Intelligent guidance method, system, device and storage medium

Abstract

The present application provides an intelligent guidance method, system, device, and storage medium, the method comprising: obtaining user historical behavior data from a navigation system database to generate a user preference feature vector; obtaining a real-time traffic status parameter matrix based on a real-time monitoring mechanism, dynamically adjusting the weight configuration in path planning according to the real-time traffic status parameter matrix and the user preference feature vector, and generating an optimal weight configuration scheme; obtaining road network topology data to generate a set of candidate paths, comprehensively scoring the set of candidate paths according to the optimal weight configuration scheme, and generating a path priority ranking list; performing dynamic path adjustment according to the path switching timing judgment condition to generate a final optimized navigation path scheme. The present application dynamically adjusts the path weight configuration by combining real-time traffic status parameters and user preference characteristics to ensure that the recommended path not only conforms to user habits but also always adapts to current road conditions.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an intelligent guidance method, system, device and storage medium. Background Art

[0002] Traditional navigation systems often use fixed algorithms and evaluation criteria for route planning, making them difficult to adapt to the personalized needs of different users and the dynamically changing traffic environment. This can lead to significant discrepancies between recommended routes and actual user preferences, reducing the user experience. Furthermore, due to a lack of in-depth analysis and learning of user historical behavior, the system cannot accurately grasp users' travel habits and preferences, making it difficult to provide truly personalized navigation services. Furthermore, in complex and volatile urban traffic environments, the acquisition and processing of real-time traffic information is subject to lags, hindering the timeliness and accuracy of navigation decisions. When faced with unexpected situations such as traffic congestion and accidents, the system struggles to quickly adjust and optimize, potentially leaving users stranded in even worse traffic conditions. Furthermore, existing systems often only consider single factors, such as distance or time, when evaluating and recommending routes, ignoring multi-dimensional metrics that may be of concern to users, such as road comfort and scenic beauty, making it difficult to meet their comprehensive needs. These combined issues result in low navigation system accuracy and user satisfaction, hindering the provision of a truly intelligent and personalized travel experience. Summary of the Invention

[0003] To solve the above problems, in a first aspect, the present invention provides an intelligent guidance method, which mainly includes:

[0004] Obtain user historical behavior data from the navigation system database, and generate a user preference feature vector based on the user historical behavior data; set a personalized traffic flow threshold according to the user preference feature vector, start a real-time monitoring mechanism, collect current traffic status data, and generate a real-time traffic status parameter matrix; use a gradient descent algorithm to dynamically adjust the time cost weight, distance cost weight, and congestion cost weight in path planning for the real-time traffic status parameter matrix and the user preference feature vector to generate an optimal weight configuration scheme; obtain road network topology data, generate a set of candidate paths, comprehensively score the candidate path set according to the optimal weight configuration, and generate a path priority ranking list; monitor the real-time traffic status of the recommended path according to the path priority ranking list, and if an anomaly is detected, generate a set of alternative paths and calculate the path switching timing judgment conditions, perform dynamic path adjustment according to the path switching timing judgment conditions, and generate a final optimized navigation path plan.

[0005] Furthermore, the step of obtaining user historical behavior data from the navigation system database and generating a user preference feature vector includes:

[0006] Extracting user historical behavior data from the navigation system database, wherein the user historical behavior data includes travel time distribution and route selection records;

[0007] Performing dimensionality reduction processing on the user's historical behavior data, extracting main feature components, and determining key patterns of user behavior;

[0008] Grouping user behaviors according to the key patterns to categorize time preferences, distance preferences, and congestion preferences;

[0009] A user preference feature vector is constructed according to the time preference component, the distance preference component, and the congestion preference.

[0010] Furthermore, the process of setting a personalized traffic flow threshold according to the user preference feature vector, starting a real-time monitoring mechanism, collecting current traffic status data, and generating a real-time traffic status parameter matrix includes:

[0011] Classifying users by using the user preference feature vector to determine the personalized traffic flow threshold;

[0012] If the personalized traffic flow threshold is determined, the real-time monitoring mechanism is activated to collect current traffic flow, road congestion index and weather environment data to construct a real-time collection data set;

[0013] Extracting traffic flow change trends, congestion index fluctuation characteristics and weather impact weights based on the real-time collected data set;

[0014] If the traffic flow component exceeds the personalized traffic flow threshold, the dynamic analysis module is triggered to generate a real-time traffic status parameter matrix including a travel speed component, a congestion index component and a weather impact component.

