Map trajectory optimization method and device, computer equipment and storage medium

Abstract

The invention discloses a map trajectory optimization method and device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, respectively drawing a real-time trajectory diagram and a historical trajectory diagram by acquiring real-time positioning data and historical trajectory data of a user; and then, classifying the positioning points in the real-time trajectory diagram, and identifying abnormal positioning points by using an abnormal point detection algorithm. Then, carrying out region division on the real-time trajectory diagram, and respectively calculating the density and type distribution of positioning points in each region; and based on the features, a pre-trained data quality evaluation model is used to evaluate the data quality grade of each track area. And finally, according to the data quality grade, configuring a track deviation rectification weight, and carrying out deviation rectification processing on the real-time track diagram. The invention also relates to the technical field of block chains, and the positioning data is stored in a block chain network. According to the method, the accuracy of track drawing is improved, and the problem that the user track is not accurate enough due to positioning deviation is solved.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a map trajectory optimization method, device, computer equipment and storage medium. Background Art

[0002] Map trajectory refers to a series of points or line segments in a map or navigation system that represent the movement path of a moving object (such as a person, vehicle, animal, etc.) over time. These points or line segments are usually connected in chronological order to form a continuous path, so as to intuitively display the movement direction and movement process of the object. Map trajectory can help users plan routes, locate in real time and guide to the destination. For example, in the field of transportation, by analyzing the trajectory data of vehicles or pedestrians, we can understand traffic flow, congestion, travel patterns, etc., and provide decision support for transportation planning and management. In the field of logistics, by analyzing the transportation trajectory of goods, we can optimize distribution routes and reduce transportation time and costs. In the field of sports and health, map trajectories can record information such as movement routes, speeds, distances, etc., to help users better understand their own movement status.

[0003] In map applications, the user's real-time location and movement trajectory are very important information. However, due to various factors, such as unstable GPS signals and difficulty in indoor positioning, the location data obtained by relying solely on real-time positioning often has deviations, resulting in inaccurate user trajectories, which affects the user experience of map applications. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a map trajectory optimization method, device, computer equipment and storage medium to solve the technical problem that the location data obtained by existing real-time positioning has deviations, resulting in inaccurate user trajectories drawn, affecting the user experience of map applications.

[0005] In order to solve the above technical problems, the present application embodiment provides a map trajectory optimization method, which adopts the following technical solutions:

[0006] A map trajectory optimization method, comprising:

[0007] Obtain the user's real-time positioning data and draw a real-time trajectory map based on the real-time positioning data;

[0008] Obtain the user's historical trajectory data and draw a historical trajectory map based on the historical trajectory data;

[0009] Based on the real-time trajectory map and the historical trajectory map, an outlier detection algorithm is used to classify the positioning points in the real-time trajectory map;

[0010] Divide the real-time trajectory map into regions to obtain several trajectory region maps, and calculate the positioning point density and positioning point type distribution of each trajectory region map;

[0011] Based on the density of positioning points and the distribution of positioning point types of each trajectory area map, the data quality level of each trajectory area map is determined using a pre-trained data quality assessment model;

[0012] Configure the trajectory correction weight according to the data quality level, and use the trajectory correction weight to correct the real-time trajectory map.

[0013] Furthermore, the outlier detection algorithm is a density clustering algorithm. The classification of positioning points includes abnormal positioning points and non-abnormal positioning points. Based on the real-time trajectory map and the historical trajectory map, the steps of using the outlier detection algorithm to classify the positioning points in the real-time trajectory map specifically include:

[0014] Construct a spatial coordinate system and import the real-time trajectory map and historical trajectory map into the spatial coordinate system for spatiotemporal registration;

[0015] In the spatial coordinate system, a density clustering algorithm is used to detect outliers in the real-time trajectory graph and mark the outliers as potential abnormal points;

[0016] For each potential abnormal point, extract the real-time trajectory segment and the corresponding historical trajectory segment in the area around the potential abnormal point;

[0017] Calculate the angle deviation between the real-time trajectory segment and the historical trajectory segment, and compare the angle deviation with a preset deviation threshold;

[0018] If the angle deviation is greater than the preset deviation threshold, the potential abnormal point is determined to be an abnormal positioning point, otherwise, the potential abnormal point is determined to be a non-abnormal positioning point.

[0019] Furthermore, the real-time trajectory map is divided into regions to obtain a plurality of trajectory region maps, and the steps of calculating the density of positioning points and the distribution of positioning point types of each trajectory region map specifically include:

[0020] The real-time trajectory map is divided into regions according to a preset division rule to obtain a plurality of trajectory region maps;

[0021] Count the number of positioning points in the real-time trajectory graph to obtain the number of first positioning points;

[0022] For each trajectory area graph, count the number of positioning points in the trajectory area graph to obtain the second number of positioning points;

[0023] Calculate the density of the positioning points of each track area graph according to the first number of positioning points and the second number of positioning points;

[0024] For each trajectory area map, the abnormal positioning points and non-abnormal positioning points in the trajectory area map are counted to obtain the positioning point type distribution.

[0025] Further, based on the positioning point density and the positioning point type distribution of each trajectory area map, the step of using the pre-trained data quality assessment model to determine the data quality level of each trajectory area map specifically includes:

[0026] For each track area map, the density of the anchor points and the distribution of the anchor point types are respectively extracted to obtain the density features of the anchor points and the distribution features of the anchor point types.

[0027] Perform feature alignment on the anchor point density features and the anchor point type distribution features;

[0028] The density feature of the positioning points and the distribution feature of the positioning points after feature alignment are combined to obtain an input feature vector;

[0029] The input feature vector is imported into the data quality assessment model to obtain the data quality level of the trajectory area graph.

