A personalized self-driving travel route planning method and system

Abstract

The present invention discloses a personalized self-driving travel route planning method and system, which relates to the technical field of intelligent travel. It includes obtaining user historical travel trajectory data, collecting real-time road condition data and weather information around the destination; using clustering analysis to extract the user preference feature matrix from the user historical travel trajectory data, constructing a geographical location-interest point association network, and using the community discovery algorithm to divide the geographical location-interest point association network to obtain a destination group that meets the user preferences; constructing a road network cost matrix, using an improved ant colony algorithm for path search, and generating candidate routes in combination with real-time road conditions; mapping the candidate routes to a rasterized map, comprehensively evaluating the candidate routes, and selecting the Pareto optimal solution as the recommended route. The present invention can improve the practicability and reliability of route planning, provide a reliable travel plan for users, and improve the travel experience and satisfaction of users.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent travel, and in particular to a personalized self-driving travel route planning method and system. Background Art

[0002] With the progress of technology and the in-depth development of informatization, intelligent travel and personalized tourism have gradually become important needs in modern society. In the field of self-driving travel, the emergence of intelligent route planning systems enables travelers to arrange their itineraries more efficiently. Traditional self-driving travel route planning methods mainly rely on static Geographic Information System (GIS) data, such as traffic networks, road conditions, etc., and combine simple path optimization algorithms for route recommendation. However, these traditional methods often ignore the user's personalized needs and the changes in real-time factors, resulting in the lack of pertinence of the recommended routes and being difficult to adapt to the travel preferences of different users and the changes in real-time road conditions.

[0003] In recent years, with the rapid development of big data, artificial intelligence (AI) and machine learning technologies, intelligent recommendation systems based on user historical data and real-time dynamic information have gradually entered the field of self-driving travel route planning. Many path planning methods in the prior art still rely on simple rules or static data and fail to fully mine the user's historical behavior data to establish a more accurate personalized preference model. For example, many existing systems can only recommend routes based on a single user input (such as the destination or the departure place), ignoring the user's diverse interest points and travel habits. In addition, although community discovery algorithms and clustering analysis have been applied in some recommendation systems, how to effectively combine these algorithms with factors such as real-time road conditions and weather is still a challenge. Therefore, how to provide a reasonable and efficient self-driving travel route planning method under the premise of comprehensively considering historical data, real-time data and personalized preferences is still an urgent problem in the current technology. Summary of the Invention

[0004] In view of the problems existing in the existing personalized self-driving travel route planning methods, the present invention is proposed. Therefore, the problem to be solved by the present invention is how to provide a personalized self-driving travel route planning method and system.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a personalized self-driving travel route planning method, which includes obtaining user historical travel trajectory data, collecting real-time road condition data and weather information around the destination;

[0007] Extract the user preference feature matrix from the user's historical travel trajectory data by using clustering analysis, construct a geographical location - point of interest association network, and use a community discovery algorithm to partition the geographical location - point of interest association network to obtain a destination group that meets the user's preferences;

[0008] Construct a road network cost matrix, use an improved ant colony algorithm for path search, and generate candidate routes in combination with real - time traffic conditions;

[0009] Map the candidate routes to a rasterized map, comprehensively evaluate the candidate routes, and select the Pareto optimal solution as the recommended route.

[0010] As a preferred solution of the personalized self - driving travel route planning method of the present invention, wherein: the obtaining of the user's historical travel trajectory data includes connecting with the user's intelligent device to obtain the stored travel records, and for users using specific travel service applications, obtaining the user's itinerary data from the platform's database;

[0011] The collecting of the real - time traffic conditions data and weather information around the destination includes integrating the real - time traffic conditions data from multiple map service providers and obtaining the real - time weather data around the destination from a meteorological data service provider.

[0012] As a preferred solution of the personalized self - driving travel route planning method of the present invention, wherein: the extracting of the user preference feature matrix includes,

[0013] Calculate the straight - line distance between the starting point and the ending point of each user's trip to obtain the travel distance data, statistically analyze the travel distance data, and calculate the average travel distance to form the user's travel distance feature;

[0014] Analyze the location information of the stop points in the user's historical trajectory, combine the data of the geographic information system and the online travel platform, determine the scenic spot type to which the stop points belong, count the number of stops and the stop time of the user in different scenic spot types, and divide the user's preference degree for different scenic spot types to form the scenic spot type feature;

[0015] Analyze the driving speed, acceleration, and deceleration mode data in the user's historical travel trajectory, extract the user's driving habit features, and form the driving habit features;

[0016] Integrate the extracted user travel distance features, scenic spot type features, and driving habit features into a user preference feature matrix;

[0017] Use the K - means clustering algorithm to perform clustering analysis on the user preference feature matrix. According to the data in the user preference feature matrix, divide the users into different clustering clusters, and each clustering cluster represents a user group with similar preference features.

