Method for generating recommended application list and vehicle

Abstract

The invention discloses a method for generating a recommended application list and a vehicle, and is applied to the technical field of data processing. According to the method for generating the recommended application list, vehicle-mounted terminal application data focuses on behaviors and requirements of a user in a driving scene, and the vehicle-mounted terminal application data is used for generating the first recommended application list, so that application use habits of the user when the user uses mobile equipment to interact with a vehicle-mounted terminal can be reflected; the mobile terminal application data records various behaviors and preferences of the user in daily life, the second recommended application list is generated according to the mobile terminal application data, the application use habits of the user in the mobile terminal can be reflected, and the first recommended application list and the second recommended application list are fused, so that the user experience is improved. According to the method, the target recommendation application number is obtained, the fused recommendation application list is generated according to the target recommendation application number, finally, the recommendation application list which is more personalized and meets scene use can be obtained, the intelligence and convenience of a vehicle-mounted terminal system are improved, and the actual requirements of a vehicle-mounted terminal user in the driving process are effectively met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a method for generating a recommended application list and a vehicle. BACKGROUND

[0002] With the deep integration of mobile communication and intelligent terminal technology, mobile device-IVI interconnection technology has become an important development direction in the field of intelligent vehicles. At present, the mainstream interconnection scheme can project the massive application ecology of mobile terminals to the IVI system, greatly enriching the application service capability of the IVI end. However, the existing technical solutions have significant defects in the application recommendation and display logic, which restricts the user experience and driving safety. Specifically, the current implementation method highly depends on the original application recommendation algorithm and sorting logic on the mobile device side. The use scenario of the IVI user is unique, and its demand is quite different from that of the mobile device user. During driving, the user needs to concentrate on attention, the operation should be as simple and safe as possible, and the requirement for information acquisition and processing should be fast and accurate. The recommended application algorithm on the mobile device cannot fully consider these characteristics of the IVI scenario, and if it is directly applied to the IVI display, it often cannot accurately match the actual needs of the user in the vehicle. Therefore, the existing mobile device recommended application algorithm cannot be directly adapted to the IVI scenario display, and cannot effectively meet the actual needs of the IVI user during driving, which has become a problem to be solved in the development process of the current IVI system and mobile device interconnection technology. SUMMARY

[0003] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method for generating a recommended application list and a vehicle, which can generate a recommended application list by fusing mobile terminal data and IVI end data of the IVI application, and is more in line with the use habits of the IVI user.

[0004] According to a first aspect of the present application, a method for generating a recommended application list is provided, comprising: obtaining mobile terminal application data, IVI end application data and a target recommended application quantity; wherein the mobile terminal application data comprises an application behavior spectrum of the mobile terminal and an application set supported by the mobile terminal for running on the IVI end, and the IVI end application data comprises interaction data between the mobile terminal and the IVI end and application behavior data of the IVI end; generating a first recommended application list according to the interaction data between the mobile terminal and the IVI end and the application behavior data of the IVI end; generating a second recommended application list according to the application behavior spectrum of the mobile terminal, the application set supported by the mobile terminal for running on the IVI end and the target recommended application quantity; and generating a fused recommended application list according to the first recommended application list, the second recommended application list and the target recommended application quantity.

[0005] As a possible implementation manner, the interaction data between the mobile terminal and the vehicle terminal includes: a number of times of triggering an application from the mobile terminal to display on the vehicle terminal and a number of times of migrating the application from the mobile terminal to the vehicle terminal; the application behavior data of the vehicle terminal includes: a category to which the application belongs on the vehicle terminal and a score ranking of the application on the vehicle terminal; wherein, the first recommended application list is generated according to the interaction data between the mobile terminal and the vehicle terminal and the application behavior data of the vehicle terminal, including: for the interaction data between the mobile terminal and the vehicle terminal and the application behavior data of the vehicle terminal, when any one of the following four conditions meets, the recommended value of the application is calculated according to the data meeting the condition and the corresponding weight; wherein, the four conditions include: the number of times of triggering the application from the mobile terminal to display on the vehicle terminal is greater than a first preset number of times, the number of times of migrating the application from the mobile terminal to the vehicle terminal is greater than a second preset number of times, the application belongs to an application category already installed on the vehicle terminal, and the application has a score on the vehicle terminal; or, when any one of the four conditions does not meet the preset requirement, the recommended value of the application is set to 0; ranking is performed based on the recommended value of each application to generate the first recommended application list.

[0006] The recommended value of the application is calculated by multi-dimensional score calculation, which can quantify multi-dimensional value and avoid single standard deviation. If only a single indicator (such as download volume or score) is relied on to evaluate the application, the personalized use characteristics of the user may be ignored. By triggering the display number of times, the migration number of times, the category, and the application ranking for scoring, the multi-dimensional value of the application can be fully captured to ensure that the recommended result is closer to the actual needs of the user. In addition, the demand for applications of different user groups is significantly different, and the weights of the conditions can be adjusted for different scenarios to make the recommended score more targeted. If it is necessary to add or reduce conditions, only the score of the new condition needs to be defined or the score of the old condition needs to be directly reduced, and the total score can still be calculated without affecting the overall logic. The weight of the condition can also be dynamically adjusted to adjust the importance of different dimensions. Therefore, this method of calculating the recommended value is objective and transparent, the rules are clear, the discrimination is high, it can reflect multi-dimensional advantages, and the calculation is simple. The final first recommended application list not only meets the personalized characteristics of the user, but also is suitable for the special scenario of the vehicle terminal.

[0007] As a possible implementation manner, when any one of the following four conditions meets, the recommended value of the application is calculated according to the data meeting the condition and the corresponding weight, including: when the number of times of triggering the application from the mobile terminal to display on the vehicle terminal is greater than a first preset number of times, a first number of times weight of the application is determined according to the number of times of triggering the application from the mobile terminal to display on the vehicle terminal; wherein, the number of times of triggering the application from the mobile terminal to display on the vehicle terminal is proportional to the first number of times weight; the product of the first number of times weight and a first preset feature weight is calculated as the first recommended value of the application; wherein, the first preset feature weight represents a predefined weight value of the first number of times weight.

[0008] The product of the first frequency weight and the first preset feature weight is calculated as the first recommended value of the application. The first preset feature weight can reflect the importance of the frequency of the application triggered from the mobile terminal to the display of the vehicle terminal. The first preset feature weight can be pre-set based on expert experience, historical data or theoretical analysis. The product of the first frequency weight and the first preset feature weight can be regarded as a measure of the comprehensive importance of the frequency of the application triggered from the mobile terminal to the display of the vehicle terminal, which takes into account both the theoretical importance of the frequency of triggering and display and the actual situation, so that the finally calculated first recommended value is more reasonable and adapts to the actual use of the user.