[0030] Furthermore, before the step of determining the data quality level of each trajectory area map using a pre-trained data quality assessment model based on the positioning point density and the positioning point type distribution of each trajectory area map, the method further includes:

[0031] Obtaining model training data, wherein the model training data is the density of positioning points, the distribution of positioning point types, and the quality level of historical data of a pre-collected historical trajectory area map;

[0032] Perform feature engineering on the density of anchor points, distribution of anchor point types, and quality level of historical data in the historical trajectory area map to obtain the historical input feature vector;

[0033] Import the historical input feature vector into the preset initial evaluation model to obtain the historical data prediction level, wherein the initial evaluation model is implemented based on the support vector machine algorithm;

[0034] Compare the historical data prediction level and the historical data quality level to obtain the prediction error, and iteratively update the initial evaluation model based on the prediction error until the model is fitted to obtain a trained data quality evaluation model.

[0035] Further, the step of configuring a trajectory correction weight according to the data quality level and using the trajectory correction weight to perform trajectory correction on the real-time trajectory map specifically includes:

[0036] According to the data quality level of each track area map, the corresponding track correction weight is obtained from the preset level weight mapping table to obtain the track correction weight of each track area map;

[0037] For each trajectory area map, obtain the coordinate sequence of the positioning points in the trajectory area map, and based on the coordinate sequence of the positioning points, use the Kalman filter algorithm combined with the trajectory correction weight of the trajectory area map to perform correction calculation on the trajectory point coordinates to obtain the corrected trajectory point coordinate sequence;

[0038] Based on the trajectory point coordinate sequence after correction of the trajectory area map, a trajectory area supplementary map of the trajectory area map is drawn, and trajectory correction is performed on the trajectory area map based on the trajectory area supplementary map;

[0039] When all trajectory area maps have completed trajectory correction, the corrected real-time trajectory map is obtained.

[0040] Furthermore, after all the trajectory area maps have completed the trajectory correction, after the step of obtaining the corrected real-time trajectory map, the method further includes:

[0041] Based on the data quality levels of each track area map, an average data quality level of the real-time track map is calculated to obtain a first data quality level;

[0042] Calculate the average data quality level of the real-time trajectory map after deviation correction to obtain a second data quality level;

[0043] Calculating a level difference between the first data quality level and the second data quality level, and comparing the level difference with a preset difference threshold;

[0044] If the level difference is greater than the difference threshold, the ratio of the level difference to the difference threshold is calculated;

[0045] The trajectory correction weight is adjusted according to the ratio of the level difference to the difference threshold, and the trajectory correction is re-performed using the adjusted trajectory correction weight until the level difference is less than or equal to the difference threshold, and a real-time trajectory map with correction is output.

[0046] In order to solve the above technical problems, the present application also provides a map trajectory optimization device, which adopts the following technical solution:

[0047] A map trajectory optimization device, comprising:

[0048] A real-time trajectory drawing module is used to obtain the user's real-time positioning data and draw a real-time trajectory map based on the real-time positioning data;

[0049] A historical trajectory drawing module is used to obtain the user's historical trajectory data and draw a historical trajectory map based on the historical trajectory data;

[0050] A positioning point classification module is used to classify the positioning points in the real-time trajectory map based on the real-time trajectory map and the historical trajectory map using an outlier detection algorithm;

[0051] The track area division module is used to divide the real-time track map into regions, obtain several track area maps, and calculate the positioning point density and positioning point type distribution of each track area map;

[0052] A data quality assessment module, for determining the data quality level of each track area map based on the density of the positioning points and the distribution of the positioning point types of each track area map using a pre-trained data quality assessment model;

[0053] The real-time trajectory correction module is used to configure the trajectory correction weight according to the data quality level, and use the trajectory correction weight to perform trajectory correction on the real-time trajectory map.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0055] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the map trajectory optimization method as described in any one of the above items are implemented.

[0056] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0057] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of the map trajectory optimization method as described in any one of the above.

[0058] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0059] The present application discloses a map trajectory optimization method, device, computer equipment and storage medium, which belongs to the field of artificial intelligence technology. In order to solve the trajectory deviation problem caused by the existing reliance on real-time positioning, by combining the user's historical trajectory data with the real-time positioning data, using the outlier detection algorithm and the pre-trained data quality assessment model, the abnormal positioning points can be effectively identified and classified. At the same time, based on the density and type distribution of the positioning points in the trajectory area, the correction weights are flexibly configured to accurately correct the real-time trajectory map. This application significantly improves the accuracy of trajectory drawing, solves the problem of inaccurate user trajectories due to positioning deviation, improves the user experience of map applications, and improves the reliability and accuracy of positioning services. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0061] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0062] Figure 2 A flowchart of an embodiment of a map trajectory optimization method according to the present application is shown;

[0063] Figure 3 A schematic structural diagram of an embodiment of a map trajectory optimization device according to the present application is shown;

[0064] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0068] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0069] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0070] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0071] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0072] It should be noted that the map trajectory optimization method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the map trajectory optimization device is generally arranged in the server / terminal device.

[0073] It should be understood that Figure 1 The numbers of terminal devices, networks and servers in the embodiment are merely illustrative. The above system may have any number of terminal devices, networks and servers according to implementation requirements.

[0074] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for optimizing map trajectory according to the present application. The map trajectory optimization method comprises the following steps:

[0075] S201, obtaining the user's real-time positioning data, and drawing a real-time trajectory map according to the real-time positioning data.