[0018] As a preferred solution of the personalized self-driving travel route planning method described in the present invention, wherein: the obtaining of the destination group meeting the user's preferences includes the following steps,

[0019] Integrate the tourism scenic spot database to obtain the location information and scenic spot types of the scenic spots, screen out the points of interest in the region from the data of the geographic information system and the online tourism platform, and determine the initial importance weights of the points of interest according to the types, popularity and user evaluations of the points of interest;

[0020] For every two points of interest, calculate the geographical distance between the points of interest, and determine the geographical location association strength between the points of interest according to the magnitude of the geographical distance, and construct a geographical location association matrix;

[0021] Based on the user preference feature matrix and the attribute information of the points of interest, calculate the similarity between every two points of interest, and the calculation formula is:

[0022] ;

[0023] In the formula, is the feature vector of point of interest A, is the feature vector of point of interest B, and S is the similarity between point of interest A and point of interest B;

[0024] Construct an association network, with the points of interest as nodes, and use the geographical location association strength and the point of interest similarity as the weights of the edges to construct a geographical location-point of interest association network;

[0025] Adopt an improved community discovery algorithm to perform community division on the geographical location-point of interest association network, match the preference characteristics of the target user group with the community division results, determine the destination group meeting the preferences of the target user group, and optimize the community division by maximizing the modularity. The formula is:

[0026] ;

[0027] Among them, Q is the community modularity, is the adjacency matrix of the network, indicating the edge weight between node i and node j, and are the degrees of node i and node j, m is the sum of the weights of all edges in the network, γ is the resolution parameter, is the Kronecker function, which is 1 when node i and node j belong to the same community, and 0 otherwise;

[0028] Dynamically adjust the edge weights according to the real-time road conditions, and the adjustment formula is:

[0029] ;

[0030] Among them, is the adjusted edge weight, is the initial static edge weight, and w(t) is the real-time data, is the weight coefficient;

[0031] Calculate the matching probability between the target user group and each community. The formula is:

[0032] ;

[0033] where, is the matching probability between the target user group and community c, is the preference feature vector of the target user group, is the preference feature vector of the point of interest z in the community.

[0034] As a preferred solution of the personalized self-driving travel route planning method described in the present invention, wherein: the generation of candidate routes includes the following steps,

[0035] Collect road network data in the target area, analyze road accident records in the area, and calculate the accident rate of each section of the road;

[0036] Construct a basic road network cost matrix according to road grade, traffic capacity, and accident rate parameters;

[0037] Use the real-time traffic condition API of the traffic sensor network and map service provider to obtain the real-time traffic condition data of the current road, and calculate the real-time travel time and congestion degree of each section of the road;

[0038] Combine the basic road network cost matrix and real-time traffic condition data to formulate a dynamic adjustment strategy for the road network cost. The formula is:

[0039] ;

[0040] where, is the road network cost at time t after dynamic adjustment, is the basic road network cost, is the additional cost brought by real-time traffic conditions, is the weight parameter;

[0041] Set the basic parameters of the ant colony algorithm, comprehensively consider real-time traffic condition factors and historical path experience, and introduce a pheromone update factor. The formula is:

[0042] ;

[0043] where F is the pheromone update factor, is the real-time travel time, is the historical average travel time, is the cost of historical path experience, is the weight parameter;

[0044] Starting from the starting point, each ant selects the next node according to the basic road network cost matrix and pheromone concentration, following the probability rule. The formula is:

[0045] ;

[0046] Where, is the path selection probability of selecting the next node j, is the set of next nodes that ant k can select when at node i, and l is any node in the set of next nodes ; is the pheromone concentration on the edge (i, j) at time t, is the pheromone weight, is the heuristic information of the edge (i, j), and β is the heuristic information weight, is the pheromone concentration on the edge (i, l) at time t, is the heuristic information of the edge (i, l);

[0047] After an ant completes a path exploration, the pheromone on the path is updated according to the pheromone update factor. After multiple iterations, multiple candidate routes are generated. After the path search ends, the pheromone on the optimal path is globally enhanced. The formula is:

[0048] ;

[0049] Where, is the enhanced pheromone concentration on the optimal path, is the amount of pheromone increased on the edge (i, j) of the optimal path; is the pheromone evaporation coefficient;

[0050] During the movement of the ant, the pheromone on the current edge is locally updated. The formula is:

[0051] ;

[0052] Where, is the enhanced pheromone concentration during the movement of the ant, is the amount of pheromone increased each time the ant passes through the edge (i, j).

[0053] As a preferred solution of the personalized self-driving travel route planning method described in the present invention, wherein: mapping the candidate route to the rasterized map includes the following steps,

[0054] Collect the geographical information data of the target geographical area, and determine the appropriate raster size according to the size and resolution requirements of the geographical area;

[0055] Divide the geographical area into multiple grids to form a grid map, and obtain multiple candidate routes from the path planning algorithm;

[0056] Convert the geographical coordinates of each road node in the candidate route into corresponding grid coordinates, and represent the route as connected grids according to the grid coordinates of the nodes to generate a grid matrix.

[0057] As a preferred solution of the personalized self-driving travel route planning method described in the present invention, wherein: the comprehensive evaluation of the candidate routes includes the following steps,

[0058] Collect scenic spot information within the target geographical area, convert the longitude and latitude coordinates of the scenic spots into corresponding grid coordinates, and determine the grids where the scenic spots are located;

[0059] For each candidate route, calculate the scenic spot coverage rate, average road condition score, and average safety factor included in the grids passed by the route according to the grid matrix and the scenic spot grid association information;

[0060] Take the scenic spot coverage rate, road condition score, and safety factor as the objectives of a multi-objective optimization problem, and construct a mathematical model;

[0061] Use a multi-objective optimization algorithm to comprehensively evaluate the candidate routes, find the set of Pareto optimal solutions, select the final recommended route according to the user's preferences or specific needs, and dynamically update the route recommendation results according to the user's usage feedback and real-time road condition changes.