[0015] Furthermore, the method uses a gradient descent algorithm to dynamically adjust the time cost weight, distance cost weight, and congestion cost weight in path planning based on the real-time traffic status parameter matrix and the user preference feature vector to generate an optimal weight configuration scheme, including:

[0016] Based on the real-time traffic status parameter matrix, the time cost, distance cost and congestion cost related data of the current road are obtained to obtain the initial cost distribution characteristics;

[0017] Determine the comprehensive cost calculation model by combining the initial cost distribution characteristics with the user preference feature vector;

[0018] The gradient descent algorithm is used to dynamically adjust the adjustment range of the calculation time cost weight, distance cost weight, and congestion cost weight to generate a preliminary weight configuration combination;

[0019] If the comprehensive cost of the preliminary weight configuration combination exceeds a preset threshold, the preliminary weight configuration combination is updated to generate an optimal weight configuration scheme.

[0020] Furthermore, the acquiring of the road network topology data, generating a set of candidate paths, comprehensively scoring the set of candidate paths according to the optimal weight configuration, and generating a path priority ranking list includes:

[0021] Extracting the road network topology data and node connection relationship data from a preset database to construct an initial path network model;

[0022] According to the initial path network model, a graph traversal algorithm is used to generate a set of candidate paths;

[0023] The candidate path set is comprehensively scored according to the optimal weight configuration to generate a path priority ranking list.

[0024] Furthermore, the real-time traffic status of the recommended path is monitored according to the path priority list. If an anomaly is detected, a set of alternative paths is generated and a path switching timing judgment condition is calculated. Dynamic path adjustment is performed according to the path switching timing judgment condition to generate a final optimized navigation path solution, including:

[0025] Acquire the real-time traffic status data, extract the real-time traffic status parameter matrix, and analyze the trend of road condition changes;

[0026] If the traffic condition change trend shows abnormal fluctuations, it is determined that there is a traffic emergency; if the congestion probability value exceeds a preset threshold, a traffic emergency flag is generated;

[0027] Extracting the set of alternative paths according to the traffic emergency identifier, and sorting the set of alternative paths;

[0028] The event severity score is extracted to determine whether a path switching condition is met. If the path switching condition is met, the highest priority path is extracted from the set of candidate paths to generate an updated recommended path.

[0029] In a second aspect, the present application provides an intelligent guidance system, the system comprising:

[0030] A user preference feature vector generation module, which obtains user historical behavior data from a navigation system database and generates a user preference feature vector based on the user historical behavior data;

[0031] A real-time traffic state parameter matrix generation module sets a personalized traffic flow threshold according to the user preference feature vector, activates a real-time monitoring mechanism, collects current traffic state data, and generates a real-time traffic state parameter matrix;

[0032] An optimal weight configuration scheme generation module, which uses a gradient descent algorithm to dynamically adjust the time cost weight, distance cost weight, and congestion cost weight in path planning based on the real-time traffic state parameter matrix and the user preference feature vector to generate an optimal weight configuration scheme;

[0033] a path priority ranking list generating module, which obtains road network topology data, generates a set of candidate paths, comprehensively scores the set of candidate paths according to the optimal weight configuration, and generates a path priority ranking list;

[0034] The final optimized navigation path solution generation module monitors the real-time traffic status of the recommended path according to the path priority list. If an anomaly is detected, it generates a set of alternative paths and calculates the path switching timing judgment conditions. According to the path switching timing judgment conditions, dynamic path adjustment is performed to generate the final optimized navigation path solution.

[0035] In a third aspect, the present application provides an intelligent boot device, which includes: a memory, a processor, and an intelligent boot program stored in the memory and executable on the processor, wherein the intelligent boot program is configured to implement the intelligent boot method as described above.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, on which an intelligent boot program is stored. When the intelligent boot program is executed by a processor, the intelligent boot method as described above is implemented.

[0037] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0038] The present invention discloses an intelligent navigation method based on user preferences. It generates preference feature vectors by analyzing user historical behavior data, sets personalized traffic flow thresholds and monitors road conditions in real time. When the threshold is exceeded, a dynamic analysis module is triggered to generate a traffic status parameter matrix. In combination with user preferences and real-time road conditions, the present invention adopts a gradient descent algorithm to dynamically adjust the path planning weights, constructs an optimal weight configuration scheme, and comprehensively scores and ranks candidate paths. The system continuously monitors the status of recommended paths, generates alternative paths when necessary, and determines the switching timing to obtain the final output optimized navigation solution. By analyzing historical behavior data to generate feature vectors, path planning is tailored to the user's individual habits; combining user preferences with real-time traffic parameters, the path weights are dynamically adjusted to avoid the "one-size-fits-all" recommendation of traditional navigation; by continuously monitoring traffic changes, candidate paths are automatically re-evaluated when preset conditions (such as congestion worsening beyond a threshold) are triggered, reducing the need for user intervention in manual adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1A specific flow chart of an intelligent guidance method of the present invention;