[0076] Specifically, real-time positioning data is dynamic location data obtained through multiple positioning technologies such as GPS, Wi-Fi signals, and cellular networks of user devices, which can reflect the user's current geographic location information. In this step, the system will continuously collect the user's real-time positioning data at preset time intervals and draw a real-time trajectory map of the user based on this data. The real-time trajectory map shows the user's walking, driving, and other activity paths in the current time period.

[0077] However, due to factors such as device signal fluctuations, environmental occlusion, and network delays, real-time positioning data usually has certain errors or noise, which will affect the accuracy of the trajectory map. The system combines multiple signal sources such as GPS, Wi-Fi, and base station positioning through a highly integrated processing method, and comprehensively considers the accuracy of GPS satellite signals, the regional reference provided by Wi-Fi hotspots, and the stability of base station positioning. In addition, the system will use advanced filtering algorithms to effectively eliminate data points with large errors based on dynamic information such as the directional consistency of the previous and next positioning points, changes in moving speed, and the angle of the device's travel, to ensure smooth and accurate positioning results.

[0078] S202, obtaining historical trajectory data of the user, and drawing a historical trajectory map according to the historical trajectory data.

[0079] Specifically, historical trajectory data is the positioning information accumulated by the user over a period of time, which is usually stored locally on the device or on the server. By calling these historical data, the system can draw the user's movement trajectory during the historical period. Compared with real-time data, historical trajectory data has more stability and continuity, and is less affected by signal fluctuations, so it is usually more accurate than real-time positioning data. By drawing a historical trajectory map, the system can use the historical trajectory to determine the user's regular activity area or route pattern.

[0080] S203, based on the real-time trajectory map and the historical trajectory map, an outlier detection algorithm is used to classify the positioning points in the real-time trajectory map.

[0081] Specifically, the outlier detection algorithm is a method for identifying positioning points in a trajectory that deviate from the normal path. Since real-time positioning data may be affected by various factors such as signal interference and equipment accuracy, some positioning points will deviate from the user's actual location. By comparing with the historical trajectory map, the outlier detection algorithm can determine whether certain positioning points conform to the user's normal trajectory pattern. In this step, the system compares the real-time trajectory map with the historical trajectory map, detects outliers in the real-time trajectory, and classifies the positioning points into normal points and outliers. Usually, the algorithm analyzes whether the positioning point is abnormal based on multiple dimensions such as the degree of spatial deviation, speed change, and direction change. Classifying the real-time trajectory helps with subsequent deviation correction, allowing the system to more accurately identify the positioning points that need to be corrected, thereby improving the overall quality of the trajectory.

[0082] S204, dividing the real-time trajectory map into regions to obtain a plurality of trajectory region maps, and calculating the positioning point density and positioning point type distribution of each trajectory region map.

[0083] Specifically, in this step, the system divides the real-time trajectory map into multiple small areas, each of which contains several positioning points. This division is usually based on the geographical scope or the user's activity pattern, and localizes different parts of the user's journey. For each area, the system calculates the density of the positioning points, that is, the number or concentration of positioning points in the area. At the same time, the system also analyzes the type distribution of positioning points in the area, including the proportion of normal points and abnormal points. The density and type distribution of positioning points can reflect the stability and reliability of the trajectory in the area. Areas with high density and a large proportion of normal points usually have higher trajectory quality, while areas with low density or a large proportion of abnormal points may have trajectory deviations.

[0084] S205 , based on the positioning point density and the positioning point type distribution of each trajectory area map, using a pre-trained data quality assessment model, determine the data quality level of each trajectory area map.

[0085] Specifically, in this step, the system will use the pre-trained data quality assessment model to analyze and evaluate the data quality of each area based on the density and type distribution of the positioning points in each trajectory area. The pre-trained model is trained with a large amount of historical data and can evaluate the accuracy and reliability of the trajectory data in the area based on the characteristics of the positioning points in different areas. The data quality level is usually derived based on factors such as the density of the positioning points, the proportion of abnormal points, and the continuity of the trajectory. For areas with dense positioning points and a high proportion of normal points, the data quality level is higher, while areas with many abnormal points or broken trajectories have a lower quality level.

[0086] S206, configuring a trajectory correction weight according to the data quality level, and using the trajectory correction weight to perform trajectory correction on the real-time trajectory map.

[0087] Specifically, in this step, the system configures different correction weights according to the data quality level of each trajectory area previously determined. Areas with high data quality may only require a small amount of trajectory correction, while areas with low data quality require a greater correction force. The correction weight is a parameter used to adjust the position of the trajectory point. The larger the weight, the greater the correction amplitude of the trajectory point. By assigning different weights, the system can make targeted corrections to the trajectory of each area, try to eliminate the deviation of the positioning point or the influence of abnormal points, and finally generate a more accurate real-time trajectory map. This process can effectively solve the problem of inaccurate trajectory caused by real-time positioning deviation, improve the overall quality of trajectory data, and enable users to experience more accurate navigation or location services.

[0088] Furthermore, the outlier detection algorithm is a density clustering algorithm. The classification of positioning points includes abnormal positioning points and non-abnormal positioning points. Based on the real-time trajectory map and the historical trajectory map, the steps of using the outlier detection algorithm to classify the positioning points in the real-time trajectory map specifically include:

[0089] Construct a spatial coordinate system and import the real-time trajectory map and historical trajectory map into the spatial coordinate system for spatiotemporal registration;

[0090] In the spatial coordinate system, a density clustering algorithm is used to detect outliers in the real-time trajectory graph and mark the outliers as potential abnormal points;

[0091] For each potential abnormal point, extract the real-time trajectory segment and the corresponding historical trajectory segment in the area around the potential abnormal point;

[0092] Calculate the angle deviation between the real-time trajectory segment and the historical trajectory segment, and compare the angle deviation with a preset deviation threshold;

[0093] If the angle deviation is greater than the preset deviation threshold, the potential abnormal point is determined to be an abnormal positioning point, otherwise, the potential abnormal point is determined to be a non-abnormal positioning point.