[0062] In a second aspect, the present invention provides a personalized self-driving travel route planning system, which includes:

[0063] An acquisition module for acquiring the user's historical travel trajectory data, collecting the real-time road condition data and weather information around the destination;

[0064] An analysis module for extracting the user preference feature matrix from the user's historical travel trajectory data by using clustering analysis, constructing a geographical location-interest point association network, and dividing the geographical location-interest point association network by using a community discovery algorithm to obtain a destination group that meets the user's preferences;

[0065] A construction module for constructing a road network cost matrix, performing path search by using an improved ant colony algorithm, and generating candidate routes in combination with real-time road conditions;

[0066] A recommendation module for mapping the candidate routes to a grid map, comprehensively evaluating the candidate routes, and selecting the Pareto optimal solution as the recommended route.

[0067] The beneficial effects of the present invention are that it can deeply explore users' travel habits and preferences, ensure the smoothness and safety of travel, improve the practicality and reliability of route planning, generate multiple candidate routes that meet users' needs and real-time road conditions, provide reliable travel plans for users, and improve users' travel experience and satisfaction. Detailed implementation manners

[0068] To make the above objects, features, and advantages of the present invention more understandable, the specific implementation manners of the present invention will be described in detail. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0069] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0070] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is separate or selectively mutually exclusive with other embodiments.

[0071] This is the first embodiment of the present invention, which provides a personalized self-driving travel route planning method, including:

[0072] S1: Obtain users' historical travel trajectory data, collect real-time road condition data and weather information around the destination;

[0073] Specifically, by connecting to users' intelligent devices (such as mobile phones, in-vehicle navigation systems, etc.), the travel records stored therein are obtained. These records are usually recorded by the positioning system of the device (such as GPS) at regular time intervals (for example, every 10 seconds) with location information including longitude, latitude, and altitude. For users who use specific travel service applications (such as online car-hailing platforms), the travel data of the users can also be obtained from the platform's database, and these data may contain more detailed travel information, such as the specific addresses of the departure and destination.

[0074] Extract the start time of each trip from the records, accurate to the minute or even the second. This helps analyze the user's travel time patterns, such as whether it is during the peak commuting hours on weekdays or for leisure travel on weekends. By analyzing the changes in location information, when the device stays at a certain location for a period of time (which can be judged based on speed and location changes, for example, the speed remains 0 and the location remains basically unchanged for more than 5 minutes), record this location as a stop point. At the same time, record the arrival time and departure time of the stop point, as well as the geographical coordinates of the stop point. Calculate based on consecutive location recording points. The distance can be obtained by calculating the geographical distance between two consecutive location points (using formulas for latitude and longitude coordinates, such as the Haversine formula).

[0075] Collect real-time traffic condition data and integrate real-time traffic condition data from multiple map service providers (such as AutoNavi Map, Baidu Map, etc.). These providers analyze traffic conditions through users' map usage data (such as real-time location and speed information when users turn on navigation) and traffic camera data, and provide it to other applications in the form of an API (Application Programming Interface) for use.

[0076] Collect weather information and obtain real-time weather data around the destination from professional meteorological data service providers (such as the National Meteorological Center, commercial meteorological companies, etc.). The data includes information such as temperature, humidity, precipitation probability, wind speed, and wind direction. Meteorological data is usually collected comprehensively through various means such as meteorological satellites and ground meteorological observation stations, and will be updated according to real-time meteorological changes.

[0077] Clean the collected user historical travel trajectory data to remove abnormal data points (such as points that deviate significantly from the normal path due to positioning errors) and duplicate data points. By setting reasonable thresholds (such as speed thresholds, distance thresholds, etc.), identify and eliminate data points that do not conform to normal travel patterns to ensure the accuracy and reliability of the data.

[0078] It can deeply explore users' travel habits and preferences, provide a basis for constructing a user preference feature matrix, make the subsequent planned routes more in line with users' actual needs, provide real-time environmental factor considerations for route planning. For example, if the traffic conditions around the destination are congested or the weather is bad, the route can be adjusted in advance to avoid unnecessary troubles for users during travel and ensure the smoothness and safety of travel. It provides important real-time constraint conditions for path search and improves the practicality and reliability of route planning.

[0079] S2: Use clustering analysis to extract the user preference feature matrix from the user historical travel trajectory data, construct a geographical location - point of interest association network, and use the community discovery algorithm to divide the geographical location - point of interest association network to obtain destination groups that meet user preferences;

[0080] Specifically, for the extraction of the user's travel distance feature, calculate the straight-line distance between the starting point and the ending point of each user trip to obtain travel distance data. Conduct statistical analysis on these travel distance data and calculate the average travel distance to reflect the user's preference characteristics in terms of travel distance.

[0081] For the extraction of scenic spot type features, combine Geographic Information System (GIS) data and data from online travel platforms to classify the stop points in the user's historical travel trajectory and determine the scenic spot type to which the stop points belong (such as natural scenery, historical and cultural sites, theme parks, etc.). Statistically analyze the number of stops and the stop time of the user at different scenic spot types, and use these as indicators of the user's preference degree for different scenic spot types. For example, if the user has a relatively large number of stops and a relatively long stop time at natural scenery scenic spots, it indicates that the user has a high preference for natural scenery scenic spots.

[0082] For the extraction of driving habit features, analyze data such as the driving speed, acceleration, and deceleration patterns in the user's historical travel trajectory to extract the user's driving habit features. For example, calculate indicators such as the average driving speed of the user under different road conditions, the frequency of sudden acceleration and sudden deceleration. Through these indicators, the user's driving habits can be classified into different types, such as steady type, aggressive type, etc., providing a basis for subsequent analysis.

