Destination recommendation method and device for vehicle navigation, vehicle, and storage medium

Abstract

This application provides a destination recommendation method, device, vehicle, and storage medium for in-vehicle navigation, relating to the field of intelligent in-vehicle navigation technology. The method includes: responding to a user's destination recommendation request for a target functional scenario; acquiring target user preference data for the target functional scenario, the target user preference data being constructed based on the user's historical behavior data during historical navigation; filtering destinations within the target functional scenario based on the target user preference data and the vehicle's current in-vehicle scenario information; and recommending destinations to the user based on the filtering results. By combining the user's preference data from historical navigation with the vehicle's real-time in-vehicle scenario information, the method accurately filters and recommends candidate destinations, overcoming the problems of insufficient generalization and personalization in recommendations caused by traditional solutions relying solely on static indicators. This improves the scenario adaptability of in-vehicle navigation destination recommendations and reduces the burden of manual filtering for users.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle navigation technology, and in particular to a method, device, vehicle, and storage medium for destination recommendation in vehicle navigation. Background Technology

[0002] Existing in-vehicle navigation systems typically rely on generalized evaluation dimensions to list destinations when providing destination recommendations for lifestyle services, requiring users to manually filter and compare them; or they build personalized user profiles on relevant terminal devices to provide more accurate recommendation services. These recommendation methods can meet users' destination filtering needs to a certain extent, but they still have technical problems such as cumbersome operation and weak targeting. Summary of the Invention

[0003] This application provides a destination recommendation method, device, vehicle, and storage medium for in-vehicle navigation. In this method, by combining the user's preference data formed during historical navigation and deeply associated with specific functional scenarios with the real-time in-vehicle scenario information of the vehicle, candidate destinations are accurately filtered and recommended. This effectively overcomes the problem of insufficient recommendation generalization and personalization caused by traditional solutions relying solely on static indicators such as distance and general scores. It improves the accuracy and scenario adaptability of destination recommendations in the in-vehicle environment and reduces the burden of manual filtering for users.

[0004] Firstly, a destination recommendation method for in-vehicle navigation is provided. The method includes: responding to a user's destination recommendation request for a target functional scenario, obtaining target user preference data of the user in the target functional scenario, wherein the target user preference data is constructed based on the user's historical behavior data during historical navigation; filtering each destination in the target functional scenario based on the target user preference data and the vehicle's current in-vehicle scenario information; and recommending destinations to the user based on the filtering results.

[0005] The beneficial effects of the technical solution described in the first aspect include at least the following: First, it abandons the reliance on general data from external platforms and instead deeply mines historical behavioral data generated by the vehicle's own navigation system that is highly relevant to the user's true intentions. Based on this, it constructs user preference data for relevant functional scenarios, making the preference data more realistic and highly consistent with in-vehicle usage scenarios, laying a data foundation for subsequent accurate personalized recommendations. Next, it integrates static personalized user preference data with dynamic real-time scenario information, and performs multi-dimensional and intelligent filtering on various destinations under the target functional scenarios. This comprehensive filtering method not only ensures that the recommendation results conform to the user's long-term usage habits but also adapts to the user's current specific driving situation, thereby improving the practicality and scenario fit of the recommendations. Finally, the system recommends destinations to the user based on the filtering results. Since the recommendation list has been filtered by both personalized preferences and real-time scenarios, its relevance and accuracy are greatly improved, reducing the manual filtering time required when users face a large number of irrelevant options. Users can quickly make decisions from a concise and highly adaptable list, thereby optimizing the entire in-vehicle human-machine interaction experience and improving the convenience and user satisfaction during the travel process.

[0006] In some possible implementations, the above method further includes: collecting the user's behavior data during the navigation process through the in-vehicle navigation system in the vehicle, wherein each behavior data includes at least one of search data, navigation data, interaction evaluation data after the user experience, and scenario data during route navigation; associating each behavior data with the corresponding functional scenario to construct user preference data under each functional scenario, wherein each user preference data includes at least one of usage preference data for the above functional scenario and scenario preference data during route navigation.

[0007] Through the technical solutions described above, the in-vehicle navigation system automatically collects multi-dimensional behavioral data of users during navigation (including search data, navigation data, interaction evaluation data, and scene data), and deeply correlates this data with specific functional scenarios to construct a refined and scenario-based user preference data system. This not only ensures the authenticity and scenario relevance of the data source, avoiding biases and omissions caused by relying on external platforms or user input, but also, by distinguishing between "usage preferences" and "scenario preferences," makes the constructed user preference data more comprehensive and accurate, providing reliable and comprehensive data support for subsequent highly personalized and deeply adapted intelligent recommendations for the in-vehicle environment.

[0008] In some possible implementations, the above-mentioned filtering of destinations under the target functional scenario based on the target user preference data and the vehicle's current in-vehicle scenario information includes: determining candidate destinations under the target functional scenario based on the real-time location of the in-vehicle navigation, where each candidate destination is a destination within a preset distance range of the vehicle's current location; performing user preference matching among the candidate destinations based on the target user preference data; and filtering candidate destinations that match the target user preference data in conjunction with the vehicle's current actual scenario information.

