Trajectory tracking method, system and device based on knowledge graph and medium

Abstract

The invention discloses a trajectory tracking method, system and device based on a knowledge graph, and a medium. The trajectory tracking method comprises the following steps: constructing a trajectory knowledge graph; obtaining original trajectory data, and preprocessing the original trajectory data to obtain trajectory data; associating the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relation graph; performing trajectory tracking on the original trajectory data according to the trajectory knowledge relation graph to obtain a trajectory tracking result; and graphically displaying the trajectory data, the trajectory knowledge relation graph and the trajectory tracking result through a preset visual interface. According to the method, the trajectory data and the trajectory knowledge graph technology are combined, the semantic understanding ability of the trajectory data can be improved, more accurate and more efficient trajectory analysis can be achieved, a user can visually know the spatial and temporal distribution, the motion law and the mutual relation of the trajectory, the user experience is improved, and the method can be widely applied to the technical field of trajectory tracking.

Description

Technical Field

[0001] The present application relates to the field of trajectory tracking technology, and in particular to a trajectory tracking method, system, device and medium based on a knowledge graph. Background Art

[0002] With the explosive growth of Internet information data and the rapid development of big data technology, trajectory tracking technology has been increasingly used in urban management, public safety, intelligent transportation and other fields. Intuitive and interactive relationship networks and map space visualization systems have also become the key to people's rapid understanding of information. However, trajectory tracking methods in previous technologies usually rely on simple spatiotemporal data analysis, lack semantic understanding of trajectory-related entities and events, and find it difficult to discover the complex relationships and patterns hidden in trajectory data, limiting the depth and breadth of data analysis. On the other hand, the trajectory data display methods in previous technologies, such as tables and text reports, are difficult to intuitively display the spatiotemporal distribution, movement patterns and mutual relationships of trajectories, which brings inconvenience to data analysis and decision making. Summary of the invention

[0003] In order to solve the above technical problems, the purpose of the present invention is to provide a knowledge graph-based trajectory tracking method, system, device and medium with high accuracy and efficiency.

[0004] To achieve the above purpose, one aspect of an embodiment of the present application proposes a trajectory tracking method based on a knowledge graph, comprising the following steps:

[0005] Construct trajectory knowledge graph;

[0006] Acquire original trajectory data, and preprocess the original trajectory data to obtain trajectory data;

[0007] Associating the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph;

[0008] Performing trajectory tracking on the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result;

[0009] The trajectory data, the trajectory knowledge relationship diagram, and the trajectory tracking result are graphically displayed through a preset visualization interface.

[0010] In some embodiments, constructing a trajectory knowledge graph specifically includes:

[0011] Acquire trajectory data samples, perform entity recognition on the trajectory data samples, and obtain multiple types of entities;

[0012] Extracting relationships between the entities according to the trajectory data samples to obtain multiple relationship structures;

[0013] The trajectory knowledge graph is constructed with each of the entities as a node and each of the relationship structures as an edge.

[0014] In some embodiments, the preprocessing of the original trajectory data to obtain trajectory data specifically includes:

[0015] Eliminate outliers from the original trajectory data to obtain first trajectory data;

[0016] Performing standardization processing on the first trajectory data to obtain second trajectory data;

[0017] Performing semantic annotation on the second trajectory data to obtain the trajectory data;

[0018] The standardization process includes time standardization, space standardization and data format standardization.

[0019] In some embodiments, the trajectory data includes entity information and attribute information, and the semantic annotation of the second trajectory data to obtain the trajectory data specifically includes:

[0020] Segmenting the second trajectory data according to a preset time interval to obtain a plurality of trajectory segments;

[0021] Performing entity labeling on each of the trajectory segments to obtain the entity information;

[0022] Attributes are labeled on each of the trajectory segments to obtain the attribute information.

[0023] In some embodiments, associating the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph specifically includes:

[0024] Matching the entity information with entities in the trajectory knowledge graph to obtain an entity matching result;

[0025] The relationship structure in the trajectory knowledge graph is updated according to the entity matching result and the attribute information to obtain the trajectory knowledge relationship graph.