[0083] Integrate the extracted user travel distance features, scenic spot type features, and driving habit features into a user preference feature matrix. The rows of the matrix represent different feature dimensions (travel distance, scenic spot type, driving habit), and the columns represent different users. The value of each element represents the user's preference degree in the corresponding feature dimension, quantifying the user's preference characteristics in a numerical way and providing a data basis for cluster analysis.

[0084] Use the K-means clustering algorithm to conduct cluster analysis on the user preference feature matrix. According to the data in the user preference feature matrix, divide the users into different cluster clusters, and each cluster cluster represents a group of users with similar preference characteristics. Through cluster analysis, the commonalities and differences in the travel preferences of users can be discovered, providing a basis for the subsequent construction of the geographical location-interest point association network.

[0085] Take the scenic spots as the nodes of the network, and obtain the location information (latitude and longitude coordinates) and scenic spot type and other attributes of the scenic spots by integrating the tourism scenic spot database (such as scenic spot lists, scenic spot information on online travel platforms, etc.). From the Geographic Information System (GIS) data and data from online travel platforms, screen out the interest points within a certain area, and determine the initial importance weights of the interest points according to factors such as the type, popularity, and user evaluations of the interest points.

[0086] For every two points of interest, calculate the geographical distance between the points of interest (such as Euclidean distance or actual road distance). Based on the magnitude of the geographical distance, determine the geographical location association strength between the points of interest. The closer the geographical distance, the higher the association strength. By calculating the geographical location association strength between all points of interest, construct a geographical location association matrix.

[0087] Based on the user preference feature matrix and the attribute information of the points of interest (such as scenic spot type, special projects, etc.), calculate the similarity between every two points of interest. The calculation of similarity can adopt methods such as cosine similarity, Jaccard similarity coefficient, etc. According to the similarity degree of the points of interest in terms of user preferences and attribute information, determine the similarity value. The higher the similarity value, the more similar the two points of interest are in terms of user preferences and attributes, providing a basis for the subsequent construction of the association network; the calculation formula is:

[0088] ;

[0089] In the formula, is the feature vector of point of interest A, is the feature vector of point of interest B, is the similarity between point of interest A and point of interest B;

[0090] Construct an association network. Using the points of interest as nodes, and taking the geographical location association strength and the similarity of the points of interest as the weights of the edges, construct a geographical location - point of interest association network. In the network, the nodes represent the points of interest, the edges represent the association relationships between the points of interest, and the greater the weight of the edge, the closer the association between the two points of interest.

[0091] Use an improved community detection algorithm to perform community partitioning on the geographical location - point of interest association network. The improved community detection algorithm introduces a dynamic adjustment mechanism for edge weights on the basis of the traditional community detection algorithm. According to the changes in the association strength and similarity between the points of interest, dynamically adjust the weights of the edges, so that the community partitioning results can more accurately reflect the user preference characteristics.

[0092] Apply the improved community detection algorithm to partition the association network to obtain multiple communities. Each community represents a group of points of interest with similar user preference characteristics and geographical location associations. Through community partitioning, a large number of points of interest are classified to provide destination group recommendations that meet the user's preferences.

[0093] Based on the user's historical travel track data and preference feature matrix, determine the target user group. The target user group can be users with similar travel preference characteristics, or specific types of users (such as users who like natural scenery, users who like historical and cultural sites, etc.).

[0094] Match the preference characteristics of the target user group with the community division results to determine the destination groups that meet the preferences of the target user group. According to the user preference characteristic matrix and the characteristic information of the communities, calculate the matching degree between the target user group and each community. The higher the matching degree, the more the points of interest in the community meet the preferences of the target user group. Through the matching process, destination group recommendations that meet the user's preferences can be provided to the user to meet the user's personalized needs, and optimize the community division by maximizing the modularity.

[0095] ;

[0096] Among them, Q is the community modularity, is the adjacency matrix of the network, representing the edge weight between nodes i and j, and are the degrees of nodes i and j (the sum of the weights of the connected edges), m is the sum of the weights of all edges in the network, γ is the resolution parameter used to control the size of the community, is the Kronecker function, which is 1 when nodes i and j belong to the same community and 0 otherwise;

[0097] Dynamically adjust the edge weights according to the real-time road conditions, and the adjustment formula is:

[0098] ;

[0099] Among them, is the adjusted edge weight, is the initial static edge weight, w(t) is the real-time data, is the weight coefficient, which controls the degree of fusion of static and dynamic data;

[0100] Calculate the matching probability between the target user group and each community,

[0101] ;

[0102] Among them, is the matching probability between the target user group and community c, is the preference characteristic vector of the target user group, is the preference characteristic vector of the point of interest z in the community.

[0103] Achieve the precise quantification of the user's travel preferences and provide more personalized recommendations for the user. For example, if the user likes natural scenery, the geographical locations and points of interest containing natural scenery can be divided into the same community, so as to recommend destination groups that meet the user's preferences to the user and improve the accuracy and satisfaction of the recommendations.

[0104] S3: Construct a road network cost matrix, perform path search using an improved ant colony algorithm, and generate candidate routes in combination with real-time traffic conditions;

[0105] Specifically, collect and organize road network data within the target area, including information such as the length, grade (such as expressways, first-class highways, second-class highways, etc.), and traffic capacity (such as the number of vehicles passing through per hour) of roads. This data can be obtained from channels such as public databases of transportation departments and map service providers.

