Vehicle-mounted application recommendation method and system based on user portrait analysis and electronic equipment

Abstract

The invention discloses a vehicle-mounted application recommendation method and system based on user portrait analysis and electronic equipment, and relates to the field of vehicle data analysis, and the method comprises the steps: collecting user operation data, vehicle CAN bus data and driving scene data through a data collection module, and generating an input data set; uploading the input data set to a temporary storage component, and uploading the input data set to a cloud server through a vehicle machine network according to an uploading sequence; generating a recommendation weight corresponding to each application by using an algorithm model through the input data set; the recommendation weights are arranged in a descending order, and recommendation cards carrying scene parameters are generated; the scene parameters comprise vehicle CAN bus data and driving scene data; and responding to a click operation of a target user on the system-level recommended card through a cross-application starting module.

Description

Technical Field

[0001] This application relates to the field of vehicle-mounted data analysis, and in particular to a method for recommending in-vehicle applications based on user profile analysis, an in-vehicle application recommendation system based on user profile analysis, an electronic device, and a storage medium. Background Technology

[0002] With the development of intelligent and connected vehicles, the applications on car central control screens are becoming increasingly diverse. Faced with such a wide range of applications, users also need in-vehicle systems to recommend some applications to them. In existing technologies, the intelligent recommendation function of in-vehicle systems typically sorts applications and functions based on simple usage frequency or recent usage records. For example, some systems record the number of times a user opens an application and then sort the applications in descending order of the number of times they are opened. However, this method has several problems:

[0003] Lack of context awareness: Existing recommendation systems often ignore the vehicle's current operating status (such as speed, battery level, and location), resulting in recommended content that does not match the driving scenario. For example, recommending multimedia functions that require complex operation while driving at high speed increases driving risk.

[0004] The urgency of functions was not taken into account: In certain scenarios (such as low battery), the priority of certain functions (such as finding charging stations) should be significantly increased, but the existing system cannot dynamically adjust this.

[0005] Insufficient cross-application recommendations: Existing solutions typically remain at the application level and cannot delve into the functional recommendations within an application, and there is a lack of collaboration between applications.

[0006] Due to the aforementioned issues, existing in-vehicle recommendation systems often perform poorly in practical use, requiring users to manually search for functions, which can distract them while driving and increase safety hazards. Therefore, there is a need for an intelligent in-vehicle recommendation method that can combine real-time vehicle status, user historical behavior, and safety factors to provide more accurate, safe, and convenient function recommendation services. Summary of the Invention

[0007] In view of this, the purpose of this invention is to provide a method for recommending in-vehicle applications based on user profile analysis, an in-vehicle application recommendation system based on user profile analysis, an electronic device and a storage medium, which aims to solve the problems of limited functionality and security risks in existing in-vehicle recommendation systems, and to facilitate users to use in-vehicle applications more accurately and safely.

[0008] This invention provides the following solution: According to one aspect of this application, a method for recommending in-vehicle applications based on user profile analysis is provided, comprising the following steps:

[0009] The data acquisition module collects user operation data, vehicle CAN bus data, and driving scenario data to generate an input dataset.

[0010] The input dataset is uploaded to a temporary storage component and then uploaded to a cloud server via the vehicle network according to the upload order.

[0011] Using the input dataset and the algorithm model, the corresponding recommendation weights for each application are generated.

[0012] The recommendation weights are sorted in descending order to generate recommendation cards carrying scene parameters;

[0013] The scenario parameters include: vehicle CAN bus data and driving scenario data;

[0014] The system launch module responds to the target user's click on the system-level recommendation card.

[0015] Furthermore, including:

[0016] The temporary storage component includes: storing the input dataset through an update queue;

[0017] Communicate with the cloud server and use the vehicle network to transmit data in queue order;

[0018] The cloud server receives data and categorizes and stores it.

[0019] Furthermore, including:

[0020] The categorized storage includes: vehicle CAN bus data and driving scenario data, which are updated in real time when the status changes;

[0021] User operation data is aggregated by application ID to count the number of application launches within a preset time threshold.

[0022] Furthermore, including:

[0023] The algorithm model is a time decay model algorithm, which obtains the corresponding weights of each application, and adjusts the coefficients dynamically to correct and generate recommendation cards carrying scene parameters.

[0024] Furthermore, including:

[0025] Driving scenario data includes: highway scenarios, urban congestion scenarios, parking lot scenarios, and stationary vehicle scenarios.