[0009] The technical solutions described above, employing a phased filtering mechanism, enhance the accuracy and usability of in-vehicle navigation destination recommendations. First, by locking onto candidate destinations within a preset distance range based on the in-vehicle navigation's real-time location, the geographical relevance of the recommendations is ensured. Second, a dual filtering logic is used, not only performing initial personalized matching of candidate destinations based on target user preference data but also further dynamically adapting them by incorporating the vehicle's current real-world scenario information. This layered and progressive filtering mechanism achieves a deep integration of personalized preferences and implicit scenario requirements. While ensuring that the recommended results closely align with user preferences, it also strictly conforms to the user's current driving context, effectively avoiding the problem of recommendations that conform to daily habits but fail to meet immediate scenario constraints. This facilitates presenting users with a highly matched and real-time usable list of destinations.

[0010] In some possible implementations, the above-mentioned user preference matching in each candidate destination based on the target user preference data includes: retaining destinations that meet the preset difference conditions with the target user preference data among all candidate destinations, and filtering out destinations that do not meet the preset difference conditions with the target user preference data.

[0011] By employing the technical solutions described above in the possible implementation methods, pre-defined differential conditions are introduced to accurately match and filter candidate destinations based on target usage preference data, thereby improving the matching degree between recommendation results and users' actual needs. Specifically, the system constructs differentiated filtering thresholds based on target user preference data, retaining only destinations that highly match user preferences while filtering out options with insufficient matching. This proactive filtering mechanism based on quantitative or rule-based differences can systematically exclude destinations that significantly deviate from users' explicit preferences in core attributes. This not only improves the relevance of subsequent recommendation lists but also reduces the interference of irrelevant information on users, making the recommendation process more focused on high-quality options that truly meet users' personalized needs, further enhancing the accuracy and intelligence of the recommendation system.

[0012] In some possible implementations, recommending destinations to the user based on the filtering results includes: sorting the filtering results according to the weight configuration ratio of each data item in the target user's preference data, and recommending the sorted results to the user through the in-vehicle navigation screen.

[0013] Through the technical solutions in the above possible implementation methods, the screening results are sorted based on the weight configuration ratio of each data in the target user preference data. This weight-driven sorting mechanism quantifies the importance differences of different preference elements in the user preference data and integrates them into the final recommendation sorting logic. This allows the sorting results to more realistically and accurately reflect the priority and intensity of user preferences. It not only improves the accuracy of recommendations but also helps users make quick decisions through the visual presentation on the in-vehicle screen. This effectively solves the problems of messy results and difficulty in selection in traditional recommendation systems, and enhances the practicality of in-vehicle navigation systems and the overall human-computer interaction experience.

[0014] In some possible implementations, the above method further includes: if the interval update time reaches a preset time condition, and / or the interval update quantity reaches a preset quantity condition, updating the user preference data and the corresponding weight configuration ratio based on the newly collected behavioral data, wherein the interval update time is the difference between the last data update time and the current time, and the interval update quantity is the difference between the data quantity at the time of the last data update and the current data quantity.

[0015] By employing the technical solutions described above in the possible implementation methods, a closed-loop optimization system of "data collection - data optimization - recommendation iteration" is constructed by setting dual trigger conditions based on time intervals or data accumulation to dynamically update user preference data and its weight configuration ratio. This ensures that user preference data can continuously adapt to changes in personal habits. Specifically, on the one hand, timed updates ensure that user profiles do not become fixed due to long-term inactivity, and can periodically incorporate recent behaviors to reflect potential changes in preferences. On the other hand, triggers based on the accumulation of behavioral data ensure that when users use the system frequently and generate a large amount of new feedback, the system can respond promptly and quickly optimize preference data, avoiding inaccurate recommendations due to update lag. This dynamic update strategy, which combines timeliness and data-driven approaches, effectively balances system resource consumption and data update real-time performance, enabling user preference data to continuously and accurately follow the evolution of users' actual preferences, thereby maintaining a high level of recommendation accuracy and user experience in the long term.

[0016] In some possible implementations, the target functional scenario mentioned above is catering, and the target user preference data mentioned above is user taste preference data.

[0017] By employing the technical solutions described above in various possible implementations, general destination recommendation methods are precisely anchored to the high-frequency, high-demand, and differentiated vertical scenario of dining. Using structured taste preferences as the core basis for personalized recommendations, this achieves deep integration and precise matching between in-vehicle navigation systems and lifestyle service scenarios. By focusing on the dining scenario, the system can construct a refined taste profile based on the user's historical navigation behavior (such as frequently searched cuisines, repeatedly navigated restaurants, and post-dining reviews), covering dimensions such as frequent cuisine preferences (e.g., Sichuan cuisine, Cantonese cuisine) and taste preferences (e.g., preference for spicy food, preference for mild food). This application of scenario-based preference data allows the system to combine real-time vehicle location, current time, and the number of people traveling with the user to recommend highly matching dining destinations. This effectively solves the problems of limited recommendation functionality and taste bias in traditional in-vehicle navigation systems, improving the efficiency and satisfaction of users' dining decisions in self-driving scenarios.