[0094] In this embodiment, a spatial coordinate system is first constructed, and the real-time trajectory map and historical trajectory map of the user are imported into the coordinate system for spatiotemporal registration, that is, the two are aligned so that they can be directly compared in time and space dimensions. In the spatial coordinate system, the system uses a density clustering algorithm to analyze the real-time trajectory map, detect outliers in the trajectory, that is, those positioning points that deviate significantly from the normal trajectory according to the density distribution of the positioning points, and mark these outliers as potential abnormal points. Next, for each potential abnormal point, the system extracts the trajectory segments around the point, including real-time trajectory segments and historical trajectory segments. The system calculates the angle deviation between these trajectory segments, specifically, it analyzes the changes in the user's movement direction. Then, the system compares the calculated angle deviation with the pre-set deviation threshold. If the angle deviation is greater than the threshold, the potential abnormal point is considered to be an abnormal positioning point, which means that the positioning data of the point has a significant deviation; if the angle deviation is less than the threshold, the potential abnormal point is considered to be a non-abnormal positioning point, that is, a positioning point with normal positioning. This multi-step judgment process based on spatiotemporal registration and angle deviation makes the detection of positioning abnormal points more accurate.

[0095] Through the above steps, positioning anomalies caused by signal errors, equipment problems or other environmental factors can be effectively identified, thereby improving the accuracy and reliability of trajectory data.

[0096] Furthermore, the real-time trajectory map is divided into regions to obtain a plurality of trajectory region maps, and the steps of calculating the density of positioning points and the distribution of positioning point types of each trajectory region map specifically include:

[0097] The real-time trajectory map is divided into regions according to a preset division rule to obtain a plurality of trajectory region maps;

[0098] Count the number of positioning points in the real-time trajectory graph to obtain the number of first positioning points;

[0099] For each trajectory area graph, count the number of positioning points in the trajectory area graph to obtain the second number of positioning points;

[0100] Calculate the density of the positioning points of each track area graph according to the first number of positioning points and the second number of positioning points;

[0101] For each trajectory area map, the abnormal positioning points and non-abnormal positioning points in the trajectory area map are counted to obtain the positioning point type distribution.

[0102] In this embodiment, the real-time trajectory map is first divided into regions according to a preset division rule, and the entire trajectory map is divided into several independent trajectory area maps. The division rule can be based on the gridding of the geographical location, the path characteristics of the user's movement, or other customized area division standards. Then, the system counts all the positioning points of the entire real-time trajectory map to obtain the first number of positioning points of the map, that is, the total number of positioning points of the user in the entire trajectory. Then, for each trajectory area map, the number of positioning points in the area is counted respectively to obtain the second number of positioning points. Based on the first number of positioning points and the second number of positioning points, the system calculates the density of positioning points for each trajectory area map. The density of positioning points reflects the concentration of positioning points in a certain area, which can help the system identify areas where user activities are frequent or positioning points are sparse. In addition, for each trajectory area map, the system further counts the abnormal positioning points and non-abnormal positioning points therein, so as to obtain the distribution of positioning point types and determine the proportion of abnormal points and normal points in each area.

[0103] Through the above steps, the density of positioning points and the distribution of abnormal points in each trajectory area can be analyzed in detail, thereby providing an accurate basis for trajectory optimization and effectively improving the overall quality of trajectory data.

[0104] Further, based on the positioning point density and the positioning point type distribution of each trajectory area map, the step of using the pre-trained data quality assessment model to determine the data quality level of each trajectory area map specifically includes:

[0105] For each track area map, the density of the anchor points and the distribution of the anchor point types are respectively extracted to obtain the density features of the anchor points and the distribution features of the anchor point types.

[0106] Perform feature alignment on the anchor point density features and the anchor point type distribution features;

[0107] The density feature of the positioning points and the distribution feature of the positioning points after feature alignment are combined to obtain an input feature vector;

[0108] The input feature vector is imported into the data quality assessment model to obtain the data quality level of the trajectory area graph.

[0109] In this embodiment, the system first extracts features for the density of anchor points and the distribution of anchor point types for each trajectory area map, and obtains the density feature of the anchor point and the distribution feature of the anchor point type, respectively. The density feature of the anchor point describes the concentration of anchor points in the trajectory area, while the distribution feature of the anchor point type reflects the proportion and distribution of abnormal anchor points and non-abnormal anchor points in the area. Next, the system aligns the two features, that is, makes them comparable in feature dimensions and weights, and ensures that the density feature of the anchor point and the distribution feature of the anchor point type can be comprehensively considered to avoid evaluation bias caused by inconsistency between features. After completing the feature alignment, the system combines the two features into an input feature vector. The input feature vector is used as the feature data that comprehensively describes the trajectory area, which can reflect the location density, abnormal point distribution and other information of the area. Finally, the system imports this feature vector into the pre-trained data quality assessment model, and the model calculates the data quality level of the trajectory area map based on historical data and preset standards.

[0110] Through the above steps, the data quality of the trajectory area can be accurately evaluated, and the accuracy of trajectory data quality evaluation can be improved by combining the characteristics of density and type distribution.