[0026] In some embodiments, performing trajectory tracking on the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result specifically includes:

[0027] Determine semantic retrieval information and spatiotemporal retrieval information;

[0028] Performing trajectory retrieval on the original trajectory data according to the semantic retrieval information and the spatiotemporal retrieval information through the trajectory knowledge relationship graph to obtain a trajectory retrieval result;

[0029] The trajectory retrieval result is tracked by using the trajectory knowledge relationship graph to obtain the trajectory tracking result.

[0030] In some embodiments, the trajectory tracking result includes a first trajectory tracking result, a second trajectory tracking result, and a third trajectory tracking result, and the trajectory tracking of the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the trajectory tracking result specifically includes:

[0031] Performing trajectory pattern analysis on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the first trajectory tracking result;

[0032] Performing abnormal behavior analysis on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the second trajectory tracking result;

[0033] The trajectory trend is predicted on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the third trajectory tracking result.

[0034] To achieve the above purpose, another aspect of the embodiment of the present application proposes a trajectory tracking system based on a knowledge graph, including:

[0035] Graph construction module, used to build trajectory knowledge graph;

[0036] A data preprocessing module, used to obtain original trajectory data, and preprocess the original trajectory data to obtain trajectory data;

[0037] A trajectory graph fusion module, used to associate the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph;

[0038] A trajectory tracking module, used to track the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result;

[0039] The data visualization module is used to graphically display the trajectory data, the trajectory knowledge relationship diagram and the trajectory tracking result through a preset visualization interface.

[0040] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the trajectory tracking method based on the knowledge graph as described above is implemented.

[0041] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the trajectory tracking method based on the knowledge graph as described above.

[0042] The beneficial effects of the present invention are as follows: the trajectory tracking method, system, device and medium based on the knowledge graph of the present invention first constructs a trajectory knowledge graph, then obtains the original trajectory data, preprocesses the original trajectory data to obtain trajectory data, and then associates the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph, and finally tracks the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result, and graphically displays the trajectory data, trajectory knowledge relationship graph and trajectory tracking result through a preset visualization interface. On the one hand, the present invention uses the knowledge graph to track trajectories, which can effectively represent the complex relationships between trajectory data entities, improve the semantic understanding of trajectory data, and achieve more accurate and efficient trajectory tracking; on the other hand, the preprocessed trajectory data, trajectory knowledge relationship graph and trajectory data tracking results are graphically displayed through a visualization interface, which can enable users to intuitively understand the spatiotemporal distribution, movement laws and mutual relationships of the trajectory, and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A step flow chart of a trajectory tracking method based on a knowledge graph provided in an embodiment of the present invention;

[0045] Figure 2 A step flow chart of step S101 provided in an embodiment of the present invention;

[0046] Figure 3 A flowchart of the steps of preprocessing the original trajectory data provided by an embodiment of the present invention;

[0047] Figure 4 A step flow chart of step S1023 provided in an embodiment of the present invention;

[0048] Figure 5 A step flow chart of step S103 provided in an embodiment of the present invention;

[0049] Figure 6 A step flow chart of step S104 provided in an embodiment of the present invention;

[0050] Figure 7 A step flow chart of step S1043 provided in an embodiment of the present invention;

[0051] Figure 8 A schematic diagram of a flow chart of a trajectory tracking method based on a knowledge graph provided in an embodiment of the present invention;

[0052] Fig. 9 A schematic diagram of the structure of a trajectory tracking system based on a knowledge graph provided in an embodiment of the present invention;

[0053] Fig.10 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0055] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0056] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0057] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0058] Knowledge Graph: A graph-based data structure that connects all different types of information in the form of nodes and edges to form a relational network, providing the ability to analyze problems from the perspective of "relationships".

[0059] Trajectory Tracking System: A system based on location data and trajectory information, which collects and analyzes the movement trajectory data of entities in the map and visualizes it on the map.