[0040] Figure 2 This is a specific flow chart of step S103 of the intelligent guidance method in this embodiment;

[0041] Figure 3 Schematic diagram of the structure of an intelligent guidance system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] like Figure 1 In this embodiment, an intelligent guidance method may specifically include:

[0044] S101, acquiring user historical behavior data from a navigation system database, and generating a user preference feature vector based on the user historical behavior data;

[0045] In this embodiment, user historical behavior data is obtained, which includes travel time distribution, route selection records and speed change sequences. Multidimensional features are extracted through principal component analysis and clustering algorithm to generate a user preference feature vector. The user preference feature vector includes a time preference component, a distance preference component and a congestion preference component.

[0046] Furthermore, historical user behavior data is extracted from the navigation system database. The data covers travel time distribution and route selection records, and an initial data set is constructed to obtain a multidimensional information set of user behavior. Based on the initial data set, the multidimensional information of user behavior is standardized to eliminate the dimensional differences between data of different dimensions, and a normalized data matrix is ​​obtained. The principal component analysis method is used to reduce the dimensionality of the normalized data matrix, extract the main characteristic components, and obtain a feature data set after dimensionality reduction. The feature data set after dimensionality reduction is grouped and analyzed using a clustering algorithm to divide the categories of time preference, distance preference, and congestion preference to obtain the classification results of user behavior. Based on the classification results, the core characteristic values ​​of user behavior in each category are calculated, and a feature vector containing the time preference component, distance preference component, and congestion preference component is constructed to obtain the user preference feature vector.

[0047] Specifically, historical user behavior data was extracted from the navigation system database. SQL queries were used to filter travel records from the past six months. This data was used to obtain travel time distribution data, such as a 35% morning peak period and a 28% evening peak period. Route selection records included the ID and frequency of the route selected by the user, and a speed change sequence recorded vehicle speed changes, sampled once per second. The initial dataset was Z-score normalized, with dimensions such as travel time, route frequency, and average speed normalized to the range [-1, 1]. Principal component analysis (PCA) was performed with a variance contribution threshold of 85%, and the first three principal components were extracted as feature components, generating a dimensionality-reduced dataset containing 92% of the cumulative variance. The K-means clustering algorithm was used with a set number of clusters (k=3). Cluster centers were iteratively calculated based on Euclidean distance, and the clusters were divided into time preference categories (e.g., concentrated commuting time), distance preference categories (e.g., short distance preference with a 60% probability), and congestion preference categories (e.g., a probability of escaping congestion of 0.2). The coordinates of each cluster center were calculated based on the clustering results, and user preference feature vectors were constructed, corresponding to time preference, distance preference, and user preference, respectively.

[0048] S102, setting a personalized traffic flow threshold according to the user preference feature vector, starting a real-time monitoring mechanism, collecting current traffic status data, and generating a real-time traffic status parameter matrix;

[0049] In this embodiment, a personalized traffic flow threshold is set based on the user preference feature vector, and a real-time monitoring mechanism is started to continuously collect current traffic flow, road congestion index and weather environment data. If the traffic flow exceeds the preset threshold, the dynamic analysis module is triggered to generate a real-time traffic status parameter matrix, which includes a road speed component, a congestion index component and a weather impact component.

[0050] Furthermore, based on the user's preference feature vector, a personalized traffic flow threshold is set by analyzing historical behavior data and personalized needs, resulting in a user-specific traffic restriction standard. Based on the set personalized traffic flow threshold, a real-time monitoring mechanism is activated, continuously collecting current traffic flow, road congestion index, and weather environment data from sensors and meteorological interfaces to obtain a real-time data set. Based on the real-time data set, data cleaning and standardization methods are used to remove outliers and unify the data format, resulting in processed structured traffic data. If the traffic flow in the processed structured traffic data exceeds the personalized traffic flow threshold, the dynamic analysis module is triggered, initiating a real-time traffic status assessment process and obtaining preliminary assessment results. Based on these preliminary assessment results, the dynamic analysis module uses a multi-dimensional analysis algorithm to calculate the road speed component, congestion index component, and weather impact component to generate a real-time traffic status parameter matrix. If any component in the real-time traffic status parameter matrix exceeds the preset range, data fusion technology is used to compare the matrix data with historical traffic patterns to determine the degree of abnormality in the current traffic status. Based on the abnormality determination results, a weight adjustment algorithm is used to optimize the real-time traffic status parameter matrix, updating the influence ratio of each component in the matrix to obtain the optimized status parameter matrix. The optimized state parameter matrix is ​​combined with the weather environment data in the real-time collected data set to perform a secondary verification algorithm to determine the real-time traffic state parameter matrix.