[0009] As a possible implementation, when any of the following four conditions is met, the recommended value of the application is calculated according to the data meeting the condition and the corresponding weight, including: when the frequency of the application migrating from the mobile terminal to the vehicle terminal is greater than the second preset frequency, determining the second frequency weight of the application; wherein the frequency of the application migrating from the mobile terminal to the vehicle terminal is proportional to the second frequency weight; calculating the product of the second frequency weight and the second preset feature weight as the second recommended value of the application; wherein the second preset feature weight represents a predefined weight value of the second frequency weight, and the second preset feature weight is less than the first preset feature weight.

[0010] The product of the second frequency weight and the second preset feature weight is calculated as the second recommended value of the application. The second preset feature weight can reflect the importance of the frequency of the application triggered from the mobile terminal to the display of the vehicle terminal. The first preset feature weight can be pre-set based on expert experience, historical data or theoretical analysis. The product of the second frequency weight and the second preset feature weight can be regarded as a measure of the comprehensive importance of the frequency of the application triggered from the mobile terminal to the display of the vehicle terminal, which takes into account both the theoretical importance of the frequency of triggering and display and the actual situation, so that the finally calculated second recommended value is more reasonable and adapts to the actual use of the user.

[0011] As a possible implementation, when any of the following four conditions is met, the recommended value of the application is calculated according to the data meeting the condition and the corresponding weight, including: when the application belongs to the application category installed on the vehicle terminal, determining the category weight of the application according to the category to which the application belongs; wherein the weight proportion of each category is predefined according to the application category of the vehicle terminal to form the category weight; calculating the product of the category weight and the third preset feature weight as the third recommended value of the application; wherein the third preset feature weight represents a predefined weight value of the category weight, and the third preset feature weight is less than the second preset feature weight.

[0012] The product of the category weight and the third preset feature weight is calculated to obtain the third recommendation value of the application. The category weight reflects the actual interest degree of the current user or user group in the category, or reflects the importance of the application on the vehicle terminal. The third preset feature weight is a fixed value or an adjustment range preset in advance, and reflects the objective influence of the category on the recommendation. Therefore, the third recommendation value calculated finally respects the personal preferences of the user and meets the core needs of the scene, and the data has comprehensive characteristics.

[0013] As a possible implementation manner, when any one of the following four conditions is met, the recommendation value of the application is calculated according to the data meeting the condition and the corresponding weight, including: when the application has a score on the vehicle terminal, the ranking weight of the application is determined according to the score ranking of the application; wherein the ranking weight is proportional to the score ranking of the application on the vehicle terminal, and the higher the score ranking, the greater the value of the ranking weight; the product of the ranking weight and the fourth preset feature weight is calculated as the fourth recommendation value of the application; wherein the fourth preset feature weight represents a predefined weight value of the ranking weight, the fourth preset feature weight is less than the second preset feature weight, and the fourth preset feature weight is greater than the third preset feature weight.

[0014] The product of the ranking weight and the fourth preset feature weight is calculated as the fourth recommendation value of the application. The recommendation index of the application can be considered from the perspective of big data to provide a reference for the user. Or, in the case where the user does not have specific operations, the initial recommendation can be made according to the popular applications on the market to ensure that the user has a good user experience when using the application on the vehicle terminal for the first time.

[0015] As a possible implementation manner, when any one of the following four conditions is met, the recommendation value of the application is calculated according to the data meeting the condition and the corresponding weight, including: the sum of the recommendation values corresponding to the conditions meeting the conditions is calculated as the recommendation value of the application.

[0016] Only the recommendation value corresponding to the condition meeting the condition can be used as the recommendation value of the application, which ensures that the result has multi-dimensional adaptability and meets the user behavior characteristics and the scene characteristics of the vehicle terminal.

[0017] As a possible implementation manner, the fusion recommendation application list is generated according to the first recommended application list, the second recommended application list and the target number of recommended applications, including: when there are repeated applications in the first recommended application list and the second recommended application list, the repeated applications are weighted and sorted; and the fusion recommendation application list is generated according to the order after the weighted sorting and the target number of recommended applications.

[0018] The fusion of the two recommended application lists remedies the defects of a single strategy, takes the strengths and weaknesses, and makes the results both personalized and robust. A single list may focus on a certain dimension, resulting in a narrow range of recommendations. Fusion of multiple lists from different sources can cover a wider range of candidate items, avoid information silos, and provide users with more diverse options. When a recommended application list is insufficient, other application lists can be used to supplement it, avoiding interruptions or quality drops in recommendations.

[0019] As a possible implementation, generating a second recommended application list according to the application behavior spectrum of the mobile terminal and the application set supported by the mobile terminal for running on the car machine end and the target number of recommended applications includes: generating a personalized application recommendation set according to the application behavior spectrum of the mobile terminal; determining overlapping applications according to the personalized application recommendation set and the application set supported by the mobile terminal for running on the car machine end; and generating a second recommended application list according to the overlapping applications and the target number of recommended applications.

[0020] The number of applications in the personalized application recommendation set is not fixed, and there may be applications that do not support display on the car machine end, so they need to be supplemented and screened. According to the personalized application recommendation set and the application set supported by the mobile terminal for running on the car machine end, the overlapping applications are determined, and the second recommended application list is generated according to the overlapping applications and the target number of recommended applications. Overlapping applications represent applications that are frequently used by users and can be displayed on the car machine end, and such applications should belong to the second recommended application list. However, the number of such applications may be insufficient, and in the case of insufficient applications, the remaining applications that do not overlap with the personalized application recommendation set can be supplemented to the second recommended application list in order.

[0021] According to a second aspect of the present application, a device for generating a recommended application list is provided, including: an acquisition module for acquiring mobile terminal application data, car machine end application data, and a target number of recommended applications; wherein the mobile terminal application data includes an application behavior spectrum of a mobile terminal and an application set supported by the mobile terminal for running on the car machine end, the car machine end application data includes interaction data between the mobile terminal and the car machine end and application behavior data of the car machine end; a first generation module for generating a first recommended application list according to the interaction data between the mobile terminal and the car machine end and the application behavior data of the car machine end; a second generation module for generating a second recommended application list according to the application behavior spectrum of the mobile terminal and the application set supported by the mobile terminal for running on the car machine end and the target number of recommended applications; and a third generation module for generating a fusion recommended application list according to the first recommended application list, the second recommended application list, and the target number of recommended applications.

[0022] According to a third aspect of the present application, a vehicle is provided, comprising: an in-vehicle interaction system, representing a car-end, the in-vehicle interaction system being communicatively connected with a mobile terminal; and a device for generating a recommended application list, the device being configured to perform the method for generating a recommended application list according to the first aspect or any one of the implementation forms of the first aspect, the device being communicatively connected with the in-vehicle interaction system and the mobile terminal.

[0023] According to a fourth aspect of the present application, a computer device is provided, comprising: one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processors to implement the method according to the first aspect or any one of the implementation forms of the first aspect.

[0024] According to a fifth aspect of the present application, a computer readable storage medium is provided, storing a computer program for performing the method according to the first aspect or any one of the implementation forms of the first aspect.