[0060] With the explosive growth of Internet information data and the rapid development of big data technology, trajectory tracking technology has been increasingly used in urban management, public safety, intelligent transportation and other fields. Intuitive and interactive relationship networks and map space visualization systems have also become the key to people's quick understanding of information. However, when processing trajectory data, trajectory tracking methods in previous technologies often only focus on the statistics and analysis of basic attributes such as location and time, while ignoring the semantic meaning behind the trajectory. For example, a vehicle trajectory may not only represent the change in the vehicle's position, but also imply a variety of information such as vehicle type, driver behavior, road conditions, and traffic events. This information is crucial for in-depth understanding of the essence of trajectory data and mining its potential value. However, due to the limitations of previous technologies, this semantic information is often not fully extracted and utilized, thus limiting the depth and breadth of data analysis. On the other hand, from the perspective of data presentation, although the trajectory data presentation methods in previous technologies, such as tables and text reports, can provide a certain data overview, they are obviously insufficient in terms of intuitiveness, interactivity and information richness. These methods are difficult to intuitively display the spatiotemporal distribution, movement patterns and relationships of trajectories, making the data analysis and decision-making process cumbersome and inefficient.

[0061] To this end, an embodiment of the present invention proposes a trajectory tracking method based on a knowledge graph, first constructing a trajectory knowledge graph, then obtaining the original trajectory data, preprocessing the original trajectory data to obtain trajectory data, and then associating the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph, and finally tracking the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result, and graphically displaying the trajectory data, the trajectory knowledge relationship graph, and the trajectory tracking result through a preset visualization interface. On the one hand, the present invention uses the knowledge graph to track trajectories, which can effectively represent the complex relationship between trajectory data entities, improve the semantic understanding ability of trajectory data, and achieve more accurate and efficient trajectory tracking; on the other hand, the preprocessed trajectory data, the trajectory knowledge relationship graph, and the trajectory data tracking results are displayed in a graphical manner through a visualization interface, which can enable users to intuitively understand the spatiotemporal distribution, movement laws, and mutual relationships of the trajectory, thereby improving user experience. The trajectory tracking method can be applied to scenarios such as urban management, public safety, and intelligent transportation, but is not limited thereto.

[0062] Reference Figure 1 , Figure 1 A flowchart of a trajectory tracking method based on a knowledge graph provided in an embodiment of the present invention. An embodiment of the present invention proposes a trajectory tracking method based on a knowledge graph, and the method includes steps S101 to S105:

[0063] S101, construct trajectory knowledge graph;

[0064] In some optional embodiments, the trajectory knowledge graph is constructed based on domain ontology and data mining technology to construct a trajectory knowledge graph containing geographic entities, time events, behavior patterns, and other information including entities, relationships, and attributes. For example, entities include people, vehicles, places, etc., relationships include passing, staying, transferring, etc., and attributes include time, speed, direction, etc.

[0065] Reference Figure 2 , Figure 2 A step flow chart of step S101 provided in an embodiment of the present invention, further as an optional implementation, the step of constructing a trajectory knowledge graph can be further divided into the following steps S1011 to S1013:

[0066] S1011, obtaining trajectory data samples, performing entity recognition on the trajectory data samples, and obtaining multiple types of entities;

[0067] In some optional embodiments, trajectory data samples can be obtained through devices such as GPS positioning terminals, smart phones, RFID tag technology, and satellite altimeters. The trajectory data samples include information such as the location of the target object (including longitude, latitude, initial location and last appearance location, etc.), time (initial appearance time, last appearance time, etc.) and speed.

[0068] Exemplarily, entities identified in trajectory data samples include moving objects (such as people, vehicles, animals, etc.), moving object information (such as name, license plate number, vehicle model, species, etc.), location (such as shopping malls, schools, parks, etc.), time (such as date, timestamp, etc.) and events (such as traffic accidents, traffic congestion, etc.), but are not limited to these.

[0069] S1012, extracting relationships between entities based on trajectory data samples to obtain multiple relationship structures;

[0070] Specifically, after identifying the entities in the trajectory data sample, it is necessary to determine the association or interaction relationship between these entities and use these relationship structures as the skeleton of the trajectory knowledge graph.

[0071] Exemplarily, the relational structure is represented in the form of a triple of "entity-relationship-entity", such as "person-passing-place", "vehicle-stay-time", "vehicle-arrival-destination" and "animal-migration-route".

[0072] S1013. Construct a trajectory knowledge graph with each entity as a node and each relationship structure as an edge.