[0026] Furthermore, including:

[0027] The cross-application launch module includes: a deep linking component and a security interceptor;

[0028] The deep link component takes in the scene parameters through the intent launch mechanism provided by the system, launches the specified activity component of the target application, and jumps to the target function page of the recommended application.

[0029] Furthermore, including:

[0030] The intent initiation mechanism includes: security interceptors;

[0031] The security interceptor determines the safety of an operation based on scenario parameters;

[0032] When the scene parameter is a highway scene and the current vehicle speed exceeds the preset upper limit threshold, the launch request of entertainment applications is blocked.

[0033] When the scene parameter is urban congestion and the current vehicle speed is lower than the preset lower threshold, the launch requests of video playback and game applications are blocked.

[0034] Furthermore, including:

[0035] The cross-application launch module also includes a parameter feedback unit; the parameter feedback unit uploads the launch result of the target application, the user's operation time in the target application, and the interception records of the security interceptor to the cloud server.

[0036] Furthermore, including:

[0037] The cloud server adjusts the dynamic coefficients of the algorithm model or corrects the application's scenario matching degree.

[0038] If a user starts the target application and the operation time is preset to a threshold, the weight of this start record will be increased when the basic frequency factor is calculated next time.

[0039] If the same user is blocked from launching entertainment applications more than a preset number of times in a highway scenario, the base calculation value of the scenario matching degree of that type of entertainment application will be reduced.

[0040] According to two aspects of this application, an in-vehicle application recommendation system based on user profile analysis is provided, comprising:

[0041] The module includes a data acquisition module, a cloud synchronization module, a model calculation module, a recommendation generation module, and an operation response module.

[0042] The data acquisition module is used to collect user operation data, vehicle CAN bus data, and driving scenario data to generate an input dataset.

[0043] The cloud synchronization module is used to upload the input dataset to the temporary storage component and then upload it to the cloud server via the vehicle network according to the upload order.

[0044] The model calculation module is used to generate corresponding recommendation weights for each application by taking the input dataset and using the algorithm model.

[0045] The recommendation generation module is used to sort the recommendation weights in descending order and generate recommendation cards carrying scene parameters;

[0046] Scenario parameters include: vehicle CAN bus data and driving scenario data;

[0047] The action response module is used to respond to the target user's click on the recommended card through the cross-application launch module.

[0048] According to three aspects of this application, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0049] The memory stores a computer program that, when executed by a processor, causes the processor to perform steps of a vehicle application recommendation method based on user profile analysis.

[0050] According to four aspects of this application, a computer-readable storage medium is provided that stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform steps of a vehicle application recommendation method based on user profile analysis.

[0051] Compared with the prior art, the present invention has the following advantages:

[0052] This application utilizes a personalized application and function recommendation algorithm based on user profile analysis. This algorithm captures user interaction events and corresponding vehicle CAN bus data (including vehicle speed, gear status, charging connection status, etc.) in real time, uploading this data to the cloud via a point-based upload method. The cloud then categorizes and stores this information for easy application access. Simultaneously, it dynamically classifies driving scenario types (e.g., highway scenarios, urban congestion scenarios, parking lot scenarios, stationary vehicle scenarios, etc.) based on the vehicle's real-time movement and GPS location information. This data generates system-level recommendation cards, and the algorithm determines the recommended order of applications within these cards, along with recommendation information parameters. A system-level DeepLinkController parses the recommendation card click events and transmits the recommendation information parameters to the applications. This addresses the issues of limited functionality and security vulnerabilities in existing in-vehicle recommendation systems, enabling users to use in-vehicle applications more accurately and safely. Attached Figure Description

[0053] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0054] Figure 1 This is a flowchart of an in-vehicle application recommendation method based on user profile analysis provided by one or more embodiments of the present invention.

[0055] Figure 2 This is a structural diagram of an in-vehicle application recommendation system based on user profile analysis provided by one or more embodiments of the present invention.

[0056] Figure 3 This is a block diagram of an electronic device structure for a vehicle application recommendation method based on user profile analysis, provided by one or more embodiments of the present invention. Detailed Implementation

[0057] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Figure 1 This is a flowchart of an in-vehicle application recommendation method based on user profile analysis provided by one or more embodiments of the present invention.

[0059] like Figure 1 As shown, it includes the following steps:

[0060] Step S1: Collect user operation data, vehicle CAN bus data, and driving scenario data through the data acquisition module to generate an input dataset;

[0061] Specifically, by collecting data from user-initiated application launch points, vehicle status data on the CAN bus, and driving scenario data, the model's input dataset is generated based on the collected multi-source data.