[0018] Secondly, a destination recommendation device for in-vehicle navigation is provided, the device comprising:

[0019] The data acquisition module is used to respond to the user's destination recommendation request for the target functional scenario and acquire the target user preference data of the user in the target functional scenario. The target user preference data is constructed based on the user's historical behavior data during the historical navigation process. The data filtering module is used to filter the destinations under the target functional scenarios based on the target user preference data and the current in-vehicle scenario information of the vehicle. The results recommendation module is used to recommend destinations to the above users based on the filtering results.

[0020] Thirdly, a vehicle is provided, including a memory for storing executable program code; and a processor for calling and running the executable program code from the memory, causing the vehicle to perform the methods described in the first aspect or any possible implementation thereof.

[0021] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0022] Fifthly, a computer-readable storage medium is provided that stores a computer program, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof. Attached Figure Description

[0023] Figure 1This is a schematic flowchart of a destination recommendation method for in-vehicle navigation provided in an embodiment of this application; Figure 2 This is a schematic flowchart of a destination recommendation method for in-vehicle navigation provided in an embodiment of this application; Figure 3 This is a schematic flowchart of a destination recommendation method for in-vehicle navigation provided in an embodiment of this application; Figure 4 This is a schematic flowchart of a destination recommendation method for in-vehicle navigation provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0024] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0025] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0026] Current in-vehicle navigation systems primarily focus on route planning and basic navigation services. Their ability to provide destination recommendations, such as lifestyle services, is relatively basic. Mainstream solutions typically rely on pre-defined, generic evaluation dimensions, such as prioritizing geographical distance as the primary sorting criterion, supplemented by static indicators like comprehensive user ratings or basic category tags provided by third-party platforms to generate the recommendation list. In this model, users often have to manually filter and compare a large number of homogeneous recommendations to find destinations that truly match their personal preferences—a time-consuming and inefficient process. While some restaurant recommendation platforms are attempting to build personalized user profiles by analyzing users' historical consumption, search, and review data on mobile devices to provide more accurate services, these solutions mainly serve mobile internet scenarios, and their data collection logic and recommendation models are not deeply integrated with the in-vehicle environment.

[0027] Existing recommendation methods have several limitations. First, the recommendation logic is too simplistic and rigid, lacking personalized modeling capabilities. The system fails to integrate behavioral data chains during user navigation, leading to discrepancies between recommendation results and actual user preferences. Second, when mobile recommendation logic is directly transferred to the in-vehicle environment, the specific constraints of the driving scenario are not considered (such as the impact of route congestion on meal duration and passenger number data from in-vehicle seat sensors), resulting in a mismatch between recommendation results and actual needs. Finally, existing systems only collect basic interaction data, lacking a closed-loop optimization mechanism of "behavior collection - profile building - recommendation feedback - dynamic updates," and struggle to accurately quantify user needs priority through weight allocation algorithms, resulting in homogeneous recommendation results.

[0028] Therefore, this application provides a destination recommendation method for vehicle navigation to solve the technical problems of existing destination recommendation methods, such as cumbersome operation and weak targeting.

[0029] Please see Figure 1 , Figure 1 An exemplary system architecture diagram of a destination recommendation method for in-vehicle navigation provided in an embodiment of this application.

[0030] like Figure 1 As shown, the system architecture may include vehicle 101, network 102, and server 103. Network 102 serves as the medium for providing a communication link between vehicle 101 and server 103. Network 102 may include various types of wireless communication links, such as Bluetooth communication links, Wireless-Fidelity (Wi-Fi) communication links, or microwave communication links.

[0031] In this embodiment, vehicle 101 can interact with server 103 via network 102 to receive messages from or send messages to server 103. Alternatively, vehicle 101 can interact with server 103 via network 102 to receive messages or data sent to server 103 by other users. For example, when a user initiates a restaurant recommendation request for a dining scenario in vehicle 101, the in-vehicle system can upload data such as the current real-time location, destination information, and locally preliminarily processed user identifier to server 103 via network 102. Server 103 stores and continuously updates the user's taste preference profile and behavior history database in the cloud. Upon receiving the request, it can retrieve the user's unique taste preference data and combine it with the current in-vehicle scenario information obtained from the vehicle to complete the filtering and sorting calculation of surrounding restaurants on the server side. Finally, server 103 sends the generated personalized recommendation list back to vehicle 101 via network 102, and it is presented to the user on the in-vehicle navigation screen.

[0032] Server 103 can be a business server providing various services. It should be noted that server 103 can be hardware or software. When server 103 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When server 103 is software, it can be implemented as multiple software programs or software modules (e.g., used to provide distributed services), or as a single software program or software module; no specific limitations are made here.

[0033] Alternatively, the system architecture may not include server 103. In other words, server 103 may be an optional device in the embodiments of this specification. That is, the method provided in the embodiments of this specification can be applied to a system structure that only includes vehicle 101. The embodiments of this application do not limit this.