[0111] Furthermore, before the step of determining the data quality level of each trajectory area map using a pre-trained data quality assessment model based on the positioning point density and the positioning point type distribution of each trajectory area map, the method further includes:

[0112] Obtaining model training data, wherein the model training data is the density of positioning points, the distribution of positioning point types, and the quality level of historical data of a pre-collected historical trajectory area map;

[0113] Perform feature engineering on the density of anchor points, distribution of anchor point types, and quality level of historical data in the historical trajectory area map to obtain the historical input feature vector;

[0114] Import the historical input feature vector into the preset initial evaluation model to obtain the historical data prediction level, wherein the initial evaluation model is implemented based on the support vector machine algorithm;

[0115] Compare the historical data prediction level and the historical data quality level to obtain the prediction error, and iteratively update the initial evaluation model based on the prediction error until the model is fitted to obtain a trained data quality evaluation model.

[0116] In this embodiment, firstly, a data set for training is obtained. These data sets are derived from the relevant information of the historical trajectory area map collected in advance, specifically including the density of the positioning points, the distribution of the positioning point types, and the quality level of the historical data. The positioning point density reflects the density of the positioning points in the area, and the type distribution describes the distribution of abnormal points and normal points. The quality level of the historical data represents the actual data accuracy of the trajectory in the area. Next, the system performs feature engineering on these historical data, that is, converting the positioning point density, the positioning point type distribution, and the data quality level into feature vectors that can be used for model training, which are called historical input feature vectors. These feature vectors can fully express the positioning point characteristics of the historical trajectory area. Subsequently, the system imports these historical input feature vectors into an initial data quality assessment model based on the support vector machine (SVM) algorithm. The model predicts the quality level of historical data for each area based on the input features, that is, the historical data prediction level. Then, the system compares the prediction results with the actual quality level of the historical data and calculates the prediction error. By continuously calculating the prediction error and iteratively optimizing the initial evaluation model, the system finally obtains a model that can accurately evaluate the data quality, that is, the trained data quality assessment model.

[0117] Through the above steps, a high-precision data quality assessment model can be constructed. By continuously adjusting the model, it can achieve a higher prediction accuracy in trajectory data quality assessment.

[0118] Further, the step of configuring a trajectory correction weight according to the data quality level and using the trajectory correction weight to perform trajectory correction on the real-time trajectory map specifically includes:

[0119] According to the data quality level of each track area map, the corresponding track correction weight is obtained from the preset level weight mapping table to obtain the track correction weight of each track area map;

[0120] For each trajectory area map, obtain the coordinate sequence of the positioning points in the trajectory area map, and based on the coordinate sequence of the positioning points, use the Kalman filter algorithm combined with the trajectory correction weight of the trajectory area map to perform correction calculation on the trajectory point coordinates to obtain the corrected trajectory point coordinate sequence;

[0121] Based on the trajectory point coordinate sequence after correction of the trajectory area map, a trajectory area supplementary map of the trajectory area map is drawn, and trajectory correction is performed on the trajectory area map based on the trajectory area supplementary map;

[0122] When all trajectory area maps have completed trajectory correction, the corrected real-time trajectory map is obtained.

[0123] In this embodiment, first, according to the data quality level of each trajectory area map, the corresponding trajectory correction weight is obtained from the preset level weight mapping table (data quality level-correction weight mapping table). The area with high data quality level usually has high positioning accuracy, so the correction weight is low. On the contrary, the area with poor quality will be assigned a higher correction weight to enhance the correction strength. Then, for each trajectory area map, the system obtains the coordinate sequence of the positioning points therein, that is, the coordinate information of all points on the trajectory. The system uses the Kalman filter algorithm to correct these coordinate points. Kalman filtering is a classic trajectory smoothing and prediction algorithm that can effectively filter out noise and abnormal points. When performing Kalman filtering, the system combines the correction weight of each trajectory area to dynamically adjust the coordinates of the trajectory points to obtain the coordinate sequence of the trajectory points after correction. Based on these corrected trajectory points, the system draws a supplementary map of the trajectory area, which reflects the corrected trajectory path. The corrected path is smoother and conforms to the actual motion trajectory. Finally, the system integrates the correction results of each trajectory area. When the correction of all trajectory areas is completed, a complete real-time trajectory map after correction is obtained.

[0124] Through the above steps, the data quality level and Kalman filter algorithm are used to achieve accurate correction of different trajectory areas, effectively correct the trajectory deviation, and finally generate a more accurate real-time trajectory map, improving positioning accuracy and user experience.

[0125] Furthermore, after all the trajectory area maps have completed the trajectory correction, after the step of obtaining the corrected real-time trajectory map, the method further includes:

[0126] Based on the data quality levels of each track area map, an average data quality level of the real-time track map is calculated to obtain a first data quality level;

[0127] Calculate the average data quality level of the real-time trajectory map after deviation correction to obtain a second data quality level;

[0128] Calculating a level difference between the first data quality level and the second data quality level, and comparing the level difference with a preset difference threshold;

[0129] If the level difference is greater than the difference threshold, the ratio of the level difference to the difference threshold is calculated;

[0130] The trajectory correction weight is adjusted according to the ratio of the level difference to the difference threshold, and the trajectory correction is re-performed using the adjusted trajectory correction weight until the level difference is less than or equal to the difference threshold, and a real-time trajectory map with correction is output.