[0062] Step S2: Upload the input dataset to the temporary storage component, and then upload it to the cloud server via the vehicle network according to the upload order;

[0063] Specifically, the collected input dataset is categorized and temporarily stored through an upload queue. Data is transmitted via the vehicle's network using a network connection to the cloud. When data is in the queue, it is uploaded to the cloud sequentially. Each time a user launches the application, the application ID, number of clicks, and current date are recorded; key information on the CAN bus, such as vehicle speed, vehicle dwell time, battery charge, and steering wheel angle, is also recorded; and the current driving scenario, such as highway, commuting, or parking, is generated. This data is updated in the queue and uploaded to the cloud in real time. The cloud stores the data in categories, with CAN bus data and driving scenario data updated in real time with each change. User application launch data is counted by application ID and organized according to the current date, recording only the total for the most recent 7 days.

[0064] Step S3: Using the input dataset and the algorithm model, generate the corresponding recommendation weights for each application.

[0065] Specifically, the algorithm calculates the weight of each application, and the applications with the highest weights are displayed in order in the recommendation cards, along with scene parameters. This way, when a user clicks on a recommended application, the application directly leads to the corresponding scene, reducing the time users spend searching for specific functions and thus avoiding the convenience and security issues caused by excessively deep hierarchies.

[0066] The algorithm is defined as follows: .in:

[0067] Defined as the fundamental frequency factor.

[0068] Defined as a real-time scenario factor, it is derived from the current driving scenario and the degree of application matching.

[0069] Defined as an emergency factor, such as charging demand: Refueling needs: ;

[0070] The factory default setting is for dynamically adjusting the coefficient. , , It is dynamically generated and changes based on user driving habits. For example, if a user has battery / fuel anxiety, they will need to charge / refuel when the battery / fuel level is low. Therefore, the γ coefficient will gradually increase with the user's driving habits, eventually becoming... , , Users tend to perform the same behaviors in specific scenarios, which will cause the beta coefficient to increase, eventually becoming... , , .

[0071] Step S4: Arrange the recommendation weights in descending order to generate recommendation cards carrying scene parameters;

[0072] The scenario parameters include: vehicle CAN bus data and driving scenario data;

[0073] Specifically, based on the dynamically adjusted coefficients, the applications are sorted from high to low according to their weights to obtain recommendation cards carrying scenario parameters.

[0074] The dynamic adjustment coefficient is adaptively adjusted based on user operating habits. If a user frequently launches the charging application when the battery is low, the corresponding dynamic adjustment coefficient will be adjusted; if a user repeatedly launches the same application in a fixed scenario, the corresponding dynamic adjustment coefficient will be adjusted.

[0075] Step S5: Respond to the target user's click operation on the system-level recommendation card through the cross-application launch module.

[0076] Specifically, when the app corresponding to the recommended card is clicked, a cross-application launch module is used to launch the corresponding app. This module implements an in-vehicle DeepLinkController, which uses the Android system's `startIntent` method to pass the appropriate parameters to launch the app's activity, automatically redirecting to the recommended app's corresponding function tab. Simultaneously, the DeepLinkController needs to implement a security interceptor mechanism, which uses the parameters in `startIntent` for judgment. For example, in a highway scenario, launching entertainment functions like iQiyi is prohibited. If iQiyi is attempted to be launched at this time, because the parameters passed to `startIntent` include vehicle speed information and the current driving scenario (highway), the DeepLinkController will intercept the redirect based on these parameters.

[0077] Furthermore, including:

[0078] The temporary storage component includes: storing the input dataset through an update queue;

[0079] Communicate with the cloud server and use the vehicle network to transmit data in queue order;

[0080] The cloud server receives data and categorizes and stores it.

[0081] Furthermore, including:

[0082] The categorized storage includes: vehicle CAN bus data and driving scenario data, which are updated in real time when the status changes;

[0083] User operation data is aggregated by application ID to count the number of application launches within a preset time threshold.

[0084] Furthermore, including:

[0085] The algorithm model is a time decay model algorithm, which obtains the corresponding weights of each application, and adjusts the coefficients dynamically to correct and generate recommendation cards carrying scene parameters.

[0086] Furthermore, including:

[0087] Driving scenario data includes: highway scenarios, urban congestion scenarios, parking lot scenarios, and stationary vehicle scenarios.