[0034] In this embodiment, firstly, in response to a user's destination recommendation request for a target functional scenario, vehicle 101 obtains the user's target user preference data for the target functional scenario, the target user preference data being constructed based on the user's historical behavior data during historical navigation; then, vehicle 101 filters each destination for the target functional scenario based on the target user preference data and the vehicle's current in-vehicle scenario information; finally, vehicle 101 recommends destinations to the user based on the filtering results.

[0035] It should be understood that Figure 1 The number of vehicles, networks, and servers shown is only illustrative; the number can be any number depending on the implementation requirements.

[0036] Please see Figure 2 , Figure 2 This is a schematic flowchart illustrating a destination recommendation method for in-vehicle navigation provided in an embodiment of this application. The executing entity in this embodiment can be a vehicle performing destination recommendation for in-vehicle navigation, a processor within the vehicle performing the destination recommendation method, or an in-vehicle navigation destination recommendation service within the vehicle performing the destination recommendation method. For ease of description, the following uses a processor within the vehicle as the executing entity to describe the specific execution process of the destination recommendation method for in-vehicle navigation.

[0037] like Figure 2 As shown, the destination recommendation methods for in-vehicle navigation systems can include at least: S202. In response to the user's destination recommendation request for the target functional scenario, obtain the user's target user preference data in the target functional scenario. The target user preference data is constructed based on the user's historical behavior data during the historical navigation process.

[0038] Optionally, the method in this application embodiment is embedded in the vehicle's own intelligent system, aiming to achieve personalized and scenario-based destination services by deeply utilizing data streams in the in-vehicle environment. Specifically, when a destination recommendation request initiated by a user for a specific target functional scenario is received, the system can dynamically acquire personalized preference data that is highly relevant to the user in that target functional scenario. This preference data does not originate from data input from external third-party applications or general service platforms, but is based on historical behavioral data generated by the user during past use of the in-vehicle navigation system, thereby ensuring the authenticity of the preference data and its deep correlation with the in-vehicle usage environment.

[0039] S204. Based on target user preference data and the vehicle's current in-vehicle scenario information, filter the destinations under the target functional scenario.

[0040] Optionally, the in-vehicle navigation system will also collect and update the vehicle's current in-vehicle scene information in real time, including but not limited to the vehicle's precise location, driving direction, surrounding traffic conditions, weather conditions, and in-vehicle status (such as the number of passengers). This information together constitutes the dynamic context of the current scene, providing comprehensive environmental parameters for destination selection.

[0041] Furthermore, after acquiring user preference data for the target functional scenario, the system deeply integrates and matches this data with the vehicle's current in-vehicle scenario information, using both as the basis for destination selection decisions. Specifically, the system first performs preliminary scope definition and suitability assessment of all potential destinations within the target functional scenario based on the vehicle's current in-vehicle scenario information. Subsequently, based on this preliminary selection, target user preference data is further introduced to perform deep matching of candidate destinations. This process ensures that the final retained destinations not only objectively meet the user's current spatial and temporal constraints but also subjectively highly align with their long-standing personalized needs.

[0042] It should be noted that, to more concretely illustrate the application value of this solution, the following explanation will use the catering industry—a high-frequency and highly differentiated vertical scenario—as an example. In the catering scenario, user preference data can be refined into personalized preferences for cuisine, flavor, and dining environment, while in-vehicle scenario information includes real-time conditions such as dining time, number of companions, and parking convenience. By comprehensively analyzing this data, the system can recommend ideal restaurants that match the user's taste preferences and are suitable for the current dining scenario, thereby improving the efficiency and satisfaction of the user's dining decision-making in the in-vehicle environment.

[0043] S206. Recommend destinations to users based on the filtering results.

[0044] Optionally, after filtering destinations within the target functional scenario, a recommendation list containing multiple destinations will be generated. This list not only reflects the degree of matching between each destination and the user's preference data but also fully considers the vehicle's current in-vehicle scenario information. Furthermore, the system will present the recommendation list to the user in a clear and intuitive manner, possibly through a list display on the in-vehicle screen, voice announcements, or a graphical interface, to meet the usage habits and needs of different users. During the presentation, the system will also provide detailed information about the destinations, such as name, address, special services, and user reviews, to enable users to make a more comprehensive and accurate selection.

