Dynamic adaptive navigation map system and vehicle

Abstract

The invention discloses a dynamic self-adaptive navigation map system and a vehicle, and belongs to the technical field of dynamic self-adaptive navigation.The dynamic self-adaptive navigation map system comprises a user behavior analysis module used for obtaining behavior data of a user, obtaining a user portrait according to the behavior data of the user and feeding the user portrait back to a recommendation algorithm module; the environment monitoring module is used for acquiring environment data and feeding the environment data back to the recommendation algorithm module; the recommendation algorithm module is used for respectively acquiring the environment data and the user portrait, adopting a dynamic planning strategy to obtain the most suitable driving path and sending the driving path to the navigation interface module; and the navigation interface module is used for acquiring and displaying the most suitable driving path.

Description

Technical Field

[0001] The invention discloses a dynamic adaptive navigation map system and a vehicle, belonging to the technical field of dynamic adaptive navigation. Background Art

[0002] Current navigation technology mainly relies on static map data and the user's real-time location to provide navigation services. These navigation systems are usually based on predefined path algorithms (such as Dijkstra algorithm and A* algorithm) to generate optimal routes through static information (traffic speed limits, road conditions, etc.). However, with the popularization of smart devices, users' travel needs are becoming increasingly personalized and diversified, and the existing systems are becoming increasingly insufficient, as follows:

[0003] (1) Lack of personalized recommendations: Existing navigation systems are often based on traditional algorithms and are unable to provide personalized navigation options based on user historical behaviors, preferences, or habits. This results in poor user experience and reduced satisfaction.

[0004] (2) Insufficient real-time feedback: Although some applications have real-time update functions, when encountering emergencies (such as traffic accidents, road closures, etc.), the system's response speed is slow and fails to provide users with new routes in a timely manner.

[0005] (3) Low environmental adaptability: Existing technologies often ignore environmental impacts (such as weather changes, holiday traffic changes, etc.). For example, in severe weather conditions such as storms and heavy snow, navigation suggestions are not up to standard.

[0006] (4) Single data source: Most existing methods rely on a single data source, such as GPS or user input information, but lack the integration of multiple data sources (such as social media and real-time traffic monitoring), resulting in incomplete information. Summary of the invention

[0007] In view of the defects of the prior art, the present invention proposes a dynamic adaptive navigation map system and a vehicle to solve the problems in the existing navigation system that cannot perform dynamic adaptive adjustments according to user behavior and environmental changes, the user's personalized needs are not met, the system responds slowly in emergencies, affecting user travel, and lacks multi-source data fusion, which limits the comprehensiveness and accuracy of information.

[0008] The technical solution of the present invention is as follows:

[0009] According to a first aspect of an embodiment of the present invention, a dynamic adaptive navigation map system is provided, comprising:

[0010] A user behavior analysis module is used to obtain user behavior data, obtain user portraits based on the user behavior data, and feed the user portraits back to the recommendation algorithm module;

[0011] Environmental monitoring module, used to obtain environmental data and feed it back to the recommendation algorithm module;

[0012] The recommendation algorithm module is used to obtain environmental data and user portraits respectively, use dynamic planning strategies to obtain the most suitable driving path and send it to the navigation interface module;

[0013] The navigation interface module is used to obtain the most suitable driving route and display it.

[0014] Preferably, it also includes: a feedback and learning module for obtaining feedback and behavior data that users can provide during use to regularly update and optimize the machine learning model.

[0015] Preferably, the user's behavior data includes at least: the user's location information, driving speed, stop points, common routes and historical navigation data.

[0016] Preferably, the user portrait includes: routes preferred by the user, time periods that the user tends to choose, and areas that the user avoids.

[0017] Preferably, the environmental data includes: traffic conditions, weather data and event monitoring.