[0088] Furthermore, including:

[0089] The cross-application launch module includes: a deep linking component and a security interceptor;

[0090] The deep link component takes in the scene parameters through the intent launch mechanism provided by the system, launches the specified activity component of the target application, and jumps to the target function page of the recommended application.

[0091] Specifically, when the target application is a charging application, the user is redirected to the page of nearby charging stations; when the target application is a navigation application, the user is redirected to the current route navigation page.

[0092] Furthermore, including:

[0093] The intent initiation mechanism includes: security interceptors;

[0094] The security interceptor determines the safety of an operation based on scenario parameters;

[0095] When the scene parameter is a highway scene and the current vehicle speed exceeds the preset upper limit threshold, the launch request of entertainment applications is blocked.

[0096] When the scene parameter is urban congestion and the current vehicle speed is lower than the preset lower threshold, the launch requests of video playback and game applications are blocked.

[0097] Specifically, entertainment applications are prohibited from being launched on highways, and applications requiring complex input operations are prohibited from being launched while driving.

[0098] Furthermore, including:

[0099] The cross-application launch module also includes a parameter feedback unit; the parameter feedback unit uploads the launch result of the target application, the user's operation time in the target application, and the interception records of the security interceptor to the cloud server.

[0100] Furthermore, including:

[0101] The cloud server adjusts the dynamic coefficients of the algorithm model or corrects the application's scenario matching degree.

[0102] If a user starts the target application and the operation time is preset to a threshold, the weight of this start record will be increased when the basic frequency factor is calculated next time.

[0103] If the same user is blocked from launching entertainment applications more than a preset number of times in a highway scenario, the base calculation value of the scenario matching degree of that type of entertainment application will be reduced.

[0104] Specifically, through personalized application and function recommendation algorithms based on user profile analysis, the system captures real-time user operation events and corresponding vehicle CAN bus data (including vehicle speed, gear status, charging connection status, etc.). This data is uploaded to the cloud via a point-based tracking method, where it is categorized and stored for easy application access. Simultaneously, based on the vehicle's real-time movement and GPS location information, driving scenario types are dynamically categorized (e.g., highway scenarios, urban congestion scenarios, parking lot scenarios, stationary vehicle scenarios, etc.). This data generates system-level recommendation cards, and the algorithm determines the recommended order of applications within these cards, along with recommendation information parameters. The system-level DeepLinkController parses the click events of the recommendation cards and transmits the recommendation information parameters to the applications. This addresses the issues of limited functionality and security vulnerabilities in existing in-vehicle recommendation systems, enabling users to use in-vehicle applications more accurately and safely.

[0105] Figure 2 This is a structural diagram of an in-vehicle application recommendation system based on user profile analysis provided by one or more embodiments of the present invention.

[0106] like Figure 2 As shown, it includes:

[0107] The module includes a data acquisition module, a cloud synchronization module, a model calculation module, a recommendation generation module, and an operation response module.

[0108] The data acquisition module is used to collect user operation data, vehicle CAN bus data, and driving scenario data to generate an input dataset.

[0109] The cloud synchronization module is used to upload the input dataset to the temporary storage component and then upload it to the cloud server via the vehicle network according to the upload order.

[0110] The model calculation module is used to generate corresponding recommendation weights for each application by taking the input dataset and using the algorithm model.

[0111] The recommendation generation module is used to sort the recommendation weights in descending order and generate recommendation cards carrying scene parameters;

[0112] Scenario parameters include: vehicle CAN bus data and driving scenario data;

[0113] The action response module is used to respond to the target user's click on the recommended card through the cross-application launch module.

[0114] It is worth noting that although only some basic functional modules are disclosed in this embodiment, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules does not mean that the scope of protection of the claims of this invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0116] In one embodiment, it includes: a data acquisition module, a recommendation generation module, and a cross-application launch module.

[0117] The data acquisition module is primarily used to collect embedded data when the user launches the application, vehicle status data on the CAN bus, and driving scenario data. First, a queue is established to store this data. Then, network communication with the cloud is established, using the vehicle's network (mobile data / Wi-Fi) for data transmission. When data is in the queue, it is uploaded to the cloud sequentially according to the queue order. Each time the user launches the application, the application ID, number of clicks, and current date are recorded; key information on the CAN bus, such as vehicle speed, vehicle dwell time, battery level, and steering wheel angle, is also recorded; the current driving scenario, such as highway, commuting, or parking, is generated. This data is updated in the queue and uploaded to the cloud in real time. The cloud stores the data in categories: CAN bus data and driving scenario data are updated in real time with each change; user application launch data is counted by application ID and organized according to the current date, recording only the total for the most recent 7 days.