[0051] Specifically, based on the user preference feature vector [time preference, distance preference, congestion preference], the K-means clustering algorithm is used to analyze the user's historical travel data (such as peak time selection and distance preference) to obtain the user tolerance cluster. Specifically, the user tolerance cluster is obtained by the following formula:

[0052] ,

[0053] Represents the optimal clustering result of the K-means clustering algorithm, k represents the number of clusters, represents the i-th cluster, x represents the user preference feature vector including time preference, distance preference and congestion preference, Represents the center point of the i-th cluster. The formula achieves the optimal clustering division of user tolerance by minimizing the sum of square errors within the cluster to obtain the user's tolerance cluster.

[0054] Based on the user's tolerance cluster, a personalized traffic flow threshold is assigned to each user. The following formula can be used:

[0055] ,

[0056] represents the personalized basic traffic flow threshold, represents the initial flow threshold, α represents the adjustment coefficient, Represents the weight factor of the tolerance cluster to which the user belongs. This formula dynamically adjusts the personalized traffic flow threshold based on the characteristics of the user's tolerance cluster.

[0057] Specifically, the user's historical behavior revealed that 70% of trips occurred during the evening rush hour (5:00 PM to 7:00 PM), with a preference for the shortest routes. Over the past month, when traffic flow exceeded 750 vehicles per hour, User B proactively took detours 80% of the time. K-means clustering assigned User B to the medium-tolerance cluster, resulting in a personalized base threshold of 800 vehicles per hour. Traffic flow data is collected at a 1Hz sampling rate using microwave sensors deployed on the roadside. The Meteorological Bureau's API is used to obtain precipitation intensity (1.2 mm / h), visibility (500 m), and wind speed (5 m / s). A three-tuple dataset is constructed, consisting of current traffic flow, congestion index (scale 0-10), and weather conditions. The congestion index reflects the degree of deterioration of the current traffic state relative to free-flow (unimpeded) conditions and is typically expressed on a scale of 0-10 or as a percentage. The general calculation model for the congestion index is: congestion index = (1-free-flow speed / current average speed) × scaling factor + additional correction term. The free-flow speed refers to the road's design speed or the average speed during historical periods of no congestion. The scaling factor maps the result to the target range (e.g., multiplying the 0-10 scale by 10). The additional correction term accounts for temporary factors such as weather and accidents (e.g., +1 for heavy rain). Based on the above formula, the congestion index is 7.8. The raw data was processed using the Z-score normalization method, eliminating outliers that deviated from the mean by ±3σ (e.g., a sudden drop in traffic to 0 due to GPS drift). The data was then output in a structured JSON format. When the traffic flow on a particular road section reached 850 vehicles per hour, the gradient boosting decision tree model in the dynamic analysis module was activated, with the following input features: current traffic flow (850), congestion index (7.8), and precipitation intensity (1.2 mm / h). The calculated speed component (km / h) was calculated as: base speed (e.g., 80 km / h) × (1-0.2 × congestion coefficient) × (1-0.15 × precipitation intensity) = 65 m / h. If the congestion index component (7.8) in the matrix exceeded the threshold of 7.5, the DTW algorithm was used to perform time series matching with the data from the same period over the past 30 days, and the anomaly score was output. Based on the anomaly score, the entropy weight method was used to reallocate the matrix weights, adjusting the weather impact component from 0.3 to 0.4. Combined with the current wind speed data (≥8m / s), the traffic speed prediction value is corrected through Kalman filtering, and the final output is a real-time traffic status parameter matrix containing the road speed component, congestion index component, and weather impact component of [65km / h, 7.8, 0.4].

[0058] S103 : Based on the real-time traffic status parameter matrix and the user preference feature vector, a gradient descent algorithm is used to dynamically adjust the time cost weight, distance cost weight, and congestion cost weight in path planning to generate an optimal weight configuration scheme.