[0045] This application provides a destination recommendation method for in-vehicle navigation. First, it abandons the reliance on general data from external platforms and instead deeply mines historical behavioral data generated by the vehicle's own navigation system that is highly relevant to the user's true intentions. Based on this, it constructs user preference data for relevant functional scenarios. This makes the preference data more realistic and highly consistent with the in-vehicle usage scenario, laying a data foundation for subsequent accurate personalized recommendations. Next, it integrates static personalized user preference data with dynamic real-time scenario information and performs multi-dimensional, intelligent filtering on various destinations within the target functional scenario. This comprehensive filtering method not only ensures that the recommendation results conform to the user's long-term usage habits but also adapts to the user's current specific driving situation, thereby improving the practicality and scenario relevance of the recommendations. Finally, the system recommends destinations to the user based on the filtering results. Because the recommendation list has undergone dual filtering by personalized preferences and real-time scenarios, its relevance and accuracy are greatly improved, reducing the manual filtering time required when users face a large number of irrelevant options. Users can quickly make decisions from a concise and highly suitable list, thereby optimizing the entire in-vehicle human-machine interaction experience and improving convenience and user satisfaction during travel. In this method, by combining the user's preference data, which is deeply associated with specific functional scenarios and formed during the historical navigation process, with the real-time in-vehicle scenario information of the vehicle, the candidate destinations are accurately filtered and recommended. This effectively overcomes the problem of insufficient generalization and personalization of recommendations caused by traditional solutions that rely solely on static indicators such as distance and general scores. It improves the accuracy and scenario adaptability of destination recommendations in the in-vehicle environment and reduces the burden of manual filtering for users.

[0046] Please see Figure 3 , Figure 3 This is a schematic flowchart illustrating a destination recommendation method for in-vehicle navigation provided in an embodiment of this application.

[0047] like Figure 3 As shown, the destination recommendation methods for in-vehicle navigation systems can include at least: S302. Collect user behavior data during navigation through the vehicle's in-vehicle navigation system. The behavior data includes at least one of the following: search data, navigation data, user experience interaction evaluation data, and scenario data during route navigation.

[0048] Optionally, to construct accurate user preference data, the system first needs to comprehensively and systematically collect various behavioral data of users during the use of in-vehicle navigation. Specifically, the system will continuously record search data actively entered by users through the in-vehicle navigation system, such as search keywords for specific functional scenarios, the frequency of searches, and the time of initiation. This data directly reflects the user's interest in specific functional scenarios. Simultaneously, the system will also track and record the user's navigation data, such as the history of navigation to specific destinations, the actual completion rate of navigation tasks, and the number of times the same destination is repeatedly navigated. This data helps to analyze the user's preference for specific destinations and usage habits. Furthermore, user experience feedback data is also an important component in constructing user preference data, directly reflecting the user's satisfaction with the destination or service and suggestions for improvement. Finally, it is also necessary to collect scene data perceived synchronously during route navigation, such as the vehicle's real-time location, current time, driving route, and other contextual information obtained through in-vehicle sensors or user input. This data helps to more accurately capture the user's scene preferences.

[0049] Optionally, taking the dining scenario as an example, suppose a user frequently searches for the keyword "Sichuan cuisine" in their car navigation system, navigates to Sichuan restaurants multiple times, and submits positive reviews after dining. These data collectively indicate a high preference for Sichuan cuisine. Furthermore, the system also records that users tend to choose restaurants with elegant environments and higher ratings during dinner time, and prefer restaurants offering free parking on rainy days. By comprehensively analyzing this data, the system can construct detailed user preference data in dining scenarios, including preferences for cuisine, flavor characteristics, restaurant environment, and parking convenience.

[0050] S304. Associate each behavioral data with the corresponding functional scenario to construct user preference data under each functional scenario. Each user preference data includes at least one of the following: usage preference data for functional scenarios and scenario preference data during path navigation.

[0051] Optionally, after collecting behavioral data, the system will categorize, organize, and analyze the user behavior data collected through the in-vehicle navigation system. This data will then be deeply correlated with the user's current or potentially interesting functional scenarios to extract two key preference dimensions: usage preference data for functional scenarios and scenario preference data during route navigation. Usage preference data primarily reflects the user's stable interest tendencies in specific functional scenarios. It stems from long-term, high-frequency, and intentionally defined behavioral patterns, such as repeated selections or active searches for a particular type of service, constituting the core and most fundamental part of user preference data. Scenario preference data, on the other hand, captures the dynamic changes in user preferences with the external driving environment. It reflects the differentiated needs of users for the same functional scenario at different times and in different contexts. These two types of preference data together construct user preference data for specific functional scenarios. This comprehensive analysis helps the system form a comprehensive and in-depth understanding of user preferences, thereby providing users with more accurate and personalized recommendation services.

[0052] Optionally, taking the dining scenario as an example, the system analyzes users' historical behavior to extract usage preference data across dimensions such as high-frequency cuisines (e.g., Sichuan and Cantonese cuisine), flavor characteristics (e.g., preference for spicy, mild, or sweet and sour), and ingredient preferences (e.g., seafood, vegetarian, beef, and lamb). Simultaneously, combined with the specific context of navigation, it generates scenario preference data under different time periods (e.g., a preference for fast food for weekday lunches and a preference for upscale restaurants for weekend dinners) and different group sizes (e.g., a preference for private rooms for large gatherings). These two approaches work together to ensure that the final restaurant recommendations not only satisfy users' taste preferences but also perfectly adapt to their current dining context.

[0053] S306. In response to the user's destination recommendation request for the target functional scenario, obtain the user's target user preference data in the target functional scenario. The target user preference data is constructed based on the user's historical behavior data during the historical navigation process.

