix construction: The dynamic thresholds of each region are combined into a matrix, where each row of the matrix corresponds to the dynamic threshold of an abnormal hotspot distribution area.

[0075] S306. Calculate a dynamic threshold using the dynamic threshold calculation model, and determine abnormal data points from the logistics trajectory data based on the dynamic threshold.

[0076] Threshold matching: Compare each data point in the logistics trajectory data with the corresponding dynamic threshold. For time series data, use the time series dynamic threshold generated in step S303; for data in abnormal hotspot distribution areas, use the corresponding threshold in the dynamic threshold matrix obtained in step S305.

[0077] Abnormal judgment: If the value of a data point exceeds the corresponding dynamic threshold range (less than ( ) or greater than ( ), then the data point is marked as an abnormal data point.

[0078] S307. Construct a causal relationship inference model based on a graph neural network, input the abnormal data point into the causal relationship inference model, obtain the propagation chain of the abnormal data point, and save the abnormal data point and the corresponding propagation chain as an abnormal event.

[0079] (1) Model the logistics equipment failure chain and supply chain relationships as heterogeneous knowledge graphs.

[0080] Logistics equipment-related entities: Identify the various equipment entities involved in the logistics process, such as forklifts, conveyor belts, automated guided vehicles (AGVs), warehouse racks, etc. At the same time, it is also necessary to identify the attributes of the equipment, such as the equipment model, purchase date, and maintenance cycle.

[0081] Supply chain related entities: Identify the various node entities in the supply chain, including suppliers, manufacturers, distributors, retailers, etc., as well as the attributes of these entities, such as enterprise size, credit rating, geographical location, etc.

[0082] Abnormal data point entity: The abnormal data point determined in step S306 is also included in the knowledge graph as an entity, and its attributes may include the time of abnormal occurrence, abnormal type, abnormal value, etc.

[0083] Logistics equipment failure chain relationships: Identify the fault correlations between equipment. For example, a failure in one device may cause failures in other connected devices. This relationship can be represented as "fault propagation." Furthermore, there is a "maintenance" relationship between equipment and maintenance activities, and a "fault attribution" relationship between equipment and the cause of the failure.

[0084] Supply chain relationships: Sort out the business relationships between various nodes in the supply chain, such as the "supply" relationship between suppliers and manufacturers, the "sales" relationship between manufacturers and distributors, and the attributes of these relationships, such as transaction amount, transaction frequency, etc.

[0085] The relationship between abnormal data points and other entities: Determine the association between abnormal data points and logistics equipment and supply chain nodes. For example, abnormal data points may be caused by a failure of a logistics equipment or a business anomaly of a supply chain node.

[0086] Knowledge graph construction: Data storage: Choose a suitable graph database (such as Neo4j, JanusGraph, etc.) to store the knowledge graph. Store the identified entities and extracted relationships in the database as a graph, with each entity as a node and each relationship as an edge.

[0087] Data fusion: If the data comes from multiple different data sources, data fusion is required to resolve problems such as entity conflicts and relationship conflicts to ensure the consistency and accuracy of the knowledge graph.

[0088] (2) Quantify the propagation intensity of abnormal data points in the knowledge graph through the improved PageRank algorithm.

[0089] Improvements of the Improved PageRank Algorithm Edge weight considerations: In the knowledge graph, different relationships (edges) may have different degrees of influence on the propagation of anomalies. Therefore, in the improved PageRank algorithm, each edge needs to be assigned a weight w uv , represents the abnormal propagation weight from node v to node u.

[0090] Abnormal starting point setting: take the abnormal data point as the starting point of abnormal propagation, initialize the PageRank value of these nodes to 1, and the PageRank value of other nodes to 0.

[0091] Improved PageRank algorithm formula:

[0092] Among them, O v is the node set pointed to by node v, w uv is the weight of the edge from node v to node u.

[0093] Iterative calculation: Initialize the PageRank values ​​of all nodes, set the PageRank value of abnormal data points to 1, and set the PageRank value of other nodes to 0.

[0094] The PageRank value is calculated repeatedly until convergence (that is, the change in PageRank value between two iterations is less than a certain threshold).

[0095] (3) Determine the propagation chain of the abnormal data point based on the propagation strength.

[0096] Propagation path search: Starting from the abnormal data point, we search for possible propagation paths based on the propagation strength of the edges and nodes in the knowledge graph. We can use the breadth-first search (BFS) or depth-first search (DFS) algorithm.

[0097] During the search process, edges with greater propagation strength are preferentially selected for expansion to ensure that the propagation path found is the most likely abnormal propagation path.

[0098] Transmission chain determined: When a node with a propagation strength lower than a certain threshold is found, the search is stopped and the path from the abnormal data point to the node is regarded as an abnormal propagation chain.

[0099] All found propagation paths are screened and merged to remove duplicate and unreasonable paths, and finally the propagation chain of abnormal data points is determined.