[0025] According to a sixth aspect of the present application, an electronic device is provided, comprising modules for performing the method according to the first aspect or any one of the implementation forms of the first aspect.

[0026] According to a seventh aspect of the present application, a computer program product is provided, comprising program codes for performing the method according to the first aspect or any one of the implementation forms of the first aspect.

[0027] The method for generating a recommended application list and the vehicle provided by the present application focus on the behaviors and needs of the user in the driving scenario, and generate a first recommended application list based on the application data of the car-end, which can reflect the application usage habits of the user when using the mobile device and the car-end. The application data of the mobile terminal records various behaviors and preferences of the user in daily life, covering diversified usage scenarios, and a second recommended application list is generated based on the application data of the mobile terminal, which can reflect the application usage habits of the user when using the mobile terminal. The data fusion of the mobile terminal and the car-end can capture the switching and changes of the user between different scenarios, deeply understand the application usage habits of the user, build a more stereoscopic user model, and break through the data limitations of a single terminal. Therefore, by combining the application usage habits of the user and the specific car usage scenario, a fusion recommended application list is generated, which can generate a more personalized and scenario-compliant recommended application list, improving the intelligence and convenience of the car system and effectively meeting the actual needs of the car user in the driving process. BRIEF DESCRIPTION OF DRAWINGS

[0028] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of the preferred embodiments of the present application taken in conjunction with the accompanying drawings. The drawings provided in the present application are for purposes of illustration only and, as such, are not intended to limit the present application. The drawings provided are intended to be illustrative, and the present application is not limited to the specific instruments, devices, and methods depicted in the figures.

[0029] Figure 1 is a flowchart of a method for generating a recommended application list according to an example embodiment of the present application.

[0030] Figure 2 is a structural diagram of an apparatus for generating a recommended application list according to an example embodiment of the present application.

[0031] Figure 3 is a structural diagram of an electronic device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0032] Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are merely a part of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

[0033] In today's era of rapid technological development, mobile Internet technology is reshaping people's lives and travel methods at an unprecedented speed. With the deep integration of mobile communication and smart terminal technology, mobile device-vehicle infotainment technology has become an important development direction in the field of intelligent vehicles. At present, mainstream interconnection solutions (such as Apple CarPlay, Huawei HiCar, Baidu CarLife+, etc.) can project the massive application ecosystem of mobile terminals to the vehicle infotainment system, and generally support unified display interfaces that integrate desktops, greatly enriching the application service capabilities of the vehicle infotainment system.

[0034] However, the existing technical solutions have significant defects in application recommendation and display logic, which restricts user experience and driving safety. There are mainly two technical paths in current practice: The first path is to directly transplant the recommendation logic of the mobile terminal. Taking the mobile terminal as a mobile phone terminal as an example, this way highly depends on the original application recommendation algorithm and sorting logic of the mobile phone side. These algorithms are optimized based on the behavior data of the user in the mobile phone environment (such as usage frequency, click rate, etc.), and the core goal is to improve the use stickiness of the mobile phone terminal user in the mobile or stationary state. Directly applying this logic to the car machine produces a serious scene mismatch problem: 1. The demand difference is huge. The core demand of the driving scene is safety and convenience (such as navigation, communication), and the high-frequency applications recommended by the mobile phone (such as social media and short videos) are often not applicable and pose a safety risk when driving; 2. Interaction and attention are contradictory. Car machine interaction requires simplicity and low attention consumption, while the mobile phone type recommendation interface is complex and can easily distract the driver.

[0035] The second path is to avoid the mismatch of mobile phone recommendations and instead use a simple car machine hot application list for recommendations. This way, although it filters out mobile phone applications that are completely unsuitable for the driving scene to some extent, it also has obvious defects: it completely lacks personalization and ignores the individualized habits, preferences, and historical behavior of different drivers, providing a uniform hot or default application list for all users. For example, a user who never listens to audio programs may be repeatedly recommended a podcast application, while a heavy user of a specific navigation function may need to perform multiple operations to find the application. The hot list is essentially a statistical result of group behavior and cannot meet the differentiated and dynamic needs of individuals in specific journeys (such as long-distance driving and daily commuting) and specific times (such as commuting hours and weekend outings). In addition, the fixed hot recommendation makes the car machine interface lose its intelligence and exclusivity, and it cannot actively learn and adapt to the user's deep preferences, hindering the continuous optimization of the user experience.

[0036] Therefore, the existing technology is in a dilemma: on the one hand, directly using mobile device recommendation algorithms can lead to serious scene mismatches and safety hazards; on the other hand, using car machine hot recommendations can sacrifice the necessary personalized experience, making the intelligent car machine system degenerate into a simple display terminal. Therefore, there is an urgent need in the art for an innovative solution that can deeply understand the core constraints of driving scene safety and convenience, deeply integrate vehicle context information and driver individualized portrait, and achieve dynamic, precise, and safe scene-based application recommendation and display, thereby truly breaking the above dilemma and improving the interaction efficiency and user experience during driving.

[0037] To solve the above problems, the present application provides a method for generating a recommended application list, Figure 1 is a flowchart of the method for generating a recommended application list provided by an example embodiment of the present application, which is described in detail below with reference to Figure 1 For example, first, mobile terminal application data, car machine application data, and the target number of recommended applications are obtained (see FIG. 1).Figure 1 application data of the mobile terminal and a set of applications supported by the mobile terminal to run on the vehicle terminal, and the vehicle terminal application data includes interaction data between the mobile terminal and the vehicle terminal and application behavior data of the vehicle terminal. Then, a first recommended application list is generated according to the interaction data between the mobile terminal and the vehicle terminal and the application behavior data of the vehicle terminal (see S120 of FIG. 1). Figure 1 Figure 1 application behavior spectrum of the mobile terminal and the set of applications supported by the mobile terminal to run on the vehicle terminal and a target number of recommended applications, to generate a second recommended application list (see S130 of FIG. 1). Figure 1

[0038] The method for generating a recommended application list provided by the embodiments of the present application will be described in more detail below in conjunction with Figure 1

[0039] In S110, mobile terminal application data, vehicle terminal application data and a target number of recommended applications are obtained.

[0040] application behavior spectrum of the mobile terminal and a set of applications supported by the mobile terminal to run on the vehicle terminal, and the vehicle terminal application data includes interaction data between the mobile terminal and the vehicle terminal and application behavior data of the vehicle terminal.

[0041] In some embodiments, the application behavior spectrum of the mobile terminal is a data structure or a visual chart that systematically records and analyzes the application behavior patterns and features of the mobile terminal, and is essentially a structured or visual data model. For example, the behavior of the mobile device application during runtime is recorded, classified and displayed in chart form through technical means (such as dynamic analysis, data capture, AI modeling, etc.), thereby forming a chart reflecting the application behavior features. According to the application behavior spectrum, user groups can be divided, and user behavior preferences in different scenarios can be studied to achieve accurate recommendation.

