Application recommendation method and device, computer device, and storage medium

Abstract

The application discloses an application recommendation method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a driving factor, a target use frequency and a total use frequency of a plurality of first car machine applications; determining a real score value of each first car machine application of a target user based on the driving factor, the total use frequency and the target use frequency; determining a predicted score value of each second car machine application of the target user based on the real score value of each first car machine application of the target user and a similarity between each second car machine application and each first car machine application; and recommending a second car machine application to a client corresponding to the target user based on a driving stage corresponding to the target user and the predicted score value. The second car machine application that has not been used by the user is recommended in a targeted manner based on the driving stage of the target user and the real score of the first car machine application, so that the recommended car machine application is more in line with the use habit of the user.

Description

Technical Field

[0001] This application relates to the field of vehicle infotainment system technology, and more specifically, to an application recommendation method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the advancement of automotive intelligence and connectivity, the layout of the vehicle's Human Machine Interface (HMI) has become a crucial component of the user's driving experience. Typically, computer devices acquire data such as page browsing and button click events from the vehicle's HMI to analyze product usage and user needs, driving product optimization or guiding operations. However, when using this data to recommend in-vehicle applications, related technologies may not fully meet users' specific needs. Summary of the Invention

[0003] In view of the above problems, this application proposes an application recommendation method, apparatus, computer equipment, and storage medium to achieve targeted recommendation of in-vehicle applications based on the driving stage of the target user.

[0004] In a first aspect, embodiments of this application provide an application recommendation method, the method comprising: obtaining a driving factor for each of a plurality of first in-vehicle infotainment applications, a total number of uses of the plurality of first in-vehicle infotainment applications, and a target number of uses for each first in-vehicle infotainment application; the first in-vehicle infotainment applications are in-vehicle infotainment applications used by a target user, and the driving factor is used to characterize whether the driving stage corresponding to the in-vehicle infotainment application is a novice stage or an experienced stage; determining the target user's true rating value for each of the first in-vehicle infotainment applications based on the driving factor, the total number of uses, and the target number of uses, wherein the positive or negative value of the true rating value representing the novice stage is opposite to the positive or negative value of the true rating value representing the experienced stage; determining the target user's predicted rating value for each of the second in-vehicle infotainment applications based on the target user's true rating value for each of the first in-vehicle infotainment applications and the similarity between each second in-vehicle infotainment application and each of the first in-vehicle infotainment applications, wherein the second in-vehicle infotainment applications are in-vehicle infotainment applications not used by the target user; and recommending the second in-vehicle infotainment applications to the client corresponding to the target user based on the driving stage corresponding to the target user and the predicted rating value.

[0005] Secondly, embodiments of this application provide an application recommendation device, comprising: a data acquisition module, a rating determination module, a score prediction module, and an application recommendation module. The data acquisition module acquires the driving factor of each of a plurality of first in-vehicle applications, the total number of uses of the plurality of first in-vehicle applications, and the target number of uses for each first in-vehicle application. The first in-vehicle applications are those used by the target user. The driving factor characterizes whether the driving stage corresponding to the in-vehicle application is a novice or experienced driver. The rating determination module determines the target user's preference for each application based on the driving factor, the total number of uses, and the target number of uses. The first in-vehicle infotainment application's actual rating value, wherein the driving factor represents the positive or negative value of the actual rating value during the novice stage, and the driving factor represents the opposite positive or negative value of the actual rating value during the experienced stage; the score prediction module is used to determine the target user's predicted rating value for each second in-vehicle infotainment application based on the target user's actual rating value for each of the first in-vehicle infotainment applications, and the similarity between each second in-vehicle infotainment application and each of the first in-vehicle infotainment applications, wherein the second in-vehicle infotainment applications are those that the target user has not used; the application recommendation module is used to recommend the second in-vehicle infotainment applications to the client corresponding to the target user based on the target user's corresponding driving stage and the predicted rating value.

[0006] Thirdly, embodiments of this application provide a computer device, including: 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 one or more processors, and the one or more application programs are configured to perform the application recommendation method provided in the first aspect above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which can be invoked by a processor to execute the application recommendation method provided in the first aspect above.

[0008] The solution provided in this application obtains the driving factor, target usage count, and total usage count of each first in-vehicle infotainment application; based on the driving factor, total usage count, and target usage count, it determines the target user's actual rating for each first in-vehicle infotainment application; based on the target user's actual rating for each first in-vehicle infotainment application and the similarity between each second in-vehicle infotainment application and each first in-vehicle infotainment application, it determines the target user's predicted rating for each second in-vehicle infotainment application; and based on the target user's driving stage and predicted rating, it recommends second in-vehicle infotainment applications to the target user's corresponding client. Thus, by using the target user's driving stage and the actual rating of the first in-vehicle infotainment applications, it selectively recommends second in-vehicle infotainment applications that the user has not used, thereby making the recommended in-vehicle infotainment applications more in line with the user's usage habits. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 The diagram illustrates an application scenario of the application recommendation method provided in this embodiment.