[0059] In this embodiment, if Figure 2 As shown, it includes: extracting the time cost, distance cost and congestion cost related data of the current road according to the real-time traffic status parameter matrix to obtain the initial cost distribution characteristics;

[0060] The comprehensive cost calculation model is determined by combining the initial cost distribution characteristics with the user preference feature vector; the gradient descent algorithm is used to dynamically adjust the adjustment range of the calculation time cost weight, distance cost weight and congestion cost weight to generate a preliminary weight configuration combination; if the comprehensive cost of the preliminary weight configuration combination exceeds the preset threshold, the preliminary weight configuration combination is updated to generate the optimal weight configuration scheme.

[0061] Furthermore, based on the real-time traffic state parameter matrix, the relevant data on the time cost, distance cost, and congestion cost of the current road are extracted to obtain the initial cost distribution characteristics. Based on the initial cost distribution characteristics and the priority ranking in the user preference feature vector, the cost function of the path planning is constructed to determine the comprehensive cost calculation model. The gradient descent algorithm is used to iteratively optimize the comprehensive cost calculation model, calculate the adjustment direction of the time cost weight, distance cost weight, and congestion cost weight, and obtain the preliminary weight adjustment range. The comprehensive cost calculation model is as follows:

[0062] ,

[0063] C represents the comprehensive cost function value, represents the time cost weight, T represents the time cost, represents the distance cost weight, D represents the distance cost, represents the congestion cost weight, and G represents the congestion cost. This formula defines a comprehensive cost calculation model that includes three cost elements. Based on the initial weight adjustment range, the values ​​of the time cost weight, distance cost weight, and congestion cost weight are updated to generate a temporary weight configuration. Using this temporary weight configuration, the comprehensive cost value in the path planning is recalculated to obtain an updated cost distribution result. If the updated cost distribution result does not meet the preset convergence conditions, the gradient descent algorithm returns to a new round of iterative optimization to determine whether further weight adjustment is required. If the updated cost distribution result meets the preset convergence conditions, the temporary weight configuration is solidified as a candidate weight configuration scheme, and a preliminary scheme containing time weight values, distance weight values, and congestion weight values ​​is determined. Based on the candidate weight configuration scheme and the dynamically changing data in the real-time traffic status parameter matrix, final verification and fine-tuning are performed to obtain the optimal weight configuration scheme. Based on the optimal weight configuration scheme, the final path planning parameters containing time weight values, distance weight values, and congestion weight values ​​are output, completing the dynamic adjustment process.

[0064] Specifically, the time cost of the current road (e.g., a 12-minute travel time on a certain road section = distance cost / road speed component = 13 / 65), distance cost (e.g., 13 kilometers), and congestion cost (e.g., a congestion index of 0.78) are obtained from the real-time traffic status parameter matrix. The congestion cost is positively correlated with the weather impact component. Combined with the priority ranking in the user preference feature vector (e.g., time weight 0.6, distance weight 0.3, congestion weight 0.1), an initial cost distribution feature is formed. Based on this feature, a comprehensive cost calculation model is constructed using the linear weighted formula: Total cost = Time weight × Time cost + Distance weight × Distance cost + Congestion weight × Congestion cost = 0.6*12+13*0.3+0.78*0.1=11.2. Using the gradient descent algorithm, the following formula is used:

[0065] ,

[0066] in, represents the updated weight, represents the current weight, α represents the learning rate, represents the gradient of the cost function C with respect to the weight w. This formula describes the iterative update rule for weight parameters in the gradient descent algorithm. For example, setting the learning rate to 0.1, the weight adjustment direction is calculated (e.g., a time weight gradient of 0.2, a distance weight gradient of -0.1, and a congestion weight gradient of -0.05), generating a preliminary adjustment range. The weights are updated to form a temporary weight combination (0.58, 0.31, 0.105). The comprehensive cost is recalculated (e.g., the comprehensive cost decreases from 11.2 to 9.9). If the convergence threshold is not reached (e.g., the cost change is greater than 0.1), iterative optimization continues. When the comprehensive cost change is ≤ 0.1, the final weight configuration for time, distance, and congestion is output as (0.47, 0.32, 0.13) for path planning.

[0067] S104: Acquire road network topology data, generate a set of candidate paths, perform comprehensive scoring on the set of candidate paths according to the optimal weight configuration, and generate a path priority ranking list.

[0068] In this embodiment, the road network topology data and node connection relationship data are extracted from a preset database to construct an initial path network model; based on the initial path network model, a graph traversal algorithm is used to generate a set of candidate paths; and the candidate path set is comprehensively scored according to the optimal weight configuration to generate a path priority ranking list.