[0073] Specifically, after completing entity recognition and relationship extraction, these entities are used as nodes and relationship structures as edges. The extracted entities and relationship structures are formed into a mesh or ring or force-directed graph or hierarchical graph data structure, which is displayed in the form of a knowledge graph, and a graph database or graph computing framework is used to store the trajectory knowledge graph.

[0074] S102, obtaining original trajectory data, and preprocessing the original trajectory data to obtain trajectory data;

[0075] Furthermore, the raw trajectory data preprocessing is to clean, standardize and semantically annotate the raw trajectory data to obtain trajectory data that is convenient for subsequent use. The raw trajectory data includes information such as object, longitude, latitude, altitude, moving speed, moving direction, last appearance position, last appearance time, base station number and occurrence area, but is not limited thereto.

[0076] Reference Figure 3 , Figure 3A flowchart of the steps of preprocessing the original trajectory data provided by an embodiment of the present invention, further as an optional implementation manner, preprocessing the original trajectory data to obtain the trajectory data can be further divided into the following steps S1021 to S1023:

[0077] S1021, removing outliers from the original trajectory data to obtain first trajectory data;

[0078] Specifically, outliers in the original trajectory data are deleted or smoothed, and outliers include unreasonable speeds, significant jump positions, wrong timestamp sequences, and sudden changes in direction, but are not limited thereto.

[0079] S1022, performing standardization processing on the first trajectory data to obtain second trajectory data;

[0080] Among them, standardization processing includes time standardization, space standardization and data format standardization.

[0081] Specifically, time standardization is to unify the timestamps in the first trajectory data to the same time standard, such as Beijing time or local time. For data across different coordinate systems, coordinate conversion is required, and spatial standardization is to unify the longitude and latitude coordinates of the first trajectory data to the same coordinate system, such as the WGS-84 coordinate system. Data format standardization is to unify the format of the first trajectory data, such as JSON, CSV, etc., for subsequent processing and analysis.

[0082] S1023, semantically annotating the second trajectory data to obtain trajectory data;

[0083] Reference Figure 4 , Figure 4 A step flow chart of step S1023 provided in an embodiment of the present invention, further as an optional implementation manner, the trajectory data includes entity information and attribute information, and the step of semantically annotating the second trajectory data to obtain the trajectory data can be further divided into the following steps S10231 to S10233:

[0084] S10231, segmenting the second trajectory data according to a preset time interval to obtain a plurality of trajectory segments;

[0085] Specifically, the long trajectory data contains a large number of data points, and directly processing these data points may consume a lot of computing resources and time. Therefore, the embodiment of the present invention performs segmentation processing on the second trajectory data to simplify the complex long trajectory into multiple relatively simple short trajectory segments, thereby significantly reducing the amount of calculation and improving processing efficiency; and the segmented trajectory segments can also be labeled in parallel, thereby speeding up the processing speed.

[0086] It should be noted that the preset time interval can be selected according to actual needs. For example, the time interval can be three hours, five hours, etc. In addition, in addition to segmenting the second trajectory data according to the time interval, the second trajectory data can also be segmented according to the spatial distance.

[0087] S10232, perform entity labeling on each trajectory segment to obtain entity information;

[0088] Exemplarily, key entity information, such as name, license plate number, place name, etc., is extracted from each trajectory segment, and entity annotation is performed using annotation tools such as Labelme, VGG or OpenCV.

[0089] S10233: Label each trajectory segment with attributes to obtain attribute information.

[0090] Exemplarily, the attribute annotation of the trajectory segment may include time attribute annotation, which marks the time information of the trajectory event, such as "2024-09-04 10:00"; location attribute annotation, which marks the specific location information of the trajectory event, such as "longitude and latitude coordinates (116.407396, 39.904200)"; state attribute annotation, which marks the state information of the moving object, such as "moving", "stopped", "waiting"; event attribute annotation, which marks the type of event occurring on the trajectory, such as "stopping", "turning", "accelerating", "decelerating"; direction attribute annotation, which marks the direction of movement of the moving object, such as "moving north" and "moving southwest".