[0054] Optionally, for details regarding step S306, please refer to the description in step S202, which will not be repeated here.

[0055] S308, Candidate destinations in the scenario of determining the target based on the real-time location of the vehicle navigation system, where each candidate destination is a destination within a preset distance range of the vehicle's current location.

[0056] Optionally, when recommending destinations, the method in this embodiment first utilizes the real-time positioning function of the in-vehicle navigation system to determine the vehicle's current geographical location. Based on this location, and according to a preset distance range (e.g., 3 kilometers, which can be dynamically adjusted according to the user's specific needs or the system's default strategy), all possible destinations within this range are filtered out to form a candidate destination set. This preliminary filtering mechanism effectively eliminates options that are obviously infeasible due to their excessively distant geographical location, reducing the amount of data required for subsequent refined processing.

[0057] S310. Based on the target user preference data, perform user preference matching in each candidate destination, and filter the candidate destinations that match the target user preference data in combination with the current actual scenario information of the vehicle.

[0058] Optionally, after completing the initial location-based screening, the system will enter a deeper user preference matching stage to perform a more refined dual matching and screening process. Specifically, on the one hand, the system will identify and retain destinations that are highly consistent with the user's target usage preference data in terms of key attributes; on the other hand, it will simultaneously perform an exclusion filtering operation, that is, actively identify and eliminate all destinations that have unacceptable deviations from the user's explicitly expressed or implicitly expressed exclusionary preferences (i.e., do not meet the preset difference conditions).

[0059] Optionally, after completing the aforementioned preference-based two-way filtering, the system will further combine the vehicle's current actual scenario information to conduct a final scenario-appropriateness assessment of the retained candidate destinations. For example, it may determine the timeliness of service needs based on the current time, assess the venue's capacity based on the number of people traveling with the user, or consider the convenience of the destination's supporting facilities based on the user's parking needs. Only candidate destinations that pass both preference matching and scenario appropriateness assessments will be included in the final recommendation list.

[0060] Optionally, taking a dining scenario as an example, when recommending destinations, the system first filters all restaurants within a certain distance as candidates based on the real-time location of the vehicle's navigation system. Then, through preference matching, the system identifies the user's preferences for Sichuan cuisine, Cantonese cuisine, etc., and their likely preferred restaurant environments (such as quiet or unique). Simultaneously, it filters out restaurants from all candidate restaurants that the user has explicitly stated they dislike in terms of cuisine or environment. Next, considering the current time (e.g., dinner time) and the user's likely dining duration, the system further filters out restaurants that are open and suitable for the current time. If the user is traveling with a large group, the system will prioritize recommending restaurants with available private rooms or spacious dining areas. Finally, by comprehensively considering user preferences, exclusion filters, and actual scenario information, the system can provide the user with a restaurant recommendation list that matches their personal taste and is easily accessible.

[0061] S312. Recommend destinations to users based on the filtering results.

[0062] Optionally, for details regarding step S312, please refer to step S206, which will not be repeated here.

[0063] This application provides a method for destination recommendation in vehicle navigation. The method automatically collects multi-dimensional behavioral data (including search data, navigation data, interaction evaluation data, and scene data) of users during navigation through the vehicle's in-vehicle navigation system. This data is then deeply correlated with specific functional scenarios to construct a refined and scenario-based user preference data system. This not only ensures the authenticity and scenario relevance of the data source, avoiding biases and omissions caused by relying on external platforms or user input, but also, by distinguishing between "usage preferences" and "scenario preferences," makes the constructed user preference data more comprehensive and accurate. This provides reliable and comprehensive data support for subsequent highly personalized and deeply adapted intelligent recommendations for the in-vehicle environment. A phased filtering mechanism improves the accuracy and practicality of in-vehicle navigation destination recommendations. First, candidate destinations within a preset distance range are locked based on the real-time location of the in-vehicle navigation system, ensuring the geographical relevance of the recommendation results. Second, through a dual filtering logic, not only are candidate destinations initially personalized based on target user preference data, but further dynamic adaptation is performed by combining the vehicle's current actual scenario information. This layered and progressive filtering mechanism achieves a deep integration of personalized preferences and implicit scenario needs. While ensuring that recommended results closely match user preferences, it also strictly adheres to the user's current driving situation, effectively avoiding the problem of recommendations that conform to daily habits but do not meet the constraints of the immediate scenario. This facilitates presenting users with a highly matched and real-time available list of destinations. Introducing preset differential conditions for precise matching and filtering of candidate destinations based on target usage preference data improves the matching degree between recommended results and users' actual needs. Specifically, the system constructs differentiated filtering thresholds based on target user preference data, retaining only destinations that highly match user preferences while filtering out options with insufficient matching. This proactive filtering mechanism based on quantitative or rule-based differences systematically excludes destinations that significantly deviate from the user's explicit preferences in core attributes. This not only improves the relevance of subsequent recommendation lists but also reduces the interference of irrelevant information, making the recommendation process more focused on high-quality options that truly meet the user's personalized needs, further enhancing the accuracy and intelligence of the recommendation system.