[0069] Specifically, assume there is a simple urban road network, which contains the following nodes and road segments: Nodes: A, B, C, D, E, F, G, H (representing intersections or landmarks); Road segments: roads connecting each node, each road has attributes such as distance, speed limit and road type, and it is necessary to plan the optimal path from the starting point A to the end point H, including: obtaining road network topology data, extracting road network data from the database: generating a set of candidate paths, and using the A* algorithm to generate candidate paths from the starting point A to the end point H. Among them, the A* algorithm is a widely used heuristic search algorithm for finding the optimal path from the starting point to the end point in a graph or network. The core idea is to evaluate each possible movement direction and select the path with the minimum comprehensive cost for expansion. For example, (g(n)) is the actual cost (known) from the starting point to the current node (n), (h(n)) is the estimated cost (heuristic function) from the current node (n) to the end point, (f(n) = g(n) + h(n) ) is the total cost, which is used to decide which node to expand next. The ultimate goal is to decide which node to expand to next when the total cost is minimized.

[0070] In this example, assume the following candidate paths are found:

[0071] 1.A->B->C->F->H

[0072] 2.A->B->E->F->H

[0073] 3.A->D->E->F->H

[0074] 4.A->D->G->H

[0075] 5.A->B->E->G->H

[0076] The candidate paths are comprehensively scored based on the optimal weight configuration, and the final weight configuration for time, distance, and congestion is output as (0.47, 0.32, 0.13). These weights reflect the importance users place on different factors. A path priority list is generated and the paths are sorted according to the scoring results:

[0077] A->B->E->F->H, distance: 20 km, estimated time: 22 minutes, number of congestion: 3, comprehensive score: 0.47*22+0.32*20+0.13*3=17.13;

[0078] A->B->C->F->H, distance: 20 km, estimated time: 24 minutes, number of congestion: 2, comprehensive score: 0.47*24+0.32*20+0.13*2=17.94;

[0079] A->D->E->F->H, distance: 15 km, estimated time: 27 minutes, number of congestion: 5,

[0080] Comprehensive score: 0.47*27+0.32*15+0.13*5 =18.14;

[0081] A->B->E->G->H, distance: 18 km, estimated time: 29 minutes, number of congestion: 2,

[0082] Comprehensive score: 0.47*29+0.32*18+0.13*2=19.65;

[0083] A->D->G->H, distance: 15 km, estimated time: 30 minutes, number of congestion: 7, comprehensive score: 0.47*30+0.32*15+0.13*7=19.81;

[0084] Based on the above comprehensive score ranking, the path priority ranking list <4, 5, 3, 1, 2> is obtained.

[0085] S105: monitoring the real-time traffic status of the recommended routes according to the route priority list; if an anomaly is detected, generating a set of alternative routes and calculating a route switching timing judgment condition; performing dynamic route adjustment according to the route switching timing judgment condition, and generating a final optimized navigation route solution;

[0086] In this embodiment, the real-time traffic status of the recommended path is monitored with respect to the path priority list and the trend of road condition changes. If a sudden traffic event or an increase in the congestion probability value is detected through the real-time traffic status parameter matrix, a set of alternative paths is generated, and the path switching timing judgment conditions are calculated based on the event severity component and the impact range component.

[0087] Furthermore, the real-time traffic status data is obtained, the real-time traffic status parameter matrix is ​​extracted, and the trend of road condition changes is analyzed; if the trend of road condition changes shows abnormal fluctuations, it is determined that there is a sudden traffic event; if the congestion probability value exceeds a preset threshold, a sudden traffic event identifier is generated; according to the sudden traffic event identifier, the alternative path set is extracted and the alternative path set is sorted; the event severity score is extracted to determine whether the path switching condition is met; if the path switching condition is met, the highest priority path is extracted from the alternative path set to generate an updated recommended path.

[0088] Specifically, assuming the initially recommended route is route 4: A->D->G->H, when the traffic monitoring system is running, the following occurs: Real-time traffic data acquisition: The system acquires traffic data for the current time (8:00 AM). It detects a traffic emergency on route D->G and another on route BE. The congestion index increases from 0.5 to 0.9, with the increase of 0.4 exceeding the preset threshold of 0.2. A traffic emergency indicator is generated. Based on this traffic emergency indicator, a set of alternative routes is extracted and ranked as <5, 3, 1, 2>. Furthermore, the estimated travel time increases from 30 minutes to 45 minutes, and the number of congestion events increases from 7 to 10. The system analyzes traffic trends and identifies abnormal fluctuations on route 4: A->D->G->H. A traffic emergency indicator is generated, with an incident severity score of 0. 47*(45-30)+0.13*(10-7)=7.44; Path switching timing judgment: The switching timing is determined by whether the score obtained by subtracting the event severity score from the initial recommended path is still greater than the highest-ranked score among the alternative paths. Here, the score of the initial recommended path (19.81 minus 7.44) is 12.37, which is less than the total score of path 5 in the alternative path priority ranking. Therefore, the path is switched at this time, and the final optimized navigation path is path 5: A->B->E->G->H.