[0011] Figure 2 A flowchart illustrating an application recommendation method provided in one embodiment of this application is shown.

[0012] Figure 3 A flowchart illustrating an application recommendation method provided in another embodiment of this application is shown.

[0013] Figure 4 A schematic diagram of the specific process of step S201 in another embodiment of this application is shown.

[0014] Figure 5 A schematic diagram of the specific process of step S205 in another embodiment of this application is shown.

[0015] Figure 6 A structural block diagram of the application recommendation device provided in an embodiment of this application is shown.

[0016] Figure 7 A structural block diagram of a computer device provided in an embodiment of this application is shown.

[0017] Figure 8 A structural block diagram of a computer-readable storage medium provided in an embodiment of this application is shown. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0019] The inventors have proposed an application recommendation method, apparatus, computer device, and storage medium as provided in the embodiments of this application. By analyzing the target user's driving stage and their actual ratings of all previously used in-vehicle applications, the method recommends in-vehicle applications that the target user has not yet used, thereby matching the recommended applications with the target user's usage habits. The specific application recommendation method will be described in detail in subsequent embodiments.

[0020] The following describes the application scenarios of the application recommendation method provided in the embodiments of this application.

[0021] Please see Figure 1 The application recommendation method provided in this application embodiment is applied to a computer device 300, which can be a physical server, cloud server, etc. The computer device 300 can connect to multiple vehicles 100 to obtain the data points of the multiple vehicles 100. Each vehicle 100 can send relevant data points to the computer device 300 once each time a preset event occurs. Specifically, the preset events can include application startup events, application duration events, page opening events, page duration events, and button click events. When any of the above five types of events occurs in its vehicle terminal, the vehicle 100 can obtain the current general information and additional information, and send it to the computer device 300 as the data points of the vehicle 100. The general information for vehicle 100 includes vehicle ID, data collection time, network IP address or GPS location, event type, event ID, network environment, system version, and device model. Additional information for vehicle 100 may include the vehicle's gear position at the time of data collection, mileage, page source, and current page. The page source data is only obtained when a page is opened, and the current page data is only obtained when a button is clicked. Computer device 300 can analyze the received data from each vehicle 100 to determine each user's driving stage and usage habits, and then recommend in-vehicle applications accordingly.

[0022] The application recommendation methods provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0023] Please see Figure 2 , Figure 2 This paper illustrates a flowchart of an application recommendation method provided in one embodiment of this application. The following will focus on... Figure 2 The process shown will be described in detail. The application recommendation method may specifically include the following steps:

[0024] Step S110: Obtain the driving factor of each of the multiple first vehicle infotainment applications, the total number of times the multiple first vehicle infotainment applications are used, and the target number of times each first vehicle infotainment application is used. The first vehicle infotainment application is the vehicle infotainment application used by the target user. The driving factor is used to characterize whether the driving stage corresponding to the vehicle infotainment application is the novice stage or the experienced stage.

[0025] In this embodiment, the computer device can determine the target user's usage habits based on their usage of all in-vehicle applications they have used. This information is then used to recommend some in-vehicle applications that the target user might be interested in from among all the in-vehicle applications they haven't used. Therefore, the computer device can obtain the driving factor, total usage count, and target usage count corresponding to each in-vehicle application to determine the target user's predicted rating for unused in-vehicle applications, and then recommend in-vehicle applications to the target user in a targeted manner. Specifically, the computer device can use in-vehicle applications used by the target user as first in-vehicle applications. Each first in-vehicle application corresponds to a driving factor, representing whether the driving stage corresponding to the first in-vehicle application is the novice stage or the experienced stage. In other words, it represents whether the first in-vehicle application is frequently used by the target user during the novice stage or is more frequently used by the target user during the experienced stage. The total usage count obtained by the computer device refers to the sum of the usage counts of each of the multiple first in-vehicle applications, and the target usage count refers to the target usage count for each first in-vehicle application.