[0091] S103, associating the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph;

[0092] Specifically, the embodiments of the present invention combine trajectory data with trajectory knowledge graph technology to achieve efficient retrieval, statistical analysis and deep mining of data. Through the retrieval function of the trajectory knowledge graph, the data in the graph can be efficiently traversed to quickly locate the trajectory data that matches the specific query conditions. On the basis of fast retrieval, the trajectory data can also be statistically analyzed, such as predicting future trajectory trends, summarizing the trajectory behavior patterns of the target object, etc.

[0093] Reference Figure 5 , Figure 5 A step flow chart of step S103 provided in an embodiment of the present invention, further as an optional implementation manner, the step of associating the trajectory data with the trajectory knowledge graph to obtain the trajectory knowledge relationship graph can be further divided into the following steps S1031 and S1032:

[0094] S1031, matching the entity information with the entities in the trajectory knowledge graph to obtain an entity matching result;

[0095] S1032. Update the relationship structure in the trajectory knowledge graph according to the entity matching results and attribute information to obtain a trajectory knowledge relationship graph.

[0096] Specifically, confirm that the entity information in the trajectory data corresponds to an entity in the trajectory knowledge graph. For example, confirm that a place name does exist in the place entity set in the knowledge graph, and then link the entity information in the trajectory data with the corresponding entity in the trajectory knowledge graph. After successfully matching the entity, the relationship structure in the trajectory knowledge graph is further updated according to the spatiotemporal characteristics of the trajectory data and the relationship structure definition in the trajectory knowledge graph to obtain an updated trajectory knowledge relationship graph.

[0097] S104, performing trajectory tracking on the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result;

[0098] Reference Figure 6 , Figure 6 A step flow chart of step S104 provided in an embodiment of the present invention is further provided. As an optional implementation, the step of performing trajectory tracking on the original trajectory data according to the trajectory knowledge relationship graph to obtain the trajectory tracking result can be further divided into the following steps S1041 to S1043:

[0099] S1041, determining semantic retrieval information and spatiotemporal retrieval information;

[0100] S1042, performing trajectory retrieval on the original trajectory data according to the semantic retrieval information and the spatiotemporal retrieval information through the trajectory knowledge relationship graph to obtain a trajectory retrieval result;

[0101] S1043 , performing trajectory tracking on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain a trajectory tracking result.

[0102] Specifically, the index structure of the trajectory knowledge relationship graph can be established based on optimization strategies such as R-tree and quadtree to accelerate the query process. The trajectory knowledge relationship graph after the index structure is established supports trajectory retrieval based on natural language description, time range and spatial area. Therefore, using the retrieval function of the knowledge graph, the semantic retrieval information and spatiotemporal retrieval information in the retrieval target are first determined. The trajectory knowledge relationship graph traverses and matches in the graph according to the semantic retrieval information and spatiotemporal retrieval information to find all trajectory fragments or trajectory points (i.e. trajectory retrieval results) that meet the conditions. After retrieving the trajectory retrieval results that meet the conditions, the retrieval results are sorted and connected according to the timestamp, geographic location and other information in the trajectory data to form a continuous trajectory path. At the same time, the behavior pattern, activity purpose, abnormal event or trajectory trend behind the trajectory is inferred in combination with the spatiotemporal characteristics of the trajectory data.

[0103] Exemplarily, the semantic retrieval information can be "Find vehicle trajectories near shopping mall A" or "Find people going to supermarket B"; the spatiotemporal retrieval information can be "Find all vehicle trajectories in area C from 8:00 to 10:00 on August 24, 2023" or "Find the trajectories of people in the city center between 2 and 3 pm on November 1, 2023".

[0104] Among them, R-tree is a balanced tree data structure for storing multidimensional spatial objects (such as points, lines, polygons, etc.). In the trajectory knowledge relationship graph, trajectory segments or trajectory points can be regarded as spatial objects and indexed using R-tree. When it is necessary to query all trajectory points in a certain area, it is only necessary to traverse the nodes in the R-tree that overlap with the area, without checking every trajectory point in the database.

[0105] A quadtree is a tree data structure used to index two-dimensional spatial data. In the trajectory knowledge relationship graph, the entire map area can be used as the root node of the quadtree, and smaller sub-areas can be gradually divided according to the distribution of trajectory points. When you need to query trajectory points in a specific area, you can start from the root node and traverse the quadtree level by level until you find the node that contains the area. Finally, you only need to search for trajectory points in the sub-area represented by the node.