[0042] ​​​In some embodiments, the interaction data between the mobile terminal and the vehicle terminal includes: the number of times of triggering an application from the mobile terminal to display on the vehicle terminal, and the number of times of migrating the application from the mobile terminal to the vehicle terminal. By counting the number of times of triggering an application from the mobile terminal to display on the vehicle terminal, it can be clearly identified which applications are frequently initiated by the user on the mobile terminal and which applications the user wants to continue to use or view related information on the vehicle terminal. For example, for navigation applications, the user may first plan a route on the mobile terminal, and then continue to use the navigation information on the vehicle terminal after getting into the car. For music applications, the user may select a playlist on the mobile terminal, and then synchronize the playback on the vehicle terminal after getting into the car. These high-frequency cross-terminal applications can be given higher weights in the vehicle recommendation list to allow the user to quickly find and use them, thereby improving the user experience. By analyzing the number of times of migrating the application from the mobile terminal to the vehicle terminal, the user's application migration behavior in different scenarios can be understood. For example, during the morning and evening rush hours on weekdays, the user may be more inclined to migrate news and information applications from the mobile terminal to the vehicle terminal to understand the current situation during the commute. However, during the weekend, the number of times of migrating travel guide applications may increase. According to these rules, the cross-terminal applications that the user may need can be accurately recommended in different time periods and scenarios, thereby improving the timeliness and pertinence of the recommendations.

[0043] In some embodiments, the application behavior data of the vehicle terminal includes: the category of the application on the vehicle terminal, and the scoring ranking of the application on the vehicle terminal. The vehicle terminal can count the category composition of the installed applications of the vehicle system, and assign a value to each category to calculate the category weight. For example, the installed applications are divided into three categories according to the function, namely navigation, entertainment, and safety assistance, and the navigation application is assigned a category weight of 5, the entertainment application is assigned a category weight of 3, and the safety assistance application is assigned a category weight of 7. Alternatively, the categories can be divided according to the use scenario, such as driving scenario commonly used and non-driving scenario commonly used. The category composition and the assignment of the category weight can be set according to the actual needs of the user and the specific vehicle terminal plan. The scoring ranking of the application on the vehicle terminal is the hot application of the vehicle terminal generated by big data statistics, for example, the hot application of the vehicle terminal is generated according to the application use frequency and the score of multiple vehicles. For the scoring ranking of the application on the vehicle terminal, the specific ranking can be assigned a value, for example, when the vehicle terminal is ranked first, the ranking weight is 10, or the ranking range can be divided to assign a value, for example, the top 5 vehicle terminal applications are assigned a value of 10. The specific value and the value assignment method can be freely set.

[0044] In S120, a first recommended application list is generated according to the interaction data between the mobile terminal and the vehicle terminal and the application behavior data of the vehicle terminal.

[0045] In some embodiments, if the number of times of using the application is counted, it will bring a large operation burden. In order to save resources, it can be judged in priority whether the data meets the condition of calculation operation. For example, for each application, the interaction data between the mobile terminal and the vehicle terminal and the application behavior data of the vehicle terminal, when any one of the following four conditions is met, the recommended value of the application is calculated according to the data meeting the condition and the corresponding weight. The four conditions include: the number of times of triggering the application from the mobile terminal to the vehicle terminal display is greater than the first preset number of times, the number of times of migrating the application from the mobile terminal to the vehicle terminal is greater than the second preset number of times, the application belongs to the installed application category of the vehicle terminal, and the application has a score on the vehicle terminal. If any one of the four conditions of an application does not meet the preset requirement, the recommended value of the application is set to 0. Finally, ranking is performed based on the recommended value of each application to generate a first recommended application list.

[0046] By calculating the recommended value of the application through multi-dimensional scoring, the multi-dimensional value can be quantified, and the single standard deviation can be avoided. If only a single indicator (such as download volume, score) is used to evaluate the application, the personalized use characteristics of the user may be ignored. By scoring the number of triggering displays, the number of migrations, the constituent category, and the application ranking, the multi-dimensional value of the application can be fully captured, and the recommended result can be ensured to be closer to the actual needs of the user. In addition, the demand for applications of different user groups is significantly different. The weights of the conditions can be adjusted for different scenarios, so that the recommended score is more targeted. If it is necessary to add conditions or reduce conditions, only the score of the new condition needs to be defined or the score of the old condition needs to be directly reduced. The total score can still be calculated, the overall logic is not affected, and the weights of the conditions can be dynamically adjusted to adjust the importance of different dimensions. Therefore, this method of calculating the recommended value is objective and transparent, the rules are clear, the discrimination is high, the multi-dimensional advantages can be reflected, and the calculation is simple. The final first recommended application list not only meets the personalized characteristics of the user, but also is suitable for the special scenario of the vehicle terminal.

[0047] In some embodiments, when the number of times of triggering the application from the mobile terminal to the vehicle terminal display is greater than the first preset number of times, the recommended value of the application can be calculated according to the number of times. For example, when the number of times of triggering the application from the mobile terminal to the vehicle terminal display is greater than the first preset number of times, the first number of times weight of the application is determined according to the number of times of triggering the application from the mobile terminal to the vehicle terminal display; wherein the number of times of triggering the application from the mobile terminal to the vehicle terminal display is proportional to the first number of times weight; the product of the first number of times weight and the first preset feature weight is calculated as the first recommended value of the application; wherein the first preset feature weight represents the weight value of the predefined first number of times weight.

[0048] For the first preset feature weight, when an application meets the condition, the preset feature weight is assigned to the condition. For example, if the trigger display times of the application is greater than the first preset times, the first preset feature weight is 8. The first preset feature weight is determined according to the importance of the number of times that the mobile terminal triggers the display on the vehicle terminal. Since the number of times that the mobile terminal triggers the display on the vehicle terminal quantifies the situation that the user wants to use on the vehicle terminal, the first preset feature weight can be set to a high weight value, and the specific value can be set autonomously.

[0049] In determining the first times weight, there are various feasible value modes. The first times weight can be directly calculated according to the preset function relationship between the trigger times and the first times weight. For example, the trigger times and the first times weight can be set to be positively correlated. When an application is triggered 50 times, according to the function mapping rule, the corresponding first times weight is 5. Alternatively, the segmented intervals of the trigger times and the corresponding fixed weight values are defined in advance. When the trigger times fall into a certain interval, the preset weight of the interval is assigned. For example, the trigger times in 40 to 60 times (including the boundary value) are defined as interval R1, and the weight value of the interval is set to 4. If the trigger times of an application is 50 times, the first times weight is 4 because it falls into R1 interval.

[0050] The product of the first times weight and the first preset feature weight is calculated as the first recommended value of the application. The first preset feature weight can reflect the importance of the number of times that the application triggers the display on the vehicle terminal from the mobile terminal. The first preset feature weight can be set in advance based on expert experience, historical data or theoretical analysis. The product of the first times weight and the first preset feature weight can be regarded as a measure of the comprehensive importance of the number of times that the application triggers the display on the vehicle terminal from the mobile terminal, which considers both the theoretical importance of the trigger display times and the actual occurrence, and the finally calculated first recommended value is more reasonable and adapts to the actual use of the user.