[0118] Recommended generation module:

[0119] This module primarily generates recommendation card content. Based on an algorithm, it determines the weight of each application, and the applications with the highest weights are displayed sequentially in the recommendation cards, along with contextual parameters. This way, when a user clicks on a recommended application, the application directly leads to the corresponding context, reducing the time users spend searching for specific functions and thus avoiding the inconvenience and security issues caused by excessively deep hierarchical structures.

[0120] The algorithm is defined as follows: .in:

[0121] , is used to define the fundamental frequency factor;

[0122] This is used to define real-time scenario factors, derived from a comprehensive analysis of the current driving scenario and application matching degree.

[0123] This is used to define emergency factors, such as charging needs: Refueling needs: , The factory default setting is for dynamically adjusting the coefficient. , , It is dynamically generated and changed based on user driving habits. For example, if a user has battery / fuel anxiety, they will need to charge / refuel when the battery / fuel level is low. The coefficient will gradually increase as users develop their usage habits, and eventually the coefficient will become... , , Users tend to perform the same behaviors in specific scenarios, which will cause the beta coefficient to increase, eventually becoming... , , .

[0124] Cross-application launch module:

[0125] When the app corresponding to the recommended card is clicked, the cross-application launch module is used to launch the corresponding app. This module implements an in-vehicle DeepLinkController, which uses the Android system's `startIntent` method to pass the appropriate parameters to launch the app's activity, automatically redirecting to the recommended app's corresponding function tab. Simultaneously, DeepLinkController needs to implement a security interceptor mechanism that uses the parameters in `startIntent` for judgment. For example, in a highway scenario, launching entertainment functions like iQiyi is prohibited. If iQiyi is attempted to be launched at this time, because the parameters passed to `startIntent` include vehicle speed information and the current driving scenario (highway), DeepLinkController will intercept the redirection based on these parameters.

[0126] In another specific embodiment, suppose a user commutes by electric vehicle with 15% battery remaining, is traveling on a highway at 100 km / h, and the time is 8:00 AM (morning rush hour). The user has launched the navigation app 20 times, the music app 15 times, and started charging 10 times over 7 days.

[0127] First, generate a driving scenario: morning rush hour commute, and obtain CAN bus data: vehicle speed 100, battery level 15%, time 8:00 am.

[0128] Calculate the weights of navigation applications;

[0129] Fundamental frequency factor

[0130] Scene matching The current time is 8:00 AM, which is the commute time, and the route matches. However, since we are currently driving on the highway, there is no need to set a new route. Based on the overall scenario matching, the accuracy is determined.

[0131] urgency Navigation is not an urgent function, so ;

[0132] Therefore, weight ;

[0133] Calculate the weights of charging applications;

[0134] Frequency factor ;

[0135] Scene matching Currently on the highway, but not all highways have charging stations, and this is a commuting scenario, not suitable for charging en route. Therefore, the scenario matching is relatively low. .

[0136] urgency Battery level is 15%, so ;

[0137] Therefore, weight ;

[0138] Calculate the weights of music applications.

[0139] Frequency factor ;

[0140] Scene matching In high-speed commuting scenarios, playing some music is suitable to help users improve their mood. Therefore, the scenario matching degree is high. .

[0141] urgency The music function is also not considered urgent. .

[0142] Therefore, weight ;

[0143] After considering all the weights, the recommended cards at this point would display navigation, music, and then charging. However, if the user has battery anxiety, the order would be adjusted accordingly. The result was recalculated after the coefficient was increased, and the result was obtained again. , , At this point, charging has the highest priority, and the recommended cards will prioritize charging.

[0144] Similarly, if user behavior remains fixed in a specific scenario, the result can be recalculated based on the increased beta coefficient. = 1.416, , At this point, music has the highest weight, and the recommended cards will place music first.

[0145] These scenarios effectively demonstrate the strong correlation between user profiles and recommended applications.

[0146] If the user clicks on an application, such as "Charging", the recommendation card will pass the current parameters to the charging application through DeepLinkController. When the charging application receives these parameters (vehicle speed 100, battery level 15%, time 8:00 am, scenario: highway commuting, etc.), it will recognize that it may need to find a nearby charging station and directly jump to the nearby charging station interface.

[0147] Figure 3 This is a block diagram of an electronic device structure for a vehicle application recommendation method based on user profile analysis, provided by one or more embodiments of the present invention.