[0106] Analyze the road accident records in this area, and count the number of accidents on each section of the road within a certain period in the past. Calculate the accident rate of each section of the road based on information such as the number of accidents and traffic flow on the road. Roads with a high accident rate need to be treated with caution in subsequent path planning.

[0107] Construct a basic road network cost matrix based on parameters such as road grade, traffic capacity, and accident rate.

[0108] The road grade weight parameter is used to reflect the priority of different grade roads in path planning; the traffic capacity cost parameter represents the additional traffic cost caused by traffic capacity limitations on the road; the accident rate cost parameter is used to quantify the additional cost caused by accident risks on the road. Considering these three parameters comprehensively, a basic road network cost matrix is obtained, where the cost value of each section of the road is the weighted sum of the road grade weight, traffic capacity cost, and accident rate cost.

[0109] Utilize the real-time traffic conditions API of the traffic sensor network and map service providers to obtain data such as traffic flow, vehicle speed, and congestion conditions on the current road. The traffic sensor network includes devices such as traffic flow monitors and vehicle speed measuring instruments distributed along the road, and the real-time traffic conditions API can provide traffic condition analysis results based on user feedback and real-time traffic data.

[0110] Process and analyze the collected real-time traffic conditions data, and calculate indicators such as the real-time travel time and congestion degree of each section of the road. For example, according to the traffic flow and road capacity, the road saturation can be calculated; according to the vehicle speed and road speed limit, indicators such as the speed ratio can be calculated.

[0111] Combine the basic road network cost matrix and real-time traffic conditions data to formulate a dynamic adjustment strategy for the road network cost. Data such as traffic flow and vehicle speed in real-time traffic conditions will affect the travel time of sections, and accident rate data will affect the safety of sections. According to the real-time traffic conditions data, adjust the cost value of each section of the road in real-time to make it closer to the actual traffic situation. For example, when a section of the road is congested, its travel time increases, and the cost value of the section increases accordingly; when the accident rate of a section of the road rises, its safety risk increases, and the cost value of the section also increases accordingly. Combine the basic road network cost matrix and real-time traffic conditions data to dynamically adjust the section cost. The formula is:

[0112] ;

[0113] Among them, is the road network cost at time t after dynamic adjustment, is the basic road network cost, is the additional cost brought by real-time road conditions, is the weight parameter;

[0114] Set the basic parameters of the ant colony algorithm, including the number of ants, the initial concentration of pheromone, the pheromone evaporation coefficient, etc. The number of ants is determined according to the scale and complexity of the road network. The initial concentration of pheromone and the evaporation coefficient affect the convergence speed and global search ability of the algorithm. According to empirical formulas and experimental tests, appropriate initial parameter values are determined. The number of ants (N): determines the parallelism and search ability of the algorithm. The initial concentration of pheromone (τ): affects the degree of dependence of ants on historical information when choosing paths. The pheromone evaporation coefficient ( ): controls the dissipation rate of pheromone over time and avoids premature convergence of the algorithm. The weight of heuristic information (β): adjusts the sensitivity of path selection to distance or travel cost. The weight of pheromone ( ): balances the roles of pheromone and heuristic information in path selection.

[0115] Introduce a pheromone update factor, which comprehensively considers real-time road condition factors and historical path experience. The pheromone update factor is dynamically calculated based on data such as the real-time travel time and accident rate of the current section. For example, when the real-time travel time of a section is short and the accident rate is low, the pheromone update factor is large, indicating that this section should be given higher attention in path planning; otherwise, the pheromone update factor is small.

[0116] Comprehensively considering real-time road conditions and historical path experience, introduce a pheromone update factor (F), and its calculation formula is:

[0117] ;

[0118] Among them, F is the pheromone update factor, is the real-time travel time, is the historical average travel time, is the cost of historical path experience, is the weight parameter that controls the importance of real-time road conditions and historical experience.

[0119] Each ant starts from the starting point and selects the next node according to the basic road network cost matrix and pheromone concentration, following the probability rule. The selection probability is proportional to the pheromone concentration of the road section and inversely proportional to the cost of the road section. Specifically, the probability of an ant selecting a road section is jointly determined by the pheromone concentration and the road section cost. This makes the ant more inclined to select road sections with high pheromone concentration and low cost.

[0120] The probability of an ant selecting the next node is jointly determined by the pheromone concentration and heuristic information, and the formula is:

[0121] ;

[0122] where, is the path selection probability of selecting the next node j, is the set of next nodes that ant k can select when at node i, and l is any node in the set of next nodes ; is the pheromone concentration on the edge (i, j) at time t, is the pheromone weight, is the heuristic information of the edge (i, j), β is the heuristic information weight, is the pheromone concentration on the edge (i, l) at time t, is the heuristic information of the edge (i, l);

[0123] After an ant completes a path exploration, the pheromone on the path is updated according to the pheromone update factor. The pheromone evaporation amount is determined by the evaporation coefficient, and the pheromone increase amount is jointly determined by the cost of the path and the pheromone update factor. For paths with lower costs, the pheromone increase amount is larger; while for paths with poor real-time road conditions, the pheromone increase amount is smaller and may even decrease. It can quickly adapt to road condition changes, adjust the pheromone distribution, and guide subsequent ants to select better paths.