[0051] In some embodiments, when the number of times that an application migrates from a mobile terminal to a vehicle terminal is greater than a second preset number of times, a second times weight of the application is determined; wherein the number of times that the application migrates from the mobile terminal to the vehicle terminal is proportional to the second times weight; the product of the second times weight and a second preset feature weight is calculated as a second recommended value of the application; wherein the second preset feature weight represents a predefined weight value of the second times weight, and the second preset feature weight is less than the first preset feature weight.

[0052] For the second preset feature weight, a weight is assigned to the condition when the number of times of migration of the application from the mobile terminal to the vehicle terminal is greater than the second preset number of times. That is, when the number of times of migration is less than or equal to the second preset number of times, the second preset feature weight is set to 0, and this item does not bring the corresponding second recommended value to the application. Since the frequency of the number of times of migration of the application is usually less than the frequency of triggering the display, and has the characteristic of being one-time, the second preset feature weight is assigned a value less than the first preset feature weight. For example, when the application satisfies this condition, the second preset feature weight is set to 7.

[0053] It can be understood that the number of times of migration of the application from the mobile terminal to the vehicle terminal can be counted by category, for example, the navigation / music / communication service application trigger frequency of the mobile terminal migrated to the vehicle terminal is counted. If the navigation service trigger frequency is the highest, it indicates that the user has a strong demand for real-time route planning and traffic information synchronization. If the music service trigger frequency is the second highest (such as high frequency of use during commuting period), the music recommendation algorithm can be optimized. If the navigation and music trigger frequencies are high during morning and evening peak periods, the application recommendation list of the commuting mode can be recommended, and if the navigation trigger frequency is high and accompanied by music and communication demand, the application recommendation list of the travel mode can be recommended, forming a personalized classified recommendation list.

[0054] For the second number of times weight, there are various feasible value modes. The second number of times weight can be directly calculated according to the preset function relationship between the trigger number of times and the second number of times weight. For example, the migration number of times and the second number of times weight can be set to be positively correlated, and when a type of application is migrated 50 times, according to the function mapping rule, the corresponding second number of times weight is 5. Alternatively, the segmented interval of the migration number of times and the corresponding fixed weight value are defined in advance, and when the trigger number of times falls into a certain interval, the preset weight of the interval is assigned. For example, the migration number of times in 40 to 60 times (including the boundary value) is defined as interval M1, and the weight value of the interval is set to 4. If a type of application is migrated 50 times, because it falls into M1 interval, the second number of times weight is set to 4.

[0055] The product of the second number of times weight and the second preset feature weight is calculated as the second recommended value of the application. The second preset feature weight can reflect the importance of the number of times of migration of the application from the mobile terminal to the vehicle terminal trigger, and this second preset feature weight can be set in advance based on expert experience, historical data or theoretical analysis. The product of the second number of times weight and the second preset feature weight can be regarded as a measure of the comprehensive importance of the number of times of migration of the application from the mobile terminal to the vehicle terminal, which considers both the theoretical importance of the migration trigger number of times and the actual migration situation, and finally the second recommended value calculated is more reasonable and more in line with the actual use of the user.

[0056] In some embodiments, when the application belongs to the application category installed on the car machine end, the category weight of the application is determined according to the category to which the application belongs; wherein the weight proportion of each category is predefined according to the application category of the car machine end to form the category weight; the product of the category weight and the third preset feature weight is calculated as the third recommendation value of the application; wherein the third preset feature weight represents the weight value of the predefined category weight, and the third preset feature weight is less than the second preset feature weight.

[0057] For the third preset feature weight, when the application belongs to the application category installed on the car machine end, the value of the third preset feature weight can be obtained for calculating the third recommendation value, and if the application does not belong to the application category, the third preset feature weight is 0, and the third recommendation value finally calculated is also 0, that is, the application lacks this part of the recommendation value. That is, if the application is not the category expected by the car machine end, the recommendation degree of this application will decrease. The third preset feature weight is less than the second preset feature weight, and the third preset feature weight can be valued at 4.

[0058] For the category weight, different category composition schemes can be used for assignment. For example, three driving scene adaptation categories are defined, and a basic score S is set for each category. B1 category is a core driving application, which is defined as an essential application that directly serves driving safety, navigation and core driving needs. For example, it is predetermined that the original car navigation, Gaode map / Baidu map car machine version, car Bluetooth phone, car radio and the like belong to the core driving application, and the category weight of these applications will be valued as the highest weight S1. B2 category is a high-frequency application, which is defined as an application that is not essential for driving, but can significantly improve the driving experience, and the interactive design has little effect on driving attention. For example, QQ music / Netease cloud music car machine version, Himalaya / get (audio content), Tencent along / vehicle WeChat (simplified version of communication), intelligent voice assistant, the category weight of these applications will be valued as a weight value S2 less than S1, B3 category is a scenario / tool type application, which is defined as an application that is very valuable in a specific scenario, but is not used every time, or belongs to a tool class, which needs to be parked or operated by the passenger. For example, parking lot search / parking fee App, vehicle state monitoring App, video App (only for parking state), restaurant reservation, weather App. The category weight of these applications will be valued as the minimum S3. The above-mentioned classification scheme and assignment scheme are examples, and the actual classification scheme and assignment scheme are not limited to the above-mentioned example scheme, and can be set independently.

[0059] The product of the category weight and the third preset feature weight is calculated to obtain the third recommendation value of the application. The category weight reflects the actual interest degree of the current user or user group in the category, or reflects the importance of the application on the car machine. The third preset feature weight is a pre-set fixed value or an adjustment range, and reflects the objective influence of the category on the recommendation. Therefore, the third recommendation value calculated finally respects the personal preferences of the user and meets the core needs of the scene, and the data has comprehensive characteristics.

[0060] In some embodiments, when the application has a score on the car machine, the ranking weight of the application is determined according to the score ranking of the application; wherein the ranking weight is proportional to the score ranking of the application on the car machine, and the higher the score ranking, the greater the value of the ranking weight; the product of the ranking weight and the fourth preset feature weight is calculated as the fourth recommendation value of the application; wherein the fourth preset feature weight represents the weight value of the predefined ranking weight, the fourth preset feature weight is less than the second preset feature weight, and the fourth preset feature weight is greater than the third preset feature weight.

[0061] For the ranking weight, the use characteristics of most users are considered, and high-score applications can be recommended in the case that the user does not have a specific user portrait. The value of the ranking weight can be considered in the following method: collecting big data to intelligently generate popular applications of the car machine, and when the application belongs to the top 5 popular applications of the car machine, the value is P1, and when the application belongs to the 6-10 popular applications of the car machine, the value is P2.

[0062] For the fourth preset feature weight, since it is desired that the final recommendation result can better fit the user's use habits, the fourth preset feature weight of this score is set to be less than the value of the user's actual use habits, for example, the fourth preset feature weight is set to 6.