[0100] Visualization of the transmission chain: Display the identified anomaly propagation chain in a visual manner, for example, using graph visualization tools (such as Gephi, Graphviz, etc.), so that users can intuitively understand the propagation process of abnormal data points.

[0101] In an embodiment of the present invention, based on step S4, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0102] S401. For highly contributing latitude and longitude fields, their values ​​are directly mapped to spatial coordinates in the three-dimensional logistics topology. For cargo quantity fields, the volume or color depth of the cargo in the three-dimensional logistics topology is adjusted based on the value. For timestamp fields, the changing process of the logistics trajectory is displayed in the form of a dynamic timeline. S402. In the three-dimensional logistics topology, the identified abnormal events are marked, and different colors, icons, or animation effects are used to highlight the abnormal events.

[0103] To overcome the limitations of two-dimensional interaction, we developed a multimodal augmented reality presentation technology. Based on the ORB-SLAM2 algorithm, we constructed a large-screen spatial coordinate system, synchronizing gestures with the spatial pose of the 3D data model. We also employed a raycasting optimization algorithm to implement drill-down functionality for chart details, allowing users to trigger multi-level LOD (Levels of Detail) rendering with a two-finger pinch gesture, with response latency of less than 0.2 seconds.

[0104] To ensure the real-time synchronization of cross-platform data, a priority-driven message distribution mechanism is proposed, an event urgency assessment model is built, and the data transmission queue is dynamically adjusted: Priority=0.7Se+0.3Ug Where Se is the severity of the event and Ug is the urgency of the handling, so that the synchronization delay of key events such as production line shutdown is stabilized within 0.1 seconds.

[0105] To address the multi-terminal data consistency issue in network interruption scenarios, this system develops a collaborative caching strategy based on an improved CRDT: a hybrid logical clock (HLC) and vector clock are used to jointly mark operation timing to ensure the causal consistency of operation logs of nodes such as mobile terminals and AR devices; a conflict resolution strategy that prioritizes business rules is designed. When an inventory value conflict is detected, the data version that meets the non-negative constraints and has the latest timestamp is automatically selected; an incremental compression algorithm for operation logs is simultaneously developed. The differential coding technology is used to reduce the volume of cached data during network interruptions by 70%, supporting complete data recovery after 72 hours of offline operations.

[0106] In some embodiments, the large-screen logistics data dynamic display system may include multiple functional modules composed of computer program segments. The computer program of each program segment in the large-screen logistics data dynamic display system may be stored in the memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) The function of dynamically displaying logistics data on the large screen.

[0107] In this embodiment, the large-screen logistics data dynamic display system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0108] The first processing module is used to obtain logistics trajectory data and perform orthogonal decoupling on the logistics trajectory data to obtain a value set for each of the multiple fields; The second processing module is used to calculate the information entropy value of each field based on the value set of each field, and determine the contribution of the field to the visualization decision based on the information entropy value; A third processing module is used to perform anomaly analysis on the logistics trajectory data to determine abnormal events; The fourth processing module is used to convert the corresponding value set into display parameters of the three-dimensional logistics topology according to the contribution of the field to the visualization decision, and mark abnormal events in the three-dimensional logistics topology.

[0109] Figure 3The large-screen logistics data dynamic display method provided for the embodiment of the present application can be applied to the device. Those skilled in the art will understand that the device structure involved in the embodiment of the present invention does not constitute a limitation on the device, and the device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In the embodiment of the present invention, the device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0110] The device 300 may include a processor 310, a memory 320, and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention. The server structure may be a bus structure or a star structure, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0111] The memory 320 can be used to store execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the device 300 can perform some or all of the steps in the above-described method embodiments.

[0112] The processor 310 is the control center of the storage device, which uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and / or processes data by running or executing software programs and / or modules stored in the memory 320, and calling data stored in the memory. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In an embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0113] The communication unit 330 is configured to establish a communication channel so that the storage device can communicate with other devices, receive user data sent by other devices, or send user data to other devices.

[0114] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program that, when executed, may include some or all of the steps of each embodiment provided herein. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0115] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software and a necessary general-purpose hardware platform. Based on this understanding, the technical solutions in the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, among other media capable of storing program code, and includes instructions for causing a computer device (which can be a personal computer, a server, or a second device, a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention.

[0116] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

[0117] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, and can be electrical, mechanical or other forms.

[0118] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0119] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0120] Although the present invention has been described in detail with reference to the accompanying drawings and in conjunction with preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, persons of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and such modifications or substitutions shall be within the scope of the present invention. Any changes or substitutions that can be easily conceived by persons skilled in the art within the technical scope disclosed in the present invention shall be within the scope of protection of the present invention.