[0124] Global update: After the path search ends, the pheromone on the optimal path is strengthened, and the formula is:

[0125] ;

[0126] where, is the strengthened pheromone concentration on the optimal path, is the increased pheromone amount on the edge (i, j) of the optimal path; is the pheromone evaporation coefficient;

[0127] Local update: During the movement of the ant, the pheromone on the current edge is fine-tuned, and the formula is:

[0128]

[0129] Among them, is the pheromone concentration after enhancement during the movement of ants, is the amount of pheromone increased each time an ant passes through the edge (i, j);

[0130] After multiple iterations, the ant colony algorithm will generate multiple candidate routes. These paths are discovered by ants during the search process and have different costs and pheromone concentrations.

[0131] This enables a more accurate evaluation of the advantages and disadvantages of each road during the path search process, providing an important reference for path selection. Combining the global search ability and local search ability of the ant colony algorithm, it can quickly find the optimal path from the starting point to the ending point. The improved ant colony algorithm improves the convergence speed and search accuracy of the algorithm by introducing a pheromone update mechanism and heuristic information, making the searched path more in line with actual needs. If a certain road is congested or there is an accident, the path can be adjusted in a timely manner to avoid unnecessary delays for users during travel, generating multiple candidate routes that meet the user's needs and real-time road conditions, providing rich choices for comprehensive evaluation.

[0132] S4: Map the candidate routes to the rasterized map, conduct a comprehensive evaluation of the candidate routes, and select the Pareto optimal solution as the recommended route.

[0133] Specifically, collect geographical information data of the target geographical area, including regional boundaries, topography, urban distribution, etc., to provide basic reference data for the construction of the rasterized map.

[0134] Determine the appropriate grid size according to the size and resolution requirements of the geographical area. For example, in urban areas, a smaller grid (such as 100 meters × 100 meters) can be selected, and in suburban or rural areas, a larger grid (such as 500 meters × 500 meters) can be selected. Assign a unique number to each grid for subsequent data processing and analysis.

[0135] Divide the geographical area into multiple grids to form a rasterized map. Each grid represents a certain range of geographical space, and its position is determined by longitude and latitude coordinates or plane rectangular coordinates. The rasterized map can be stored as a digital map file for easy processing and analysis by a computer.

[0136] Obtain multiple candidate routes from the path planning algorithm. Each candidate route consists of a series of road nodes and the roads connecting them, representing the possible paths from the starting point to the ending point.

[0137] Convert the geographical coordinates (such as longitude and latitude) of each road node in the candidate route into the corresponding grid coordinates. Determine the grid to which each node belongs according to the numbering rule of the rasterized map.

[0138] According to the grid coordinates of the nodes, the entire route is represented as a series of connected grids. If two adjacent nodes are located in different grids, it is necessary to determine how the route is connected between the two grids, such as using an interpolation method or a geometric algorithm to generate a path between the grids.

[0139] A grid matrix is ​​generated for each candidate route, where the rows and columns of the matrix correspond to the grids in the rasterized map. The elements in the matrix indicate whether the grid is passed by the route, or record the specific situation of the route in the grid (such as the number of times it passes, the stay time, etc.).

[0140] Collect information about attractions in the target geographic area, including the name, location (latitude and longitude), type, etc. The location information of the attraction is used to determine its location in the rasterized map.

[0141] The latitude and longitude coordinates of each scenic spot are converted into corresponding grid coordinates to determine the grid where the scenic spot is located. In this way, each scenic spot is associated with one or more grids in the rasterized map.

[0142] For each candidate route, the number of attractions contained in the grids that the route passes through is calculated based on its grid matrix and the associated information of the attraction grids.

[0143] Attraction coverage rate = (the number of attractions included in the grids passed by the route) / (the total number of attractions in the geographical area) × 100%

[0144] Obtain real-time traffic data in the target geographic area, including road traffic volume, speed, congestion level, etc. This data is obtained from channels such as the real-time traffic API of the map service provider.

[0145] Based on the traffic data, a traffic score is calculated for each road section. For example, the traffic conditions can be divided into three levels: smooth, slow, and congested, according to the traffic volume and speed, and the corresponding scores are assigned (e.g., smooth is 100 points, slow is 70 points, and congested is 40 points).

[0146] For each candidate route, the average road condition score of the entire route is calculated based on the road segments it passes through and the road condition scores of the segments.

[0147] Average road condition score = (sum of road condition scores of road sections) / (number of road sections passed by the route)

[0148] Collect road safety data within the target geographic area, including road accident rates, road grades, and the degree of completeness of traffic facilities.

[0149] Based on safety data such as road grade and accident rate, the safety factor is calculated for each section of road.

[0150] Safety factor = Road grade weight × Road grade + Accident rate weight × (1 - Accident rate) / Maximum accident rate.

[0151] Among them, the road grade weight and accident rate weight are determined according to the actual situation. For example, they are set to 0.6 and 0.4 respectively.

[0152] For each candidate route, calculate the average safety factor of the entire route based on the road segments it passes through and the segment safety factors.

[0153] Average safety factor = (Sum of segment safety factors) / (Number of road segments the route passes through)

[0154] Take the scenic spot coverage rate, road condition score, and safety factor as the three objectives of the multi-objective optimization problem. Build a mathematical model, and the objective functions are to maximize the scenic spot coverage rate, maximize the road condition score, and maximize the safety factor. At the same time, consider constraints such as route length to ensure the feasibility of the route.

[0155] Use a multi-objective optimization algorithm (such as NSGA-II algorithm, MOPSO algorithm, etc.) to comprehensively evaluate the candidate routes and find the set of Pareto optimal solutions.