[0063] The product of the ranking weight and the fourth preset feature weight is calculated as the fourth recommendation value of the application. The recommendation index of the application can be considered from the perspective of big data to provide a reference for the user. Or, in the case that the user does not have specific operations, the popular applications on the market can be used for initial recommendation to ensure that the user has a good use experience when using the application on the car machine for the first time.

[0064] In some embodiments, the sum of the recommendation values corresponding to the conditions that meet is calculated as the recommendation value of the application.

[0065] Understandably, only recommended values ​​corresponding to the conditions that are met can be used as the recommended values ​​for an application, ensuring that the results are both multi-dimensionally adaptable and consistent with user behavior characteristics and the characteristics of the in-vehicle infotainment system. For example, taking application A as an example, if application A simultaneously meets four conditions: the number of times application A is triggered from the mobile terminal to the in-vehicle infotainment system is greater than the first preset number, the number of times application A migrates from the mobile terminal to the in-vehicle infotainment system is greater than the second preset number, application A belongs to the category of applications already installed on the in-vehicle infotainment system, and application A has a rating on the in-vehicle infotainment system. If the weight of the first number is N1, the weight of the first preset feature is 8, the weight of the second number is N2, the weight of the first preset feature is 7, the category weight is S1, the weight of the third preset feature is 4, the ranking weight is P1, and the weight of the fourth preset feature is 6, then the formula for calculating the recommended value L1 of application A is: L1 = N1 × 8 + N2 × 7 + S1 × 4 + P1 × 6. Taking application B as an example, if application B is triggered from the mobile terminal to the vehicle's infotainment system more than the first preset number of times, and belongs to the application category already installed on the vehicle's infotainment system, then the recommended value L2 for application B is calculated as: L2 = N1 × 8 + S1 × 4. Taking application C as an example, if application C does not meet any of the four conditions, then application C's recommended value is 0, ranking last in the first recommended application list.

[0066] In S130, a second recommended application list is generated based on the application behavior spectrum of the mobile terminal, the set of applications that the mobile terminal supports running on the vehicle terminal, and the number of target recommended applications.

[0067] In some embodiments, a personalized application recommendation set is generated based on the application behavior spectrum of the mobile terminal. The number of applications in the personalized application recommendation set is not fixed, and some applications may not be supported for display on the in-vehicle infotainment system, thus requiring supplementation and filtering. Based on the personalized application recommendation set and the set of applications supported by the mobile terminal for operation on the in-vehicle infotainment system, overlapping applications are identified. A second recommended application list is generated based on the number of overlapping applications and the target recommended applications. Overlapping applications are those that are frequently used by users and can be displayed on the in-vehicle infotainment system; these applications should be included in the second recommended application list. However, since the number of such applications may be insufficient, in cases of insufficient applications, the second recommended application list can be supplemented sequentially from the remaining applications in the set of applications supported by the mobile terminal for operation on the in-vehicle infotainment system that do not overlap with the personalized application recommendation set.

[0068] For example, the expected number of recommended applications is S, and the set of applications P that support operation on the vehicle's infotainment system from the mobile terminal is P. 02 Find personalized app recommendation set P 01 For the applications that appear in the list, generate a second recommended application list P. If the number of applications in P is less than S, then select the application from P. 02 Selected by popular applications, excluding those included in P01 The number of applications inside meets the recommendation number.

[0069] And if the car end data is insufficient, for example, according to the interaction data between the mobile terminal and the car end and the application behavior data of the car end, it is difficult to generate a first recommended application list with a proper number, then directly use the second recommended application list as the recommended application data that the car needs to display.

[0070] In S140, according to the first recommended application list, the second recommended application list and the target recommended application number, a fusion recommended application list is generated.

[0071] If the car end data is sufficient, the recommendation value of each application is calculated, and the first recommended application list is sorted from large to small according to the recommendation value. The first recommended application list and the second recommended application list are fused, and the target recommended application number of applications is selected from them to generate a fusion recommended application list. The fusion of the two recommended application lists makes up for the defects of a single strategy, takes the advantages and makes the results both personalized and robust. A single list may focus on a certain dimension, resulting in a narrow recommendation range. Fusion of multiple lists from different sources can cover a wider range of candidate items, avoid information cocooning, and provide users with more diverse options. When the data of a certain recommended application list is insufficient, other application lists can also be used to make up for it, avoiding interruption or quality drop in recommendation.

[0072] As one possible fusion method, when there are duplicate applications in the first recommended application list and the second recommended application list, the duplicate applications are weighted and sorted; according to the weighted order and the target recommended application number, a fusion recommended application list is generated.

[0073] For example, it is desired to generate 5 recommended applications. The application list returned from the mobile terminal supporting the car end running application set P 02 has 1 Baidu Map, 2 Gaode Map, 3 Douyin, 4 Bilibili, 5 QQ Music, 6 Weibo, 7 Kuaishou, 8 Youku, 9 Today's Headlines, 10 iQiyi, etc. The personalized application recommendation set P 01 has 3 applications, which are Douyin, Gaode Map and Youku, which do not meet the requirement of 5 recommended applications. Baidu Map and Bilibili are selected from P 02 to form a second recommended application list P.

[0074] Next, the recommendation value of each application in P 02 is calculated to obtain a first recommended application list P c for QQ Music (164 points), Douyin (146 points), Weibo (138 points), Gaode Map (122 points), Bilibili (112 points), Baidu Map (107 points), etc.

[0075] Finally, the first recommended application list P c and the second recommended application list P are data fused and sorted: P: Douyin, Gaode Map, Youku Video, Baidu Map, Bilibili; P c : QQ Music, Douyin, Weibo, Gaode Map, Bilibili, Baidu Map… The fusion recommended application list P t = (P+ P c ), and the top 5 applications are taken, and the final output fusion recommended application list P t result is: QQ Music, Douyin, Weibo, Gaode Map, Bilibili.

[0076] In addition, when the first recommended application list and the second recommended application list are fused, each recommended list can be weighted to adjust the sorting result according to the user's expectations or actual needs. For example, the repeated application is promoted in weight when fused, so that it can be arranged in front of other non-repeated applications, because the repeated application not only meets the user's usage habits, but also adapts to the vehicle terminal usage scenario, and promoting its recommended position can better meet the user's usage needs. It can be understood that the fusion method can be other list fusion methods in addition to the above direct addition fusion.

[0077] In some embodiments, after generating the fusion recommended application list, it can be stored in the vehicle terminal locally, bound to the vehicle owner's account, and uploaded to the cloud backup.