[0064] Please see Figure 4 , Figure 4 This is a schematic flowchart illustrating a destination recommendation method for in-vehicle navigation provided in an embodiment of this application.

[0065] like Figure 4 As shown, the destination recommendation methods for in-vehicle navigation systems can include at least: S402. In response to the user's destination recommendation request for the target functional scenario, obtain the user's target user preference data in the target functional scenario. The target user preference data is constructed based on the user's historical behavior data during the historical navigation process. Based on the target user preference data and the vehicle's current in-vehicle scene information, filter the destinations in the target functional scenario.

[0066] Optionally, for details regarding step S402, please refer to steps S202 and S204, which will not be repeated here.

[0067] S404. Sort the filtering results based on the weight configuration ratio of each data item in the target user preference data, and recommend the sorted results to the user through the in-vehicle navigation screen.

[0068] Optionally, when recommending destinations to users based on the filtering results, the method in this embodiment employs a sorting mechanism based on the weighting ratio of various data components to ensure the high personalization and accuracy of the recommended content. Specifically, the importance differences of each component within the target user's preference data are pre-quantified, and the user's level of attention and sensitivity to each dimension is reflected through preset weighting ratios. Based on this, after obtaining the filtered destination list, the system weights and integrates the preference information from different dimensions, while also incorporating other key objective factors, such as the distance between the destination and the vehicle's current location, historical evaluations from third parties or the user, and convenience indicators closely related to the current in-vehicle scenario (such as parking conditions). Through this multi-factor weighted calculation, a quantified matching score is generated for each candidate destination, and the list is then sorted in descending order accordingly.

[0069] Optionally, the ranking results can be presented to the user through the in-vehicle navigation screen, including the destination's name, type, key feature tags, distance, estimated arrival time, convenience information for specific scenarios, and matching percentage, allowing users to clearly understand the advantages and suitability of each recommended destination. Simultaneously, the system also supports one-click navigation for any recommendation, achieving seamless integration from information acquisition to action execution, further enhancing the ease of use of the in-vehicle navigation system.

[0070] S406. If the interval update time reaches the preset time condition, and / or the interval update quantity reaches the preset quantity condition, update the user preference data and the corresponding weight configuration ratio based on the newly collected behavioral data. The interval update time is the difference between the last data update time and the current time, and the interval update quantity is the difference between the data quantity at the time of the last data update and the current data quantity.

[0071] Optionally, to ensure that user preference data can continuously and accurately reflect the dynamic evolution of user interests, the method in this application embodiment also introduces an intelligent preference data update mechanism. The core of this mechanism is that it does not frequently refresh user preference data in real-time or indiscriminately, but rather balances the timeliness of data updates with the consumption of system resources through dual triggering conditions. Specifically, this mechanism triggers the update operation based on two key conditions: first, the interval update time reaches a preset time condition, that is, the length of time elapsed since the last data update reaches a threshold set by the system; second, the interval update quantity reaches a preset quantity condition, that is, the amount of newly collected behavioral data since the last data update reaches a quantity standard set by the system. When either condition or both are met simultaneously, the system will initiate the update process.

[0072] Optionally, the system will collect user interaction data with the recommendation system, including but not limited to user actions such as clicking, saving, ignoring, and negative reviews of recommended destinations, as well as new navigation requests and feedback submitted by users through the system. This newly collected behavioral data serves as an important basis for updating user preference data. After triggering the update condition, the system will analyze this new data, identify trends in user preferences and emerging needs, and then adjust the various dimensions and their weighting in the user preference data. For example, if a user has recently frequently clicked on and saved a certain type of destination, the system may increase the weight of that type of destination in the user preference data to reflect the user's current interests. This triggering strategy, based on both time and data volume, avoids wasting computing resources due to overly frequent updates and prevents data homogenization due to delayed updates, thus achieving an optimal balance between efficiency and accuracy.

[0073] This application provides a destination recommendation method for in-vehicle navigation. The method sorts the filtering results based on the weighted configuration ratio of various data points in the target user's preference data. This weight-driven sorting mechanism quantifies the importance differences of different preference elements in the user preference data and integrates them into the final recommendation sorting logic. This allows the sorting results to more realistically and accurately reflect the priority and intensity of user preferences, improving recommendation accuracy and helping users make quick decisions through visual presentation on the in-vehicle screen. It effectively solves the problems of cluttered results and difficulty in selection in traditional recommendation systems, enhancing the practicality of the in-vehicle navigation system and the overall human-computer interaction experience. By setting dual trigger conditions based on time intervals or data accumulation to dynamically update user preference data and its weighted configuration ratio, a closed-loop optimization system of "data collection - data optimization - recommendation iteration" is constructed, ensuring that user preference data can continuously adapt to changes in personal habits. Specifically, on the one hand, scheduled updates ensure that user profiles do not become static due to prolonged inactivity, and can periodically incorporate recent behaviors to reflect potential changes in preferences. On the other hand, triggers based on the accumulation of behavioral data guarantee that when users use the system frequently and generate a large amount of new feedback, the system can respond promptly and quickly optimize preference data, avoiding inaccurate recommendations due to update delays. This dynamic update strategy, combining timeliness and data-driven approaches, effectively balances system resource consumption and data update real-time performance, enabling user preference data to continuously and accurately follow the evolution of users' actual preferences, thereby maintaining a high level of recommendation accuracy and user experience in the long term.