[0156] Select the final recommended route from the set of Pareto optimal solutions according to the user's preferences or specific needs. For example, if the user pays more attention to the scenic spot coverage rate, a Pareto optimal solution with a higher scenic spot coverage rate can be selected; if the user pays more attention to road conditions and safety, a Pareto optimal solution with a higher road condition score and safety factor can be selected.

[0157] Present the recommended route to the user in a visual way, draw the route on the map, and mark the scenic spot locations, road condition information, safety factor, etc. The user can intuitively understand the characteristics of the recommended route by viewing the visual results, provide the reasons for the recommended route, and dynamically update the route recommendation results according to the user's usage feedback and real-time road condition changes. If the user feedbacks that a certain route does not meet expectations, or there are significant changes in the real-time road conditions, the path planning and optimization can be redone to provide the user with better travel suggestions.

[0158] The recommended route not only meets the user's preferences, but also has good road conditions and safety, providing the user with comprehensive and objective evaluation results, and improving the user's travel experience and satisfaction.

[0159] Furthermore, this embodiment also provides a personalized self-driving travel route planning system, including:

[0160] An acquisition module, used to acquire the user's historical travel trajectory data, collect the real-time road condition data and weather information around the destination;

[0161] An analysis module, configured to extract a user preference feature matrix from user historical travel trajectory data by using clustering analysis, construct a geographical location - point of interest association network, and divide the geographical location - point of interest association network by using a community discovery algorithm to obtain a destination group that meets user preferences;

[0162] A construction module, configured to construct a road network cost matrix, perform path search by using an improved ant colony algorithm, and generate candidate routes in combination with real - time traffic conditions;

[0163] A recommendation module, configured to map candidate routes to a rasterized map, comprehensively evaluate the candidate routes, and select a Pareto optimal solution as a recommended route.

[0164] This embodiment further provides a computer device, applicable to the case of a personalized self - driving travel route planning method, including: a memory and a processor; the memory is used to store computer - executable instructions, and the processor is used to execute the computer - executable instructions to implement all or part of the steps of the method described in the embodiment of the present invention as proposed in the above - mentioned embodiment.

[0165] This embodiment further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, it executes the method in any optional implementation manner of the above - mentioned embodiment. Among them, the storage medium can be implemented by any type of volatile or non - volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read - Only Memory (EEPROM for short), Erasable Programmable Read - Only Memory (EPROM for short), Programmable Read - Only Memory (PROM for short), Read - Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk or an optical disc.

[0166] The storage medium proposed in this embodiment and the data storage method proposed in the above - mentioned embodiment belong to the same inventive concept. Technical details not described in detail in this embodiment can be referred to in the above - mentioned embodiment, and this embodiment has the same beneficial effects as the above - mentioned embodiment.

[0167] In summary, the present invention can deeply explore users' travel habits and preferences, ensure the smoothness and safety of travel, improve the practicality and reliability of route planning, generate multiple candidate routes that meet user needs and real - time traffic conditions, provide a reliable travel plan for users, and improve users' travel experience and satisfaction.

Claims

1. A personalized self-driving travel route planning method, characterized by: include, Obtain the user's historical travel trajectory data and collect real-time traffic data and weather information around the destination; Using cluster analysis to extract user preference feature matrix from user historical travel trajectory data, constructing a geographic location-point of interest association network, and using community discovery algorithm to divide the geographic location-point of interest association network to obtain destination groups that meet user preferences; The obtaining of a destination group that meets the user's preference comprises the following steps: Integrate the tourist attraction database to obtain the location information and attraction types of the scenic area, filter out the points of interest in the area from the geographic information system data and the data of the online travel platform, and determine the initial importance weight of the points of interest based on the type, popularity and user evaluation of the points of interest; For every two points of interest, the geographical distance between the points of interest is calculated, and the geographical location association strength between the points of interest is determined according to the size of the geographical distance, and a geographical location association matrix is ​​constructed; Based on the user preference feature matrix and the attribute information of the points of interest, the similarity between every two points of interest is calculated using the following formula: ； In the formula, is the feature vector of interest point A, is the feature vector of interest point B, is the similarity between interest point A and interest point B; Construct an association network, take points of interest as nodes, use the geographic location association strength and the similarity of points of interest as the weight of the edge, and construct a geographic location-point of interest association network; The improved community discovery algorithm is used to divide the geographic location-point of interest association network into communities, and the preference characteristics of the target user group are matched with the community division results to determine the destination group that meets the preferences of the target user group. The community division is optimized by maximizing the modularity. The formula is: ； Among them, Q is the community modularity, is the adjacency matrix of the network, which represents the edge weight between node i and node j. and is the degree of node i and node j, m is the sum of the weights of all edges in the network, γ is the resolution parameter, is the Kronecker function, which is 1 when nodes i and j belong to the same community, otherwise it is 0; The edge weight is dynamically adjusted according to the real-time traffic conditions. The adjustment formula is: ； in, is the adjusted edge weight, is the initial static edge weight, w(t) is the real-time data, is the weight coefficient; Calculate the matching probability between the target user group and each community. The formula is: ； in, is the matching probability between the target user group and community c, is the preference feature vector of the target user group, is the preference feature vector of interest point z in the community; Construct a road network cost matrix, use an improved ant colony algorithm to search for paths, and generate candidate routes based on real-time traffic conditions; Map the candidate routes to the rasterized map, conduct a comprehensive evaluation on the candidate routes, and select the Pareto optimal solution as the recommended route; The comprehensive evaluation of the candidate routes comprises the following steps: Collect information on scenic spots in the target geographic area, convert the latitude and longitude coordinates of the scenic spots into corresponding grid coordinates, and determine the grid where the scenic spots are located; For each candidate route, the coverage rate of scenic spots, the average road condition score and the average safety factor contained in the grids passed by the route are calculated according to the grid matrix and the associated information of scenic spots grids; Taking scenic spot coverage, road condition score and safety factor as the objectives of multi-objective optimization problem, a model was constructed; A multi-objective optimization algorithm is used to comprehensively evaluate candidate routes and find the Pareto optimal solution set. The final recommended route is selected based on user preferences or specific needs, and the route recommendation results are dynamically updated based on user feedback and real-time traffic changes.