[0131] In this embodiment, first, based on the different data quality levels of each track area map, the system calculates the average data quality level of the entire real-time track map, that is, the first data quality level, which reflects the overall positioning accuracy of the real-time track map before correction. Next, the system performs the same calculation on the real-time track map after correction to obtain the second data quality level, that is, the overall track quality after correction. Then, the system calculates the difference between the first data quality level and the second data quality level, which indicates the degree of improvement of the track quality before and after correction. The system compares this level difference with the preset difference threshold. If the difference is greater than the threshold, it means that the current correction effect has not yet reached the expected level. At this point, the system further calculates the ratio of the level difference to the threshold, and evaluates the degree of deficiency of the correction strength through this ratio. According to this ratio, the system dynamically adjusts the track correction weight, that is, allocates more accurate correction strength to different track areas. The adjusted weight will be reapplied to the track correction, and the system will continue this process until the level difference is less than or equal to the preset threshold, indicating that the correction effect has met the requirements, and finally outputs the optimized real-time track map.

[0132] Through the above steps, the track correction strength can be dynamically adjusted to ensure that the quality of the track data after correction meets the expected standards, effectively improve the track accuracy, and ensure that the user's location data is more accurate.

[0133] In the above embodiment, the present application discloses a map trajectory optimization method, which belongs to the field of artificial intelligence technology. In view of the trajectory deviation problem caused by the existing reliance on real-time positioning, by combining the user's historical trajectory data with the real-time positioning data, using the outlier detection algorithm and the pre-trained data quality assessment model, the abnormal positioning points are effectively identified and classified. At the same time, based on the density and type distribution of the positioning points in the trajectory area, the correction weights are flexibly configured to accurately correct the real-time trajectory map. This application significantly improves the accuracy of trajectory drawing, solves the problem of inaccurate user trajectories caused by positioning deviations, improves the user experience of map applications, and improves the reliability and accuracy of positioning services.

[0134] In this embodiment, the map trajectory optimization method is executed on the electronic device (eg Figure 1 The server shown in the figure) can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0135] It should be emphasized that in order to further ensure the privacy and security of the above positioning data information, the above positioning data information can also be stored in a blockchain node.

[0136] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0137] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0138] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0139] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0140] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0141] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a map trajectory optimization device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0142] like Figure 3 As shown, the map trajectory optimization device 300 described in this embodiment includes:

[0143] A real-time trajectory drawing module 301 is used to obtain the real-time positioning data of the user and draw a real-time trajectory map according to the real-time positioning data;

[0144] A historical trajectory drawing module 302 is used to obtain the historical trajectory data of the user and draw a historical trajectory map according to the historical trajectory data;

[0145] A positioning point classification module 303 is used to classify the positioning points in the real-time trajectory map using an abnormal point detection algorithm based on the real-time trajectory map and the historical trajectory map;

[0146] The track area division module 304 is used to divide the real-time track map into regions, obtain a plurality of track area maps, and calculate the positioning point density and positioning point type distribution of each track area map;

[0147] A data quality assessment module 305 is used to determine the data quality level of each track area map based on the positioning point density and the positioning point type distribution of each track area map using a pre-trained data quality assessment model;

[0148] The real-time trajectory correction module 306 is used to configure the trajectory correction weight according to the data quality level, and use the trajectory correction weight to perform trajectory correction on the real-time trajectory map.

[0149] Furthermore, the outlier detection algorithm is a density clustering algorithm, and the classification of positioning points includes abnormal positioning points and non-abnormal positioning points. The positioning point classification module 303 is specifically used for:

[0150] A spatial coordinate system is constructed, and the real-time trajectory map and the historical trajectory map are imported into the spatial coordinate system for spatiotemporal registration; in the spatial coordinate system, a density clustering algorithm is used to detect outliers in the real-time trajectory map, and the outliers are marked as potential abnormal points; for each potential abnormal point, the real-time trajectory segment and the corresponding historical trajectory segment in the area around the potential abnormal point are extracted; the angular deviation between the real-time trajectory segment and the historical trajectory segment is calculated, and the angular deviation is compared with the preset deviation threshold; if the angular deviation is greater than the preset deviation threshold, the potential abnormal point is determined to be an abnormal positioning point, otherwise, the potential abnormal point is determined to be a non-abnormal positioning point.

[0151] Furthermore, the trajectory area division module 304 is specifically used for:

[0152] The real-time trajectory map is divided into regions according to a preset division rule to obtain a plurality of trajectory region maps; the number of positioning points of the real-time trajectory map is counted to obtain a first number of positioning points; for each trajectory region map, the number of positioning points in the trajectory region map is counted to obtain a second number of positioning points; the positioning point density of each trajectory region map is calculated according to the first number of positioning points and the second number of positioning points; for each trajectory region map, the abnormal positioning points and non-abnormal positioning points in the trajectory region map are counted to obtain a type distribution of positioning points.

[0153] Furthermore, the data quality assessment module 305 is specifically used for:

[0154] For the positioning point density and positioning point type distribution of each trajectory area map, feature extraction is performed on the positioning point density and the positioning point type distribution to obtain the positioning point density feature and the positioning point type distribution feature; feature alignment is performed on the positioning point density feature and the positioning point type distribution feature; the positioning point density feature and the positioning point type distribution feature after feature alignment are combined to obtain an input feature vector; the input feature vector is imported into the data quality assessment model to obtain the data quality level of the trajectory area map.

[0155] Furthermore, the map trajectory optimization device 300 also includes an evaluation model training module, which is specifically used for:

[0156] Obtain model training data, wherein the model training data is the density of positioning points, the distribution of positioning point types, and the quality level of historical data of the pre-collected historical trajectory area map; perform feature engineering on the density of positioning points, the distribution of positioning point types, and the quality level of historical data of the historical trajectory area map to obtain a historical input feature vector; import the historical input feature vector into a preset initial evaluation model to obtain a historical data prediction level, wherein the initial evaluation model is implemented based on a support vector machine algorithm; compare the historical data prediction level and the historical data quality level to obtain a prediction error, and iteratively update the initial evaluation model based on the prediction error until the model is fitted to obtain a trained data quality evaluation model.