[0106] Reference Figure 7 , Figure 7 A step flow chart of step S1043 provided in an embodiment of the present invention, further as an optional implementation manner, the trajectory tracking result includes a first trajectory tracking result, a second trajectory tracking result and a third trajectory tracking result, and the trajectory tracking is performed on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the trajectory tracking result. Specifically, the step can be further divided into the following steps S10431 to S10433:

[0107] S10431, performing trajectory pattern analysis on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain a first trajectory tracking result;

[0108] In some optional embodiments, a pattern mining algorithm such as an Apriori algorithm or a PrefixSpan algorithm may be used to count the frequently occurring trajectory segments or trajectory points in the trajectory data, and the probability of occurrence of these trajectory segments or trajectory points may be calculated, so as to analyze and obtain the trajectory patterns in the trajectory data, such as frequently visited places, fixed travel routes, etc., and obtain the first trajectory tracking result.

[0109] Among them, the Apriori algorithm is an association rule mining algorithm, and its core idea is to mine frequent item sets through two stages: candidate set generation and downward closure detection of the plot. The algorithm uses an iterative method of layer-by-layer search to find the relationship between item sets in the database to form rules. Its process consists of connection (matrix-like operation) and pruning (removing unnecessary intermediate results).

[0110] The PrefixSpan (Prefix-Projected Pattern Growth) algorithm, also known as prefix projection pattern mining, focuses on mining frequent sequences rather than frequent item sets. The algorithm starts mining sequence patterns from a prefix of length 1, and recursively mines frequent sequences corresponding to longer prefixes by searching the corresponding prefix projection database until the prefix projection database of a certain prefix is ​​empty.

[0111] S10432, performing abnormal behavior analysis on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain a second trajectory tracking result;

[0112] In some optional embodiments, the distance between each trajectory point or trajectory segment and other trajectory points or trajectory segments (such as Euclidean distance, Manhattan distance, etc.) is calculated to identify abnormal points or abnormal trajectory segments with a longer distance. The local density of each trajectory point or trajectory segment can also be calculated using a local outlier factor (LOF) algorithm, and abnormal points or abnormal trajectory segments with lower density can be identified to obtain a second trajectory tracking result.

[0113] Among them, the Local Outlier Factor (LOF) algorithm is an unsupervised learning method for detecting outliers in a data set. The core idea of ​​the algorithm is that outliers usually have a lower density in their surrounding neighborhoods, while normal points have a higher density in their surrounding neighborhoods. Therefore, the algorithm determines whether each data point is an outlier by calculating the density ratio of each data point to other data points in its neighborhood (i.e., the local outlier factor).

[0114] S10433. Predict the trajectory trend of the trajectory retrieval result through the trajectory knowledge relationship graph to obtain a third trajectory tracking result.

[0115] In some optional embodiments, the potential connections and rules between the various trajectory segments can be analyzed through the relationship between nodes and edges in the trajectory knowledge relationship graph, and key factors affecting the trajectory trend, such as time, location, event, etc., can be identified. Then, according to the analysis results and historical trajectory data, a trajectory trend prediction model based on a neural network is constructed, and the future trend of the original trajectory data is predicted by the trajectory trend prediction model. The prediction results include future position, speed, direction and other state information, and the corresponding confidence or probability distribution is given.

[0116] S105 , graphically displaying the trajectory data, the trajectory knowledge relationship diagram, and the trajectory tracking result through a preset visualization interface.

[0117] In some optional embodiments, the visualization interface can be deployed using Vue 3, G6 gallery and leaflet map technology. The visualization interface includes a map area, a chart area, a control panel and a data information panel, wherein the map area (for displaying the geographic location of the trajectory data and the trajectory tracking results), the chart area (using G6 to display the trajectory knowledge relationship diagram), the control panel (including interactive buttons, filter conditions, etc.) and the data information panel (displaying detailed information of the trajectory data) are used to realize multi-dimensional data display and real-time analysis. After the visualization interface is deployed, the functions of zooming, panning, clicking, etc. of the map, the node selection, highlighting, etc. of the trajectory knowledge relationship diagram, and the filtering, sorting, etc. of the control panel are tested in the local development environment. Next, cross-browser testing is performed to test the responsive layout effect of the visualization interface under different devices and screen sizes to improve the compatibility of the interface. Finally, the developer tools of the browser are used to debug JavaScript, CSS and Vue code.