[0074] Figure 5 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0075] For example, such as Figure 5 As shown, the vehicle 500 includes: at least one processor 501, at least one network interface 504, user interface 503, memory 505, and at least one communication bus 502.

[0076] The communication bus 502 is used to enable communication between these components.

[0077] The user interface 503 may include a display screen, a camera, and a voice input device. Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0078] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0079] The memory 505 stores executable program code: a destination recommendation program for vehicle navigation. The processor 501 is used to call and execute the executable program code to perform a destination recommendation method for vehicle navigation.

[0080] Furthermore, embodiments of this application also protect an apparatus that may include a memory, a processor, an interface, and a communication bus, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform a destination recommendation method for vehicle navigation provided in embodiments of this application.

[0081] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0082] When each functional module is divided according to its corresponding function, the device may also include a preference data construction module, a data update module, etc. It should be noted that all relevant content regarding the steps involved in the above method embodiments can be referenced in the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0083] It should be understood that the device provided in this embodiment is used to execute the above-described method for recommending destinations in vehicle navigation, and therefore can achieve the same effect as the above-described implementation method.

[0084] When using an integrated unit, the device may include a processing module, a storage module, an interface module, and a communication module. When the device is applied to a vehicle, the processing module can be used to control and manage the vehicle's movements. The storage module can be used to support the vehicle in executing relevant program code.

[0085] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits shown in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0086] In addition, the device provided in the embodiments of this application may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute a destination recommendation method for vehicle navigation provided in the above embodiments.

[0087] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, it causes the computer to execute the aforementioned method steps to implement the in-vehicle navigation destination recommendation method provided in the above embodiment. Figure 5 As shown, the memory 505, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a destination recommendation program for vehicle navigation.

[0088] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement the in-vehicle navigation destination recommendation method provided in the above embodiment.

[0089] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0090] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0091] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0092] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A destination recommendation method for in-vehicle navigation, characterized in that, Applied to vehicles, the method includes: In response to a user's destination recommendation request for a target functional scenario, the system obtains the user's target user preference data for that target functional scenario, which is constructed based on the user's historical behavior data during historical navigation. Based on the target user preference data and the vehicle's current in-vehicle scenario information, the destinations under the target functional scenario are filtered; Based on the filtering results, destinations are recommended to the user.

2. The method according to claim 1, characterized in that, The method further includes: The vehicle's in-vehicle navigation system collects user behavior data during the navigation process. Each behavior data includes at least one of the following: search data, navigation data, user experience interaction evaluation data, and scenario data during route navigation. By associating each behavioral data with the corresponding functional scenario, user preference data under each functional scenario is constructed. Each user preference data includes at least one of the following: usage preference data for the functional scenario and scenario preference data during path navigation.

3. The method according to claim 1, characterized in that, The filtering of destinations under the target functional scenario based on the target user preference data and the vehicle's current in-vehicle scene information includes: Based on the real-time location of the vehicle navigation system, candidate destinations for the target functional scenario are determined, and each candidate destination is a destination within a preset distance range of the current location of the vehicle. Based on the target user preference data, user preferences are matched among the candidate destinations, and the candidate destinations that match the target user preference data are filtered in combination with the current actual scene information of the vehicle.

4. The method according to claim 3, characterized in that, The step of matching user preferences in each candidate destination based on the target user preference data includes: Among all candidate destinations, those that meet the preset difference conditions with the target usage preference data are retained, while those that do not meet the preset difference conditions with the target usage preference data are filtered out.

5. The method according to claim 1, characterized in that, The process of recommending destinations to the user based on the filtering results includes: The filtering results are sorted based on the weighted proportions of each data item in the target user preference data, and the sorted results are recommended to the user through the in-vehicle navigation screen.

6. The method according to claim 2, characterized in that, The method further includes: If the interval update time reaches a preset time condition, and / or the interval update quantity reaches a preset quantity condition, the user preference data and the corresponding weight configuration ratio are updated based on the newly collected behavioral data. The interval update time is the difference between the last data update time and the current time, and the interval update quantity is the difference between the data quantity at the time of the last data update and the current data quantity.

7. The method according to claim 1, characterized in that, The target functional scenario is catering, and the target user preference data is user taste preference data.

8. A destination recommendation device for vehicle navigation, characterized in that, Applied to vehicles, the device includes: The data acquisition module is used to respond to a user's destination recommendation request for a target functional scenario and acquire the user's target user preference data in the target functional scenario. The target user preference data is constructed based on the user's historical behavior data during the historical navigation process. The data filtering module is used to filter destinations under the target functional scenario based on the target user preference data and the vehicle's current in-vehicle scenario information; The result recommendation module is used to recommend destinations to the user based on the filtering results.

9. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 7.

Images