[0157] Furthermore, the real-time trajectory correction module 306 is specifically used for:

[0158] According to the data quality level of each trajectory area map, the corresponding trajectory correction weight is obtained from the preset level weight mapping table to obtain the trajectory correction weight of each trajectory area map; for each trajectory area map, the positioning point coordinate sequence in the trajectory area map is obtained, and based on the positioning point coordinate sequence, the Kalman filter algorithm is used in combination with the trajectory correction weight of the trajectory area map to perform correction calculation on the trajectory point coordinates to obtain the corrected trajectory point coordinate sequence; based on the corrected trajectory point coordinate sequence of the trajectory area map, a trajectory area supplementary map of the trajectory area map is drawn, and trajectory correction is performed on the trajectory area map based on the trajectory area supplementary map; when all trajectory area maps have completed trajectory correction, a real-time trajectory map after correction is obtained.

[0159] Furthermore, the map trajectory optimization device 300 also includes a trajectory graph iteration optimization module, which specifically includes:

[0160] Based on the data quality levels of each trajectory area map, the average data quality level of the real-time trajectory map is calculated to obtain the first data quality level; the average data quality level of the real-time trajectory map after correction is calculated to obtain the second data quality level; the level difference between the first data quality level and the second data quality level is calculated, and the level difference is compared with a preset difference threshold; if the level difference is greater than the difference threshold, the ratio of the level difference to the difference threshold is calculated; the trajectory correction weight is adjusted according to the ratio of the level difference to the difference threshold, and the trajectory correction is re-performed using the adjusted trajectory correction weight until the level difference is less than or equal to the difference threshold, and the real-time trajectory map after correction is output.

[0161] In the above embodiment, the present application discloses a map trajectory optimization device, which belongs to the field of artificial intelligence technology. In view of the trajectory deviation problem caused by the existing reliance on real-time positioning, by combining the user's historical trajectory data with the real-time positioning data, using the outlier detection algorithm and the pre-trained data quality assessment model, the abnormal positioning points are effectively identified and classified. At the same time, based on the density and type distribution of the positioning points in the trajectory area, the correction weights are flexibly configured to accurately correct the real-time trajectory map. This application significantly improves the accuracy of trajectory drawing, solves the problem of inaccurate user trajectories caused by positioning deviations, improves the user experience of map applications, and improves the reliability and accuracy of positioning services.

[0162] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0163] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0164] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0165] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the map trajectory optimization method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0166] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the map trajectory optimization method.

[0167] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0168] In the above embodiment, the present application discloses a computer device, which belongs to the field of artificial intelligence technology. In view of the existing trajectory deviation problem caused by reliance on real-time positioning, by combining the user's historical trajectory data with the real-time positioning data, using anomaly detection algorithms and pre-trained data quality assessment models, abnormal positioning points can be effectively identified and classified. At the same time, based on the density and type distribution of positioning points in the trajectory area, correction weights are flexibly configured to accurately correct the real-time trajectory map. This application significantly improves the accuracy of trajectory drawing, solves the problem of inaccurate user trajectories caused by positioning deviations, improves the user experience of map applications, and improves the reliability and accuracy of positioning services.

[0169] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the map trajectory optimization method as described above.

[0170] In the above embodiment, the present application discloses a computer-readable storage medium, which belongs to the field of artificial intelligence technology. In view of the existing trajectory deviation problem caused by reliance on real-time positioning, by combining the user's historical trajectory data with the real-time positioning data, using anomaly detection algorithms and pre-trained data quality assessment models, abnormal positioning points are effectively identified and classified. At the same time, based on the density and type distribution of positioning points in the trajectory area, correction weights are flexibly configured to accurately correct the real-time trajectory map. This application significantly improves the accuracy of trajectory drawing, solves the problem of inaccurate user trajectories caused by positioning deviations, improves the user experience of map applications, and improves the reliability and accuracy of positioning services.

[0171] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0172] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0173] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A map trajectory optimization method, characterized in that: include: Acquire the user's real-time positioning data, and draw a real-time trajectory map based on the real-time positioning data; Obtaining historical trajectory data of the user, and drawing a historical trajectory graph according to the historical trajectory data; Based on the real-time trajectory map and the historical trajectory map, an outlier detection algorithm is used to classify the positioning points in the real-time trajectory map; Divide the real-time trajectory map into regions to obtain a plurality of trajectory region maps, and calculate the positioning point density and positioning point type distribution of each of the trajectory region maps; Based on the positioning point density and positioning point type distribution of each of the trajectory area graphs, using a pre-trained data quality assessment model, determining the data quality level of each of the trajectory area graphs; A trajectory correction weight is configured according to the data quality level, and the trajectory correction weight is used to perform trajectory correction on the real-time trajectory map.

2. The map trajectory optimization method according to claim 1, characterized in that: The outlier detection algorithm is a density clustering algorithm, the classification of the positioning points includes abnormal positioning points and non-abnormal positioning points, and the step of using the outlier detection algorithm to classify the positioning points in the real-time trajectory map based on the real-time trajectory map and the historical trajectory map specifically includes: Constructing a spatial coordinate system, and importing the real-time trajectory map and the historical trajectory map into the spatial coordinate system for spatiotemporal registration; In the spatial coordinate system, the density clustering algorithm is used to detect outliers in the real-time trajectory graph, and the outliers are marked as potential abnormal points; For each of the potential abnormal points, extract the real-time trajectory segment and the corresponding historical trajectory segment in the area around the potential abnormal point; Calculating an angle deviation between the real-time trajectory segment and the historical trajectory segment, and comparing the angle deviation with a preset deviation threshold; If the angle deviation is greater than a preset deviation threshold, the potential abnormal point is determined to be an abnormal positioning point; otherwise, the potential abnormal point is determined to be a non-abnormal positioning point.