[0118] It should be noted that the embodiments of the present invention can graphically display the preprocessed trajectory data, trajectory knowledge relationship diagram and trajectory tracking results by constructing an intuitive and interactive visualization interface and components, so that users can intuitively understand the spatiotemporal distribution, movement laws and mutual relationships of the trajectory, improve the user experience, and have good scalability and can be applied to trajectory tracking needs in different fields.

[0119] In summary, the processing flow of the trajectory tracking method based on knowledge graph in the embodiment of the present invention is as follows: Figure 8 As shown:

[0120] The first step is to build a trajectory knowledge graph;

[0121] The second step is to clean, standardize and semantically annotate the original trajectory data to obtain trajectory data;

[0122] The third step is to associate the trajectory data with the trajectory knowledge graph to obtain the trajectory knowledge relationship graph;

[0123] The fourth step is to realize the search and mining function of trajectory data based on the trajectory knowledge relationship graph and obtain the trajectory tracking result;

[0124] The fifth step is to provide a visualization interface to display the trajectory data, trajectory knowledge relationship diagram and trajectory tracking results in a graphical way.

[0125] The above describes the trajectory tracking method based on the knowledge graph in the embodiment of the present invention. It can be appreciated that compared with the trajectory tracking method in the prior art, the embodiment of the present invention has the following advantages:

[0126] 1. Combining trajectory data with trajectory knowledge graph technology to build a trajectory knowledge graph suitable for trajectory tracking can effectively represent the complex relationship between trajectory data entities, improve the ability to understand the semantics of trajectory data, and achieve more accurate and efficient trajectory analysis;

[0127] Second, by segmenting the second trajectory data, the complex long trajectory is simplified into multiple relatively simple short trajectory data segments, which can significantly reduce the amount of calculation and improve the processing efficiency. The segmented trajectory data segments can also be labeled in parallel, thereby speeding up the processing speed.

[0128] 3. By building intuitive and interactive visualization interfaces and components, the pre-processed trajectory data, trajectory knowledge relationship diagrams, and trajectory tracking results can be graphically displayed, enabling users to intuitively understand the spatiotemporal distribution, motion patterns, and relationships of the trajectories, thereby improving the user experience.

[0129] Reference Fig. 9 , an embodiment of the present invention further provides a trajectory tracking system based on a knowledge graph, comprising:

[0130] Graph construction module, used to build trajectory knowledge graph;

[0131] A data preprocessing module is used to obtain original trajectory data, preprocess the original trajectory data, and obtain trajectory data;

[0132] The trajectory graph fusion module is used to associate the trajectory data with the trajectory knowledge graph to obtain the trajectory knowledge relationship graph;

[0133] The trajectory tracking module is used to track the original trajectory data according to the trajectory knowledge relationship graph to obtain the trajectory tracking result;

[0134] The data visualization module is used to graphically display the trajectory data, trajectory knowledge relationship diagram and trajectory tracking results through a preset visualization interface.

[0135] The contents of the above-mentioned knowledge graph-based trajectory tracking method embodiment are all applicable to the present knowledge graph-based trajectory tracking system embodiment. The functions specifically implemented by the present knowledge graph-based trajectory tracking system embodiment are the same as those of the above-mentioned knowledge graph-based trajectory tracking method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned knowledge graph-based trajectory tracking method embodiment.

[0136] The embodiment of the present invention further provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned trajectory tracking method based on the knowledge graph. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0137] like Fig.10 FIG. 1 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention, referring to FIG. Fig.10 , an embodiment of the present invention provides an electronic device, including:

[0138] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0139] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other applications. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the trajectory tracking method based on the knowledge graph in the embodiment of the present invention;

[0140] Input / output interface 1003, used to implement information input and output;

[0141] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0142] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0143] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0144] An embodiment of the present invention also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned trajectory tracking method based on the knowledge graph.