[0089] like Figure 3 As shown, an embodiment of the present invention further provides an intelligent guidance system for implementing the above-mentioned intelligent guidance method. The system includes multiple modules that work together to optimize the operating parameters of the intelligent guidance. The system includes:

[0090] A user preference feature vector generation module, which obtains user historical behavior data from a navigation system database and generates a user preference feature vector based on the user historical behavior data;

[0091] A real-time traffic state parameter matrix generation module sets a personalized traffic flow threshold according to the user preference feature vector, activates a real-time monitoring mechanism, collects current traffic state data, and generates a real-time traffic state parameter matrix;

[0092] An optimal weight configuration scheme generation module, which uses a gradient descent algorithm to dynamically adjust the time cost weight, distance cost weight, and congestion cost weight in path planning based on the real-time traffic state parameter matrix and the user preference feature vector to generate an optimal weight configuration scheme;

[0093] a path priority ranking list generating module, which obtains road network topology data, generates a set of candidate paths, comprehensively scores the set of candidate paths according to the optimal weight configuration, and generates a path priority ranking list;

[0094] The final optimized navigation path solution generation module monitors the real-time traffic status of the recommended path according to the path priority list. If an anomaly is detected, it generates a set of alternative paths and calculates the path switching timing judgment conditions. According to the path switching timing judgment conditions, dynamic path adjustment is performed to generate the final optimized navigation path solution.

[0095] The above describes specific embodiments of the present invention. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art may make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. The embodiments of this application and the features in the embodiments may be combined with each other in any manner unless there is a conflict.

Claims

1. An intelligent guidance method, characterized in that: The method comprises: Acquire user historical behavior data from a navigation system database, and generate a user preference feature vector based on the user historical behavior data; The method includes: setting a personalized traffic flow threshold value according to the user preference feature vector, starting a real-time monitoring mechanism, collecting current traffic status data, and generating a real-time traffic status parameter matrix, including: classifying users according to the user preference feature vector and determining the personalized traffic flow threshold value; If the personalized traffic flow threshold is determined, the real-time monitoring mechanism is activated to collect current traffic flow, road congestion index and weather environment data to construct a real-time collection data set; Extracting traffic flow change trends, congestion index fluctuation characteristics and weather impact weights based on the real-time collected data set; If the traffic flow component exceeds the personalized traffic flow threshold, the dynamic analysis module is triggered to generate a real-time traffic state parameter matrix including a traffic speed component, a congestion index component, and a weather impact component; Based on the real-time traffic state parameter matrix and the user preference feature vector, a gradient descent algorithm is used to dynamically adjust the time cost weight, distance cost weight, and congestion cost weight in the path planning to generate an optimal weight configuration scheme, including: obtaining relevant data on the time cost, distance cost, and congestion cost of the current road based on the real-time traffic state parameter matrix to obtain an initial cost distribution feature; Determine the comprehensive cost calculation model by combining the initial cost distribution characteristics with the user preference feature vector; The gradient descent algorithm is used to dynamically adjust the adjustment range of the calculation time cost weight, distance cost weight, and congestion cost weight to generate a preliminary weight configuration combination; If the comprehensive cost of the preliminary weight configuration combination exceeds a preset threshold, the preliminary weight configuration combination is updated to generate an optimal weight configuration scheme; Acquire road network topology data, generate a set of candidate paths, perform comprehensive scoring on the set of candidate paths according to the optimal weight configuration, and generate a path priority ranking list; Monitor the real-time traffic status of the recommended routes according to the route priority list. If an anomaly is detected, generate a set of alternative routes and calculate the conditions for judging the timing of route switching. Perform dynamic route adjustment based on the conditions for judging the timing of route switching to generate the final optimized navigation route plan. include: Acquire real-time traffic status data, extract the real-time traffic status parameter matrix, and analyze the trend of road condition changes; If the traffic condition change trend shows abnormal fluctuations, it is determined that there is a traffic emergency; if the congestion probability value exceeds a preset threshold, a traffic emergency flag is generated; Extracting the set of alternative paths according to the traffic emergency identifier, and sorting the set of alternative paths; The event severity score is extracted to determine whether a path switching condition is met. If the path switching condition is met, the highest priority path is extracted from the set of candidate paths, and an updated recommended path is generated as the optimal path.