[0018] Preferably, the dynamic programming strategy includes:

[0019] Scoring travel choices based on the user portrait to obtain a user preference score;

[0020] Performing a traffic flow score according to the traffic condition to obtain a traffic condition score;

[0021] Scoring the driving impact according to the weather data to obtain a weather impact score;

[0022] Scoring the traffic jam event according to the event monitoring to obtain an event monitoring score;

[0023] The comprehensive score is obtained by formula (1) according to the user preference score, traffic condition score, weather impact score and event monitoring score:

[0024] S=w p ×P+w t ×T+w w ×W+w e ×E(1)

[0025] Among them: S is the comprehensive score, w p is the user preference weight, P is the user preference score, and w t is the traffic condition weight, T is the traffic condition score, w w is the weather impact weight, W is the weather impact score, and w eis the event monitoring weight, E is the event monitoring score;

[0026] The most suitable driving path is obtained according to the driving path corresponding to the highest score in the comprehensive score.

[0027] Preferably, the recommendation algorithm module further includes: when the environment changes, updating the path in real time and pushing it to the user.

[0028] Preferably, the recommendation algorithm module further includes: when the user is approaching an emergency, providing alternative routes again to ensure that the user selects the most optimized path.

[0029] According to a second aspect of an embodiment of the present invention, a vehicle is provided, characterized in that it includes a vehicle body and the dynamic adaptive navigation map system described in the first aspect.

[0030] The present invention discloses a dynamic adaptive navigation map system and a vehicle, which have the following beneficial effects compared with the prior art:

[0031] (1) Personalized experience: Through user behavior analysis, the system can provide more targeted navigation solutions, making users feel more comfortable and improving user satisfaction.

[0032] (2) Real-time response capability: The system can monitor environmental changes in real time and adjust navigation routes in a timely manner to avoid user distress in unexpected situations, thus significantly improving travel efficiency.

[0033] (3) Multi-source information integration: Combine multiple data sources to provide more comprehensive navigation information, such as weather, traffic, holiday activities, etc., to improve the accuracy and practicality of information.

[0034] (4) Easy to operate: The system design simplifies user operations and enhances interactivity, making users willing to actively participate in feedback and optimizing system effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a structural block diagram of a dynamic adaptive navigation map system of the present invention. DETAILED DESCRIPTION

[0036] The following is based on the attached Figure 1 The present invention is further described:

[0037] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limitations on the present invention.

[0039] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0040] like Figure 1 As shown, the first embodiment of the present invention provides a dynamic adaptive navigation map system based on the prior art, including:

[0041] The user behavior analysis module is used to obtain the user's behavior data, obtain the user portrait based on the user's behavior data and feed it back to the recommendation algorithm module. Among them:

[0042] User behavior data User location information, driving speed, stop points, common routes and historical navigation data. A user profile is obtained based on the user behavior data, and the user profile includes: the user's preferred routes, the time period the user tends to choose, and the areas the user avoids.

[0043] For users who frequently use a route within a specific time period, the system will give priority to recommending this route. By comparing it with other users' behaviors, the system can find the routes chosen by similar users and provide new alternative routes for the user.

[0044] The environmental monitoring module is used to obtain environmental data and feed it back to the recommendation algorithm module, where:

[0045] Environmental data includes: traffic conditions, weather data, and event monitoring. Traffic conditions use traffic APIs (such as Google Traffic API) to obtain real-time traffic jams, accidents, road closures, and other information. Weather data uses the meteorological API to obtain current weather conditions and forecast data. Social media information monitors social media platforms (such as Twitter) to obtain real-time feedback on a certain area. Event monitoring: Set event trigger conditions. If a user is in a certain area, the system will remind the user of relevant environmental changes through push notifications.

[0046] The recommendation algorithm module is used to obtain environmental data and user portraits respectively, use dynamic planning strategies to obtain the most suitable driving path and send it to the navigation interface module;

[0047] The dynamic programming strategy includes:

[0048] The travel selection score is calculated based on the user portrait to obtain the user preference score. The specific content is as follows:

[0049] The travel selection score is calculated based on the user portrait, and the user preference score is obtained by formula (1):

[0050] P=pw1×RP+pw2×TP+pw3×A (1)

[0051] Wherein: P is the user preference score; pw1 is the weight of the route preferred by the user; RP is the score of the route preferred by the user, the score range is 0-10, and the more preferred route, the higher the score; pw2 is the weight of the time period that the user tends to choose; TP is the score of the time period that the user tends to choose, the score range is 0-10, and the more preferred time period, the higher the score; pw3 is the weight of the area avoided by the user, A is the area avoided by the user, the score range is 0-10, and the more avoided area, the lower the score. pw1, pw2 and pw3 can be adjusted according to user data, and preferably can be set to pw1=0.5, pw2=0.3 and pw3=0.2.