[0145] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0147] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. The optional embodiment is expected, wherein the order of various operations is changed and the sub-operation described as a part of a larger operation is performed independently.

[0148] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0149] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0150] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0151] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the above-mentioned program is printed, since the above-mentioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in other suitable ways as necessary, and then stored in a computer memory.

[0152] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0153] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0154] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0155] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A trajectory tracking method based on knowledge graph, characterized in that: The following steps are involved: Construct trajectory knowledge graph; Acquire original trajectory data, and preprocess the original trajectory data to obtain trajectory data; Associating the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph; Performing trajectory tracking on the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result; The trajectory data, the trajectory knowledge relationship diagram, and the trajectory tracking result are graphically displayed through a preset visualization interface.

2. According to the knowledge graph-based trajectory tracking method of claim 1, it is characterized in that: The constructing of the trajectory knowledge graph specifically includes: Acquire trajectory data samples, perform entity recognition on the trajectory data samples, and obtain multiple types of entities; Extracting relationships between the entities according to the trajectory data samples to obtain multiple relationship structures; The trajectory knowledge graph is constructed with each of the entities as a node and each of the relationship structures as an edge.

3. According to a knowledge graph-based trajectory tracking method according to claim 1, it is characterized in that: The preprocessing of the original trajectory data to obtain trajectory data specifically includes: Eliminate outliers from the original trajectory data to obtain first trajectory data; performing standardization processing on the first trajectory data to obtain second trajectory data; Performing semantic annotation on the second trajectory data to obtain the trajectory data; The standardization process includes time standardization, space standardization and data format standardization.

4. The trajectory tracking method based on knowledge graph according to claim 3 is characterized in that: The trajectory data includes entity information and attribute information, and the semantic annotation of the second trajectory data to obtain the trajectory data specifically includes: Segmenting the second trajectory data according to a preset time interval to obtain a plurality of trajectory segments; Performing entity labeling on each of the trajectory segments to obtain the entity information; Attributes are labeled on each of the trajectory segments to obtain the attribute information.

5. A trajectory tracking method based on knowledge graph according to claim 4, characterized in that: The associating the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph specifically includes: Matching the entity information with entities in the trajectory knowledge graph to obtain an entity matching result; The relationship structure in the trajectory knowledge graph is updated according to the entity matching result and the attribute information to obtain the trajectory knowledge relationship graph.

6. The trajectory tracking method based on knowledge graph according to claim 1, characterized in that: The performing trajectory tracking on the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result specifically includes: Determine semantic retrieval information and spatiotemporal retrieval information; Performing trajectory retrieval on the original trajectory data according to the semantic retrieval information and the spatiotemporal retrieval information through the trajectory knowledge relationship graph to obtain a trajectory retrieval result; The trajectory retrieval result is tracked by using the trajectory knowledge relationship graph to obtain the trajectory tracking result.

7. The trajectory tracking method based on knowledge graph according to claim 6 is characterized in that: The trajectory tracking result includes a first trajectory tracking result, a second trajectory tracking result and a third trajectory tracking result. The trajectory tracking is performed on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the trajectory tracking result, which specifically includes: Performing trajectory pattern analysis on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the first trajectory tracking result; Performing abnormal behavior analysis on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the second trajectory tracking result; The trajectory trend is predicted on the trajectory retrieval result through the trajectory knowledge relationship graph to obtain the third trajectory tracking result.

8. A trajectory tracking system based on knowledge graph, characterized in that: include: Graph construction module, used to build trajectory knowledge graph; A data preprocessing module, used to obtain original trajectory data, and preprocess the original trajectory data to obtain trajectory data; A trajectory graph fusion module, used to associate the trajectory data with the trajectory knowledge graph to obtain a trajectory knowledge relationship graph; A trajectory tracking module, used to track the original trajectory data according to the trajectory knowledge relationship graph to obtain a trajectory tracking result; The data visualization module is used to graphically display the trajectory data, the trajectory knowledge relationship diagram and the trajectory tracking result through a preset visualization interface.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the trajectory tracking method based on the knowledge graph are realized as described in any one of claims 1 to 7.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the trajectory tracking method based on the knowledge graph as described in any one of claims 1 to 7.

Images