[0078] Figure 2 is a structural schematic diagram of the device for generating a recommended application list provided by an exemplary embodiment of the present application, as Figure 2 shown, the device for generating a recommended application list 2 comprises: an acquisition module 21 for acquiring mobile terminal application data, vehicle terminal application data and target recommended application quantity; wherein the mobile terminal application data comprises an application behavior spectrum of a mobile terminal and an application set supported by the mobile terminal for running on a vehicle terminal, the vehicle terminal application data comprises interaction data between the mobile terminal and the vehicle terminal and application behavior data of the vehicle terminal; a first generation module 22 for generating a first recommended application list according to the interaction data between the mobile terminal and the vehicle terminal and the application behavior data of the vehicle terminal; a second generation module 23 for generating a second recommended application list according to the application behavior spectrum of the mobile terminal, the application set supported by the mobile terminal for running on the vehicle terminal and the target recommended application quantity; and a third generation module 24 for generating a fusion recommended application list according to the first recommended application list, the second recommended application list and the target recommended application quantity.

[0079] As a possible implementation manner, the interaction data between the mobile terminal and the car terminal includes: the number of times of triggering the application from the mobile terminal to the display of the car terminal and the number of times of migrating the application from the mobile terminal to the car terminal; the application behavior data of the car terminal includes: the category to which the application belongs on the car terminal and the score ranking of the application on the car terminal; wherein, the first generation module 22 can be configured to: for the interaction data between the mobile terminal and the car terminal and the application behavior data of the car terminal, when any one of the following four conditions meets, calculate the recommended value of the application according to the data meeting the condition and the corresponding weight; wherein, the four conditions include: the number of times of triggering the application from the mobile terminal to the display of the car terminal is greater than the first preset number of times, the number of times of migrating the application from the mobile terminal to the car terminal is greater than the second preset number of times, the application belongs to the application category already installed on the car terminal, and the application has a score on the car terminal; or, when any one of the four conditions does not meet the preset requirement, set the recommended value of the application to 0; rank based on the recommended value of each application to generate a first recommended application list.

[0080] As a possible implementation manner, the first generation module 22 can be configured to: when the number of times of triggering the application from the mobile terminal to the display of the car terminal is greater than the first preset number of times, determine the first number of times weight of the application according to the number of times of triggering the application from the mobile terminal to the display of the car terminal; wherein, the number of times of triggering the application from the mobile terminal to the display of the car terminal is proportional to the first number of times weight; calculate the product of the first number of times weight and the first preset feature weight as the first recommended value of the application; wherein, the first preset feature weight represents the weight value of the predefined first number of times weight.

[0081] As a possible implementation manner, the first generation module 22 can be configured to: when the number of times of migrating the application from the mobile terminal to the car terminal is greater than the second preset number of times, determine the second number of times weight of the application; wherein, the number of times of migrating the application from the mobile terminal to the car terminal is proportional to the second number of times weight; calculate the product of the second number of times weight and the second preset feature weight as the second recommended value of the application; wherein, the second preset feature weight represents the weight value of the predefined second number of times weight, and the second preset feature weight is less than the first preset feature weight.

[0082] As a possible implementation manner, the first generation module 22 can be configured to: when the application belongs to the application category already installed on the car terminal, determine the category weight of the application according to the category to which the application belongs; wherein, the weight proportion of each category is predefined according to the application category of the car terminal to form the category weight; calculate the product of the category weight and the third preset feature weight as the third recommended value of the application; wherein, the third preset feature weight represents the weight value of the predefined category weight, and the third preset feature weight is less than the second preset feature weight.

[0083] As a possible implementation manner, the first generation module 22 can be configured to: when the score of the application exists on the vehicle terminal side, determine a ranking weight of the application according to a score ranking of the application; wherein the ranking weight is proportional to the score ranking of the application on the vehicle terminal side, and the higher the score ranking, the greater the value of the ranking weight; and calculate a product of the ranking weight and a fourth preset feature weight as the fourth recommendation value of the application; wherein the fourth preset feature weight represents a weight value of the predefined ranking weight, the fourth preset feature weight is smaller than the second preset feature weight, and the fourth preset feature weight is greater than the third preset feature weight.

[0084] As a possible implementation manner, the first generation module 22 can be configured to: calculate a sum of the recommendation values corresponding to the conditions that are met as the recommendation value of the application.

[0085] As a possible implementation manner, the third generation module 24 can be configured to: when there are repeated applications in the first recommended application list and the second recommended application list, perform weighted sorting on the repeated applications; and generate a fusion recommended application list according to the order after the weighted sorting and the target number of recommended applications.

[0086] As a possible implementation manner, the second generation module 23 can be configured to: generate a personalized application recommendation set according to the application behavior spectrum of the mobile terminal; determine the overlapping applications according to the personalized application recommendation set and the application set supported by the mobile terminal to run on the vehicle terminal side; and generate a second recommended application list according to the overlapping applications and the target number of recommended applications.

[0087] In some embodiments, a vehicle is installed with a vehicle interactive system, and a mobile terminal is taken as a mobile phone terminal. A mobile phone interconnection application program supporting interconnection functions such as HiCar, ICCOA, and Honor Carlink is installed in the vehicle system. A terminal such as a mobile phone and a vehicle establishes a connection through interconnection products such as HiCar, ICCOA, and Honor Carlink. On the vehicle screen, the application ecology of the mobile phone and the system functions of the vehicle can be seamlessly integrated to form a unified and coherent interactive interface, forming a fusion desktop. The device for generating a recommended application list is used to execute the method for generating a recommended application list proposed in the embodiments of the present application, that is, a fusion recommended application list can be generated according to the application data of the mobile phone terminal and the vehicle terminal, and displayed on the fusion desktop and the recommendation entry carrier of other interconnection APP of the vehicle system. It can be understood that the mobile terminal can be a mobile device such as a tablet computer in addition to a mobile phone terminal.

[0088] An electronic device, the electronic device comprising: a processor; a memory for storing processor-executable instructions; and the processor is configured to execute the method for generating a recommended application list proposed in the embodiments of the present application.

[0089] Below, an electronic device according to embodiments of the present application will be described with reference to Figure 3 The electronic device can be either one or both of the first and second devices, or a stand-alone device independent of them, which can communicate with the first and second devices to receive the acquired input signals therefrom.

[0090] Figure 3 A block diagram of an electronic device according to embodiments of the present application is illustrated.

[0091] As Figure 3 shown, the electronic device 30 includes one or more processors 31 and a memory 32.

[0092] The processor 31 can be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction executing capabilities, and can control other components in the electronic device 30 to perform desired functions.

[0093] The memory 32 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, which the processor 31 can execute to implement the above-described method of generating a recommended application list according to embodiments of the present application and / or other desired functions. Various contents such as input signals, signal components, noise components, and the like can also be stored in the computer-readable storage media.

[0094] In one example, the electronic device 30 can further include an input device 33 and an output device 34, which are interconnected through a bus system and / or other form of connection mechanism (not shown).

[0095] When the electronic device is a stand-alone device, the input device 33 can be a communication network connector for receiving the acquired input signals from the first and second devices.

[0096] In addition, the input device 33 can further include, for example, a keyboard, a mouse, and the like.