[0052] The traffic condition score is obtained by performing a traffic flow score according to the traffic condition, and the specific content is as follows:

[0053] Smoothness scoring based on traffic conditions: Traffic condition scoring is mainly based on real-time traffic data to evaluate traffic efficiency. Common indicators include: traffic speed, compared with normal speed (such as speed limit) to determine whether there is congestion; congestion delay, predicted or actual time delay, and traffic condition score is obtained through formula (2):

[0054] T=tw1×NS+tw2×CI (2)

[0055] Wherein: T is the traffic condition score, NS is the actual speed / speed limit, such as close to 10 means smooth traffic, close to 0 means congestion; CI is generated according to traffic monitoring data, 10 means completely smooth traffic, 0 means serious congestion; tw1 is the speed weight; tw2 is the traffic monitoring weight, tw1 and tw2 can be adjusted according to the specific data situation, preferably set to tw1=0.7 and tw2=0.3.

[0056] The driving impact score is obtained by scoring the weather data, and the specific content is as follows:

[0057] The driving impact score is calculated based on weather data: precipitation, the amount of rain and snow; temperature, the impact of extreme temperature; visibility, data such as haze, etc. The weather impact score is obtained through formula (3):

[0058] W=ww1×PF+ww2×TF+ww3×VF (3)

[0059] Among them: W is the weather impact score, PF is the score based on precipitation, 0-10 points, the more precipitation, the lower the score; TF is the comfort score based on weather temperature, 0-10 points, the more comfortable the score, the higher the score; VF is the line of sight clarity score, 0-10 points, the clearer the score, the higher the score. ww1 is the precipitation weight, ww2 is the comfort weight, and ww3 is the line of sight clarity weight. It can be adjusted according to the specific data situation, and can be initially set as ww1=0.5, ww2=0.3 and ww3=0.2.

[0060] According to the event monitoring, the traffic jam event is scored to obtain the event monitoring score, the specific content is as follows:

[0061] Traffic jam incidents are scored based on event monitoring: event type, analyzing the impact of different types of events; event severity, evaluating the severity and scope of the event; event duration, the impact of time on travel trajectory, and the event monitoring score is obtained through formula (4):

[0062] E=ew1×ES+ew2×ED+ew3×IA (4)

[0063] Among them: E is the event monitoring score; ES is the score of the event impact degree, 0-10 points, the greater the impact degree, the lower the score; ED is the score of the event duration, 0-10 points, the longer the time, the lower the score; IA is the impact range of the event on the region, 0-10 points, the greater the impact range, the lower the score; ew1 is the weight of the event impact degree; ew2 is the weight of the event duration, and ew3 is the weight of the event impact on the region. The weights can be adjusted according to the specific data situation, and can be initially set as ew1=0.6, ew2=0.3 and ew3=0.1.

[0064] The comprehensive score is obtained by formula (5) based on the user preference score, traffic condition score, weather impact score and event monitoring score:

[0065] S=w p ×P+w t ×T+w w ×W+w e ×E (5)

[0066] Among them: S is the comprehensive score, w p is the user preference weight, P is the user preference score, and w tis the traffic condition weight, T is the traffic condition score, w w is the weather impact weight, W is the weather impact score, and w e is the event monitoring weight, E is the event monitoring score;

[0067] The most suitable driving path is obtained according to the driving path corresponding to the highest score in the comprehensive score.