2. The intelligent guidance method according to claim 1, wherein: The method of obtaining user historical behavior data from the navigation system database and generating a user preference feature vector includes: Extracting user historical behavior data from the navigation system database, wherein the user historical behavior data includes travel time distribution and route selection records; Performing dimensionality reduction processing on the user's historical behavior data, extracting main feature components, and determining key patterns of user behavior; Grouping user behaviors according to the key patterns to categorize time preferences, distance preferences, and congestion preferences; Construct user preference feature vectors based on time preference, distance preference and congestion preference.

3. The intelligent guidance method according to claim 1, wherein: The acquiring of the road network topology data, generating a set of candidate paths, comprehensively scoring the set of candidate paths according to the optimal weight configuration, and generating a path priority ranking list includes: Extracting the road network topology data and node connection relationship data from a preset database to construct an initial path network model; According to the initial path network model, a graph traversal algorithm is used to generate a set of candidate paths; The candidate path set is comprehensively scored according to the optimal weight configuration to generate a path priority ranking list.

4. An intelligent guidance system, characterized in that: The system comprises: A user preference feature vector generation module, which obtains user historical behavior data from a navigation system database and generates a user preference feature vector based on the user historical behavior data; a real-time traffic state parameter matrix generation module, which sets a personalized traffic flow threshold value according to the user preference feature vector, activates a real-time monitoring mechanism, collects current traffic state data, and generates a real-time traffic state parameter matrix, including: classifying users according to the user preference feature vector and determining the personalized traffic flow threshold value; If the personalized traffic flow threshold is determined, the real-time monitoring mechanism is activated to collect current traffic flow, road congestion index and weather environment data to construct a real-time collection data set; Extracting traffic flow change trends, congestion index fluctuation characteristics and weather impact weights based on the real-time collected data set; If the traffic flow component exceeds the personalized traffic flow threshold, the dynamic analysis module is triggered to generate a real-time traffic state parameter matrix including a traffic speed component, a congestion index component, and a weather impact component; An optimal weight configuration scheme generation module, based on the real-time traffic state parameter matrix and the user preference feature vector, uses a gradient descent algorithm to dynamically adjust the time cost weight, distance cost weight, and congestion cost weight in path planning to generate an optimal weight configuration scheme, including: obtaining relevant data on the time cost, distance cost, and congestion cost of the current road based on the real-time traffic state parameter matrix to obtain an initial cost distribution feature; Determine the comprehensive cost calculation model by combining the initial cost distribution characteristics with the user preference feature vector; The gradient descent algorithm is used to dynamically adjust the adjustment range of the calculation time cost weight, distance cost weight, and congestion cost weight to generate a preliminary weight configuration combination; If the comprehensive cost of the preliminary weight configuration combination exceeds a preset threshold, the preliminary weight configuration combination is updated to generate an optimal weight configuration scheme; a path priority ranking list generating module, which obtains road network topology data, generates a set of candidate paths, comprehensively scores the set of candidate paths according to the optimal weight configuration, and generates a path priority ranking list; The final optimized navigation path solution generation module monitors the real-time traffic status of the recommended path according to the path priority list. If an anomaly is detected, it generates a set of alternative paths and calculates the path switching timing judgment conditions. It performs dynamic path adjustment based on the path switching timing judgment conditions to generate the final optimized navigation path solution, including: Acquire the real-time traffic status data, extract the real-time traffic status parameter matrix, and analyze the trend of road condition changes; If the traffic condition change trend shows abnormal fluctuations, it is determined that there is a traffic emergency; if the congestion probability value exceeds a preset threshold, a traffic emergency flag is generated; Extracting the set of alternative paths according to the traffic emergency identifier, and sorting the set of alternative paths; The event severity score is extracted to determine whether a path switching condition is met. If the path switching condition is met, the highest priority path is extracted from the set of candidate paths, and an updated recommended path is generated as the optimal path.

5. An intelligent guidance device, characterized in that: The intelligent boot device includes: a memory, a processor, and an intelligent boot program stored in the memory and executable on the processor, wherein the intelligent boot program is configured to implement the intelligent boot method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an intelligent boot program, and when the intelligent boot program is executed by a processor, the intelligent boot method according to any one of claims 1 to 3 is implemented.

Images