[0097] The output device 34 can output various information including the determined distance information, direction information, and the like, to the outside. The output device 34 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0098] Of course, for simplicity, Figure 3 Only some of the components of the electronic device 30 related to the present application are shown in the figure, and components such as buses, input / output interfaces, and the like are omitted. In addition to these, the electronic device 30 can include any other appropriate components according to the specific application.

[0099] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's device and partly on a remote computing device or entirely on the remote cloud device or server.

[0100] A computer readable storage medium storing a computer program for performing the method of generating a recommended application list according to the embodiments of the present application.

[0101] The computer readable storage medium can be any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0102] The above description is given for illustrative and descriptive purposes. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain modifications, permutations, additions, and sub-combinations thereof.

Claims

1. A method for generating a list of recommended applications, characterized in that, include: The system acquires mobile terminal application data, vehicle-mounted application data, and the number of target recommended applications. The mobile terminal application data includes the application behavior spectrum of the mobile terminal and the set of applications that the mobile terminal supports running on the vehicle-mounted system. The vehicle-mounted application data includes the interaction data between the mobile terminal and the vehicle-mounted system, as well as the application behavior data of the vehicle-mounted system. A first recommended application list is generated based on the interaction data between the mobile terminal and the vehicle terminal and the application behavior data of the vehicle terminal. A second recommended application list is generated based on the application behavior spectrum of the mobile terminal, the set of applications that the mobile terminal supports running on the vehicle terminal, and the number of target recommended applications. A fusion recommended application list is generated based on the first recommended application list, the second recommended application list, and the target number of recommended applications.

2. The method for generating a recommended application list according to claim 1, characterized in that, The interaction data between the mobile terminal and the vehicle terminal includes: the number of times the application is triggered from the mobile terminal and displayed on the vehicle terminal, and the number of times the application migrates from the mobile terminal to the vehicle terminal; the application behavior data on the vehicle terminal includes: the category to which the application belongs on the vehicle terminal and the rating and ranking of the application on the vehicle terminal. The step of generating a first recommended application list based on the interaction data between the mobile terminal and the vehicle-mounted system, as well as the application behavior data of the vehicle-mounted system, includes: For the interaction data between the mobile terminal and the in-vehicle infotainment system, and the application behavior data of the in-vehicle infotainment system, when any one of the following four conditions is met, the recommended application value is calculated based on the data that meets the condition and the corresponding weight; wherein the four conditions include: The number of times the application is triggered from the mobile terminal to be displayed on the vehicle terminal is greater than the first preset number; the number of times the application migrates from the mobile terminal to the vehicle terminal is greater than the second preset number; the application belongs to the application category that has been installed on the vehicle terminal; and the application has a rating on the vehicle terminal. Alternatively, if none of the four conditions meet the preset requirements, the recommended value for the application will be set to 0. Each app is ranked based on its recommendation score, generating a list of top recommended apps.

3. The method for generating a recommended application list according to claim 2, characterized in that, When any one of the following four conditions is met, the recommended value for the application is calculated based on the data meeting the condition and the corresponding weight, including: When the number of times the application is triggered from the mobile terminal to the vehicle display exceeds the first preset number, the first number of times the application is triggered from the mobile terminal to the vehicle display is determined; wherein, the number of times the application is triggered from the mobile terminal to the vehicle display is proportional to the first number of times the application is triggered from the mobile terminal to the vehicle display. Calculate the product of the first number weight and the first preset feature weight as the first recommended value for the application; wherein, the first preset feature weight represents the predefined weight value of the first number weight.

4. The method for generating a recommended application list according to claim 2, characterized in that, When any one of the following four conditions is met, the recommended value for the application is calculated based on the data meeting the condition and the corresponding weight, including: When the number of times an application migrates from a mobile terminal to an in-vehicle system exceeds a second preset number, a second number weight is determined for the application; wherein, the number of times an application migrates from a mobile terminal to an in-vehicle system is proportional to the second number weight. Calculate the product of the second number weight and the second preset feature weight as the second recommended value for the application; wherein, the second preset feature weight represents the predefined weight value of the second number weight, and the second preset feature weight is less than the first preset feature weight.

5. The method for generating a recommended application list according to claim 2, characterized in that, When any one of the following four conditions is met, the recommended value for the application is calculated based on the data meeting the condition and the corresponding weight, including: When an application belongs to the category of applications already installed on the vehicle's infotainment system, the category weight of the application is determined based on the category to which the application belongs; wherein, the category weight is formed by predefined weight proportions for each category based on the application categories on the vehicle's infotainment system. Calculate the product of the category weight and the third preset feature weight as the third recommended value for the application; wherein, the third preset feature weight represents the predefined weight value of the category weight, and the third preset feature weight is less than the second preset feature weight.

6. The method for generating a recommended application list according to claim 2, characterized in that, When any one of the following four conditions is met, the recommended value for the application is calculated based on the data meeting the condition and the corresponding weight, including: When an application has a rating on the vehicle's infotainment system, the application's ranking weight is determined based on the application's rating ranking. The ranking weight is directly proportional to the application's rating ranking on the vehicle's infotainment system; the higher the rating ranking, the greater the ranking weight. Calculate the product of the ranking weight and the fourth preset feature weight as the fourth recommendation value of the application; wherein, the fourth preset feature weight represents the predefined weight value of the ranking weight, the fourth preset feature weight is less than the second preset feature weight, and the fourth preset feature weight is greater than the third preset feature weight.

7. The method for generating a recommended application list according to claim 2, characterized in that, When any one of the following four conditions is met, the recommended value for the application is calculated based on the data meeting the condition and the corresponding weight, including: Calculate the sum of the recommended values ​​corresponding to the conditions that are met, and use this sum as the recommended value for the application.

8. The method for generating a recommended application list according to claim 1, characterized in that, The step of generating a fused recommended application list based on the first recommended application list, the second recommended application list, and the target number of recommended applications includes: When there are duplicate applications in the first recommended application list and the second recommended application list, the duplicate applications are sorted by weight; A list of fused recommended applications is generated based on the weighted sorting order and the number of target recommended applications.

9. The method for generating a recommended application list according to claim 1, characterized in that, Based on the application behavior spectrum of the mobile terminal, the set of applications supported by the mobile terminal for operation on the vehicle-mounted system, and the number of target recommended applications, a second recommended application list is generated, including: Based on the application behavior spectrum of the mobile terminal, a personalized application recommendation set is generated; Based on the personalized application recommendation set and the application set that the mobile terminal supports running on the vehicle's infotainment system, overlapping applications are identified. A second list of recommended applications is generated based on the number of overlapping applications and the target recommended applications.

10. A vehicle, characterized in that, include: The in-vehicle interactive system refers to the vehicle-mounted terminal, which is communicatively connected to a mobile terminal. An apparatus for generating a list of recommended applications, the apparatus for generating a list of recommended applications being used to perform the method for generating a list of recommended applications as described in any one of claims 1-9, the apparatus for generating a list of recommended applications being communicatively connected to the in-vehicle interactive system and the mobile terminal.

Images