[0068] Example: Assume there are three paths A, B, and C. The PTWE scores are calculated as follows:

[0069] path User preference score P Traffic Condition Score T Weather Score W Event Score E Comprehensive score A 9 8 6 7 82 B 7 5 8 6 62 C 8 6 5 9 66

[0070] Assume that the weights are set to wp = 0.4, wt = 0.3, ww = 0.2, we = 0.1

[0071] According to the formula, path A = 82 points, path B = 62 points, path C = 66 points, and finally path A is the best path.

[0072] Through the above calculation method, the best path is obtained for recommendation, and dynamic adaptive navigation map recommendation based on user behavior and environmental changes is completed. The weight and scoring system can be adjusted regularly or based on user feedback to improve the accuracy of path recommendations and user satisfaction. Machine learning models, such as reinforcement learning, can be used to optimize the efficiency of selected paths and continuously improve path selection strategies based on user driving feedback.

[0073] The navigation interface module is used to obtain and display the most suitable driving route, and provides a hierarchical display of various types of information. Users can freely choose to view traffic conditions, weather information, surrounding maps and service facilities. Users can input points of interest (POI) through voice assistants or touch. For example, if they want to find nearby food or gas stations, the system will provide real-time suggestions based on the user's current location and navigation route.

[0074] The feedback and learning module is used to obtain feedback and behavioral data provided by users during use to regularly update and optimize the machine learning model.

[0075] A second embodiment of the present invention provides a vehicle based on the prior art, including a vehicle body and the dynamic adaptive navigation map system described in the first embodiment.

Claims

1. A dynamic adaptive navigation map system, characterized in that: include: A user behavior analysis module is used to obtain user behavior data, obtain user portraits based on the user behavior data, and feed the user portraits back to the recommendation algorithm module; Environmental monitoring module, used to obtain environmental data and feed it back to the recommendation algorithm module; The recommendation algorithm module is used to obtain environmental data and user portraits respectively, use dynamic planning strategies to obtain the most suitable driving path and send it to the navigation interface module; The navigation interface module is used to obtain the most suitable driving route and display it.

2. A dynamic adaptive navigation map system according to claim 1, characterized in that: Also includes: The feedback and learning module is used to obtain feedback and behavioral data provided by users during use to regularly update and optimize the machine learning model.

3. A dynamic adaptive navigation map system according to claim 1 or 2, characterized in that: The user's behavior data includes at least: the user's location information, driving speed, stop points, common routes and historical navigation data.

4. A dynamic adaptive navigation map system according to claim 1 or 2, characterized in that: The user portrait includes: the routes preferred by the user, the time periods that the user tends to choose, and the areas that the user avoids.

5. A dynamic adaptive navigation map system according to claim 4, characterized in that: The environmental data includes: traffic conditions, weather data and event monitoring.

6. A dynamic adaptive navigation map system according to claim 4, characterized in that: The dynamic programming strategy includes: Scoring travel choices according to the user portrait to obtain a user preference score; Performing a traffic flow score according to the traffic condition to obtain a traffic condition score; Scoring the driving impact according to the weather data to obtain a weather impact score; Scoring the traffic jam event according to the event monitoring to obtain an event monitoring score; The comprehensive score is obtained by formula (1) according to the user preference score, traffic condition score, weather impact score and event monitoring score: S=w p ×P+w t ×T+w w ×W+w e ×E (1) Among them: S is the comprehensive score, w p is the user preference weight, P is the user preference score, and w t is the traffic condition weight, T is the traffic condition score, w w is the weather impact weight, W is the weather impact score, and w e is the event monitoring weight, E is the event monitoring score; The most suitable driving path is obtained according to the driving path corresponding to the highest score in the comprehensive score.

7. A dynamic adaptive navigation map system according to claim 5 or 6, characterized in that: The recommendation algorithm module also includes: when the environment changes, the path is updated in real time and pushed to the user.

8. A dynamic adaptive navigation map system according to claim 5 or 6, characterized in that: The recommendation algorithm module also includes: when the user is approaching an emergency, providing alternative routes again to ensure that the user chooses the most optimized path.

9. A vehicle, characterized in that: It comprises a vehicle body and the dynamic adaptive navigation map system described in any one of claims 1-8.

Images