3. The map trajectory optimization method according to claim 2, characterized in that: The step of dividing the real-time trajectory map into regions to obtain a plurality of trajectory region maps, and calculating the density of positioning points and the distribution of positioning point types of each of the trajectory region maps specifically includes: Dividing the real-time trajectory map into regions according to a preset division rule to obtain a plurality of trajectory region maps; Counting the number of positioning points of the real-time trajectory graph to obtain a first number of positioning points; For each of the track area graphs, counting the number of positioning points in the track area graph to obtain a second number of positioning points; Calculating the density of the positioning points of each of the track area graphs according to the first number of positioning points and the second number of positioning points; For each of the trajectory area graphs, the abnormal positioning points and non-abnormal positioning points in the trajectory area graph are counted to obtain the positioning point type distribution.

4. The map trajectory optimization method according to claim 1, characterized in that: The step of determining the data quality level of each of the trajectory area graphs based on the density of the positioning points and the distribution of the positioning point types of each of the trajectory area graphs using a pre-trained data quality assessment model specifically includes: For each of the positioning point density and the positioning point type distribution of the trajectory area map, feature extraction is performed on the positioning point density and the positioning point type distribution to obtain positioning point density features and positioning point type distribution features; Performing feature alignment on the positioning point density feature and the positioning point type distribution feature; Combining the positioning point density feature and the positioning point type distribution feature after feature alignment to obtain an input feature vector; The input feature vector is imported into the data quality assessment model to obtain the data quality level of the trajectory area map.

5. The map trajectory optimization method according to claim 4, characterized in that: Before the step of determining the data quality level of each of the trajectory area graphs based on the positioning point density and the positioning point type distribution of each of the trajectory area graphs using a pre-trained data quality assessment model, the step further includes: Acquire model training data, wherein the model training data is the density of positioning points, the distribution of positioning point types, and the quality level of historical data of the pre-collected historical trajectory area map; Performing feature engineering processing on the density of positioning points, the distribution of positioning point types, and the quality level of historical data of the historical trajectory area map to obtain a historical input feature vector; Importing the historical input feature vector into a preset initial evaluation model to obtain a historical data prediction level, wherein the initial evaluation model is implemented based on a support vector machine algorithm; The historical data prediction level and the historical data quality level are compared to obtain a prediction error, and the initial evaluation model is iteratively updated based on the prediction error until the model is fitted, thereby obtaining a trained data quality evaluation model.

6. The map trajectory optimization method according to claim 1, characterized in that: The step of configuring a trajectory correction weight according to the data quality level and using the trajectory correction weight to perform trajectory correction on the real-time trajectory map specifically includes: According to the data quality level of each of the track area maps, a corresponding track correction weight is obtained from a preset level weight mapping table to obtain the track correction weight of each of the track area maps; For each of the trajectory area maps, a coordinate sequence of the positioning points in the trajectory area map is obtained, and based on the coordinate sequence of the positioning points, a Kalman filter algorithm is used in combination with the trajectory correction weight of the trajectory area map to perform correction calculation on the trajectory point coordinates to obtain a corrected trajectory point coordinate sequence; Based on the trajectory point coordinate sequence after correction of the trajectory area map, drawing a trajectory area supplementary map of the trajectory area map, and performing trajectory correction on the trajectory area map based on the trajectory area supplementary map; When all trajectory area maps have completed trajectory correction, the corrected real-time trajectory map is obtained.

7. The map trajectory optimization method according to claim 6, characterized in that: After the step of obtaining a corrected real-time trajectory map after all trajectory area maps have completed trajectory correction, the method further includes: Based on the data quality levels of each of the trajectory area graphs, an average data quality level of the real-time trajectory graph is calculated to obtain a first data quality level; Calculating an average data quality level of the real-time trajectory graph after deviation correction to obtain a second data quality level; Calculating a level difference between the first data quality level and the second data quality level, and comparing the level difference with a preset difference threshold; If the level difference is greater than the difference threshold, calculating the ratio of the level difference to the difference threshold; The trajectory correction weight is adjusted according to the ratio of the level difference to the difference threshold, and the trajectory correction is re-performed using the adjusted trajectory correction weight until the level difference is less than or equal to the difference threshold, and a real-time trajectory map after correction is output.

8. A map trajectory optimization device, characterized in that: include: A real-time trajectory drawing module is used to obtain the real-time positioning data of the user and draw a real-time trajectory map according to the real-time positioning data; A historical trajectory drawing module is used to obtain the historical trajectory data of the user and draw a historical trajectory map according to the historical trajectory data; A positioning point classification module, used for classifying the positioning points in the real-time trajectory map by using an abnormal point detection algorithm based on the real-time trajectory map and the historical trajectory map; A track area division module, used for dividing the real-time track map into regions to obtain a plurality of track area maps, and calculating the positioning point density and the positioning point type distribution of each of the track area maps; A data quality assessment module, configured to determine the data quality level of each of the trajectory area graphs based on the density of the positioning points and the distribution of the positioning point types of each of the trajectory area graphs using a pre-trained data quality assessment model; The real-time trajectory correction module is used to configure a trajectory correction weight according to the data quality level, and use the trajectory correction weight to perform trajectory correction on the real-time trajectory map.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the map trajectory optimization method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the map trajectory optimization method according to any one of claims 1 to 7 are implemented.

Images