Claims

1. A large-screen logistics data dynamic display method, characterized in that: include: Obtain logistics trajectory data and perform orthogonal decoupling on the logistics trajectory data to obtain the value sets of multiple fields; Based on the value set of each field, the information entropy value of the field is calculated, and the contribution of the field to the visualization decision is determined based on the information entropy value; Performing anomaly analysis on the logistics trajectory data to determine abnormal events; According to the contribution of the field to the visualization decision, the corresponding value set is converted into display parameters of the three-dimensional logistics topology, and abnormal events are marked in the three-dimensional logistics topology.

2. The method according to claim 1, characterized in that Obtain logistics trajectory data and perform orthogonal decoupling on the logistics trajectory data to obtain the value sets of multiple fields, including: Acquiring logistics trajectory data, wherein the logistics trajectory data is three-dimensional data with temporal and spatial correlation; The Tucker tensor decomposition algorithm is used to perform orthogonal decoupling on the logistics trajectory data to obtain value sets of multiple fields, including timestamp, longitude and latitude, and cargo volume.

3. The method according to claim 1, characterized in that Based on the value set of each field, the information entropy value of the field is calculated, and the contribution of the field to the visualization decision is determined based on the information entropy value, including: For each field value set, calculate its information entropy value: in, represents the i-th field, X is The set of all values ​​of the field, is the distribution probability of the field value x in the set X, that is, , is the number of times the field value x appears in the field, and N is the total number of samples in the field; The information entropy value of each field is normalized to obtain the contribution coefficient.

4. The method according to claim 1, wherein Perform anomaly analysis on the logistics trajectory data to determine abnormal events, including: The STL method is used to decompose the logistics trajectory data into trend terms, periodic terms and residual terms to capture the periodicity of the data; Establishing a dynamic threshold calculation model , where The mean of the trend term, is the residual standard deviation, k is the confidence coefficient; Generate time series dynamic threshold using dynamic threshold calculation model; Use spatial density clustering algorithm to identify the abnormal hotspot distribution characteristics of logistics trajectory data in space; Based on the abnormal hotspot distribution characteristics and the time series dynamic threshold, respectively generating corresponding dynamic thresholds for multiple abnormal hotspot distribution areas to obtain a dynamic threshold matrix; Calculating a dynamic threshold using the dynamic threshold calculation model, and determining abnormal data points from the logistics trajectory data based on the dynamic threshold; Construct a causal relationship inference model based on a graph neural network, input the abnormal data point into the causal relationship inference model, obtain the propagation chain of the abnormal data point, and save the abnormal data point and the corresponding propagation chain as an abnormal event.

5. The method according to claim 4, characterized in that Constructing a causal relationship inference model based on a graph neural network, inputting the abnormal data point into the causal relationship inference model, and obtaining a propagation chain of the abnormal data point, including: Modeling logistics equipment failure chains and supply chain relationships as heterogeneous knowledge graphs; Quantify the propagation intensity of abnormal data points in the knowledge graph through the improved PageRank algorithm; A propagation chain of the abnormal data point is determined based on the propagation strength.

6. The method according to claim 1, characterized in that According to the contribution of the field to the visualization decision, the corresponding value set is converted into display parameters of the three-dimensional logistics topology, and abnormal events are marked in the three-dimensional logistics topology, including: For highly contributing latitude and longitude fields, their values ​​are directly mapped to spatial coordinates in the three-dimensional logistics topology. For cargo quantity fields, the volume or color depth of the cargo in the three-dimensional logistics topology is adjusted based on their values. For timestamp fields, the changing process of the logistics trajectory is displayed in the form of a dynamic timeline. In the three-dimensional logistics topology, identified abnormal events are marked and highlighted using different colors, icons or animation effects.

7. The method according to claim 1, characterized in that The method further comprises: A large-screen spatial coordinate system is constructed based on the ORB-SLAM2 algorithm to synchronize gesture operations with the spatial posture of the three-dimensional data model.

8. A large-screen logistics data dynamic display system, characterized in that: include: The first processing module is used to obtain logistics trajectory data and perform orthogonal decoupling on the logistics trajectory data to obtain a value set for each of the multiple fields; The second processing module is used to calculate the information entropy value of each field based on the value set of each field, and determine the contribution of the field to the visualization decision based on the information entropy value; A third processing module is used to perform anomaly analysis on the logistics trajectory data to determine abnormal events; The fourth processing module is used to convert the corresponding value set into display parameters of the three-dimensional logistics topology according to the contribution of the field to the visualization decision, and mark abnormal events in the three-dimensional logistics topology.

9. A device, characterized in that include: Memory, used to store large-screen logistics data dynamic display program; A processor is used to implement the steps of the large-screen logistics data dynamic display method as described in any one of claims 1 to 7 when executing the large-screen logistics data dynamic display program.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a large-screen logistics data dynamic display program, and when the large-screen logistics data dynamic display program is executed by the processor, the steps of the large-screen logistics data dynamic display method according to any one of claims 1 to 7 are implemented.

Images