2. The personalized self-driving travel route planning method according to claim 1, characterized in that: The obtaining of the user's historical travel trajectory data includes obtaining the stored travel records by connecting with the user's smart device, and for users using travel service applications, obtaining the user's travel data from the platform's database; The collecting of real-time traffic data and weather information around the destination includes integrating real-time traffic data from multiple map service providers and acquiring real-time weather data around the destination from a meteorological data service provider.

3. The personalized self-driving travel route planning method according to claim 2, characterized in that: The extracting of the user preference feature matrix comprises: Calculate the straight-line distance between the starting point and the end point of each user's trip to obtain travel distance data, statistically analyze the travel distance data, calculate the average travel distance, and form the user's travel distance characteristics; Analyze the location information of the stopover points in the user's historical travel trajectory data, combine the geographic information system data and the data of the online travel platform to determine the type of scenic spot to which the stopover point belongs, count the number of times and duration of users' stops at different types of scenic spots, divide the user's preference for different types of scenic spots, and form the characteristics of scenic spot types; Analyze the driving speed, acceleration and deceleration pattern data in the user's historical travel trajectory data, extract the user's driving habit characteristics, and form a driving habit feature; Integrate the extracted user travel distance features, scenic spot type features, and driving habit features into a user preference feature matrix; The K-means clustering algorithm is used to perform cluster analysis on the user preference feature matrix. According to the data in the user preference feature matrix, the users are divided into different clusters, and each cluster represents a user group with similar preference characteristics.

4. The personalized self-driving travel route planning method according to claim 3, characterized in that: Generating candidate routes comprises the following steps: Collect road network data in the target area, analyze road accident records in the area, and calculate the accident rate of each road section; Construct the basic road network cost matrix according to road grade, traffic capacity and accident rate parameters; Use the traffic sensor network and the real-time traffic API of the map service provider to obtain the real-time traffic data of the current road and calculate the real-time travel time and congestion level of each road section; Combined with the basic road network cost matrix and real-time traffic data, a dynamic adjustment strategy for the road network cost is formulated. The formula is: ； in, is the road network cost at time t after dynamic adjustment, is the basic road network cost, It is the extra cost brought by real-time traffic conditions. is the weight parameter; The basic parameters of the ant colony algorithm are set, and the real-time traffic conditions and historical path experience are comprehensively considered. The pheromone update factor is introduced. The formula is: ； Where F is the pheromone renewal factor, is the real-time transit time. is the historical average travel time, It is the price of historical experience. is the weight parameter; Each ant starts from the starting point and selects the next node according to the probability rule based on the basic road network cost matrix and pheromone concentration. The formula is: ； in, is the path selection probability of selecting the next node j, is the set of next nodes that ant k can choose when it is at node i, l is the set of next nodes Any node in is the pheromone concentration on edge (i, j) at time t, is the pheromone weight, is the heuristic information of edge (i, j), β is the heuristic information weight, is the pheromone concentration on the edge (i, l) at time t, is the heuristic information of edge (i,l); After the ant completes a path exploration, the pheromone on the path is updated according to the pheromone update factor. After multiple iterations, multiple candidate routes are generated. After the path search is completed, the pheromone on the optimal path is globally enhanced. The formula is: ； in, is the enhanced pheromone concentration on the optimal path, is the amount of pheromone added to the edge (i, j) on the optimal path; is the pheromone volatility coefficient; During the movement of ants, the pheromone on the current edge is locally updated, and the formula is: ； in, is the pheromone concentration after the ants move. is the amount of pheromone added each time an ant passes through edge (i, j).

5. The personalized self-driving travel route planning method according to claim 4, characterized in that: Mapping the candidate routes to the rasterized map comprises the following steps: Collect geographic information data of the target geographic area and determine the appropriate grid size based on the size and resolution requirements of the geographic area; Divide the geographical area into multiple grids to form a grid map, and obtain multiple candidate routes from the path planning algorithm; The geographic coordinates of each road node in the candidate route are converted into corresponding grid coordinates, and the route is represented as a connected grid according to the grid coordinates of the node to generate a grid matrix.

6. A personalized self-driving travel route planning system, based on the personalized self-driving travel route planning method according to any one of claims 1 to 5, characterized in that: include: The acquisition module is used to obtain the user's historical travel trajectory data and collect real-time traffic data and weather information around the destination; An analysis module is used to extract a user preference feature matrix from the user's historical travel trajectory data using cluster analysis, construct a geographic location-point of interest association network, and divide the geographic location-point of interest association network using a community discovery algorithm to obtain a destination group that meets the user's preferences; The construction module is used to construct the road network cost matrix, use the improved ant colony algorithm to search for paths, and generate candidate routes based on real-time road conditions; The recommendation module is used to map candidate routes to a rasterized map, conduct a comprehensive evaluation of the candidate routes, and select the Pareto optimal solution as the recommended route.

Images