[0148] like Figure 3 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0149] The memory stores a computer program that, when executed by the processor, causes the processor to perform steps of a vehicle network communication method based on CAN and Ethernet redundancy.

[0150] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a vehicle network communication method based on CAN and Ethernet redundancy.

[0151] Technical concepts involved:

[0152] Cloud:

[0153] The cloud is a widely used concept that connects remote servers and resources via the Internet, providing powerful computing capabilities, storage capacity, and service support, enabling efficient development and deployment of applications, processing and management of data, and more.

[0154] Time decay model algorithm:

[0155] The Time Decay Model is a mathematical method used to quantify the decay of an event's influence over time. This model allows for a more scientific quantification of the impact of time on the value of an event.

[0156] DeepLinkController:

[0157] DeepLinkController is the core routing controller in an in-vehicle system that enables direct access to functions across applications. By parsing standardized protocols, it achieves seamless switching and parameter transfer between different applications. Through a unified routing protocol and security control mechanism, it completely solves the pain points of fragmented functions and cumbersome operation in traditional in-vehicle systems, and is the core infrastructure for realizing "intelligent scene linkage".

[0158] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0159] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for recommending in-vehicle applications based on user profile analysis, characterized in that, Includes the following steps: The data acquisition module collects user operation data, vehicle CAN bus data, and driving scenario data to generate an input dataset. The input dataset is uploaded to a temporary storage component and then uploaded to a cloud server via the vehicle network according to the upload order. Using the input dataset and the algorithm model, the corresponding recommendation weights for each application are generated. The recommendation weights are sorted in descending order to generate recommendation cards carrying scene parameters; The scenario parameters include: vehicle CAN bus data and driving scenario data; The system launch module responds to the target user's click on the system-level recommendation card.

2. The in-vehicle application recommendation method based on user profile analysis according to claim 1, characterized in that, The temporary storage component includes: storing the input dataset through an update queue; Communicate with the cloud server and use the vehicle network to transmit data in queue order; The cloud server receives data and categorizes and stores it.

3. The in-vehicle application recommendation method based on user profile analysis according to claim 2, characterized in that, The categorized storage includes: the vehicle CAN bus data and driving scenario data are updated in real time when the status changes; The user operation data is calculated by summing the application IDs and counting the number of application launches within a preset time threshold.

4. The in-vehicle application recommendation method based on user profile analysis according to claim 1, characterized in that, The algorithm model is a time decay model algorithm, which obtains the corresponding weights of each application and corrects the generated recommendation cards carrying scene parameters based on the dynamically adjusted coefficients.

5. The in-vehicle application recommendation method based on user profile analysis according to claim 1, characterized in that, The driving scenario data includes: highway scenarios, urban congestion scenarios, parking lot scenarios, and stationary vehicle scenarios.

6. The in-vehicle application recommendation method based on user profile analysis according to claim 1, characterized in that, The cross-application launch module includes: a deep linking component and a security interceptor; The deep linking component receives the scene parameters through the intent-based initiation mechanism provided by the system, initiates the display of the specified interface of the target application and the response to user operations, and jumps to the target function page of the recommended application.

7. The in-vehicle application recommendation method based on user profile analysis according to claim 6, characterized in that, The security interceptor includes: The security interceptor determines the safety of the operation based on scenario parameters; When the scene parameter is a highway scene and the current vehicle speed exceeds the preset upper limit threshold, the launch request of entertainment applications is blocked. When the scene parameter is urban congestion and the current vehicle speed is lower than the preset lower threshold, the launch requests of video playback and game applications are blocked.

8. A vehicle application recommendation system based on user profile analysis, characterized in that, include: Data acquisition module, cloud synchronization module, model calculation module, recommendation generation module, and cross-application launch module; The data acquisition module is used to collect user operation data, vehicle CAN bus data, and driving scenario data to generate input datasets; The cloud synchronization module is used to upload the input dataset to the temporary storage component and then upload it to the cloud server via the vehicle network according to the upload order. The model calculation module is used to generate corresponding recommendation weights for each application using the input dataset and an algorithm model. The recommendation generation module is used to sort the recommendation weights in descending order and generate recommendation cards carrying scene parameters; The scenario parameters include: vehicle CAN bus data and driving scenario data; A cross-application launch module is used to respond to a target user's click on the system-level recommendation card.

9. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the in-vehicle application recommendation method based on user profile analysis as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the in-vehicle application recommendation method based on user profile analysis as described in any one of claims 1-7.

Images