[0026] In some implementations, the target usage count for each first in-vehicle infotainment application can be the number of valid uses of the application by the target user. That is, all usage counts by the target user include a portion of invalid uses and a portion of valid uses. Therefore, the computing device can determine the number of valid uses of the application by the target user based on the event tracking data obtained from the vehicle, and use this as the target usage count. Understandably, the event tracking data obtained by the computer device is triggered by five types of events: application launch events, application duration events, page open events, page duration events, and button click events. In other words, once any one of these five types of events occurs in the vehicle's in-vehicle terminal, the computer device will receive relevant event tracking data. However, obviously, not every trigger of any of these events constitutes a valid operation by the target user on the first in-vehicle infotainment application.

[0027] Specifically, the computer device can determine whether a target user's operation on the first in-vehicle infotainment application is valid based on page open events and button click events: if the target user enters the first in-vehicle infotainment application and opens a page, or enters the first in-vehicle infotainment application and clicks a button, then the computer device can consider this operation by the target user as a valid operation; otherwise, if the target user merely closes the page, closes the application, or opens the application without performing any operation, then the computer device will not consider these operations as valid operations. The computer device can analyze the user path based on the page source data uploaded when the page open event is triggered, and the current page data uploaded when the button click event is triggered, thereby determining whether the current operation is valid.

[0028] In some implementations, the computer device determines the total number of times a target user uses multiple first in-vehicle applications and the target number of times each in-vehicle application is used, based on the data uploaded by the vehicle. This calculation can be performed in units of a preset time length. For example, the preset time length is one month, meaning the computer device can obtain the total number of uses and the target number of uses once a month. Within this preset time length, the computer device can receive data uploaded by the vehicle at any time when it triggers corresponding events, but the computer device will only update the total number of uses and the target number of uses once every preset time interval. Therefore, the application recommendations for the target user based on the total number of uses and the target number of uses will also be updated accordingly every preset time interval.

[0029] Step S120: Based on the driving factor, the total number of uses, and the target number of uses, determine the target user's true rating value for each of the first vehicle-mounted applications. The driving factor represents the positive or negative value of the true rating value during the novice stage, which is opposite to the positive or negative value of the true rating value during the experienced stage.

[0030] In this embodiment, the computer device determines the true rating value of the first in-vehicle application based on the total number of uses and the target number of uses. This rating value can represent the frequency of use of the first in-vehicle application by the target user. Simultaneously, the computer device also determines the true rating value of the first in-vehicle application based on a driving factor. Since the driving factor represents whether the in-vehicle application corresponds to a novice or experienced driving stage, the computer device uses the driving factor to associate the true rating value of the first in-vehicle application with the target user's driving stage. Specifically, the computer device can set the sign of the true rating value of the first in-vehicle application to correspond the true rating value with the novice or experienced driving stage represented by the driving factor. Based on a predetermined correspondence, the computer device can determine whether the first in-vehicle application is used by the target user in the novice stage or the experienced driving stage based on whether the true rating value is positive or negative. In other words, the meaning of the driving stage represented by a positive true rating value is the opposite of the meaning of the driving stage represented by a negative true rating value.

[0031] Step S130: Based on the target user's actual rating for each first vehicle infotainment application and the similarity between each second vehicle infotainment application and each first vehicle infotainment application, determine the target user's predicted rating for each second vehicle infotainment application, wherein the second vehicle infotainment application is a vehicle infotainment application that the target user has not used.

[0032] In this embodiment, after determining the target user's actual ratings for multiple first in-vehicle infotainment applications, the computer device can determine the target user's predicted ratings for all second in-vehicle infotainment applications based on the target user's actual ratings and the similarity between the various in-vehicle infotainment applications. Understandably, the target user's actual rating for each first in-vehicle infotainment application not only represents the frequency of the target user's use of the first in-vehicle infotainment application, but also represents whether the first in-vehicle infotainment application belongs to the target user at the novice or experienced stage. Furthermore, a positive or negative actual rating corresponds to the novice or experienced stage of the first in-vehicle infotainment application. Therefore, the predicted ratings for the second in-vehicle infotainment applications determined by the computer device based on the actual ratings of the first in-vehicle infotainment applications can also correspondingly predict whether the driving stage corresponding to the second in-vehicle infotainment application is the novice or experienced stage, and a positive or negative predicted rating also corresponds to the novice or experienced stage of the second in-vehicle infotainment application.

[0033] In some implementations, the computer device obtains the similarity between each second in-vehicle application and each first in-vehicle application. This can be calculated based on the cosine similarity method. The target user's actual ratings of the two compared in-vehicle applications are used as vectors for those applications. The angle between the two vectors is calculated; the smaller the angle, the greater the cosine similarity, indicating that the two in-vehicle applications are more similar. Alternatively, the computer device can also calculate the similarity between two in-vehicle applications using the Pearson correlation coefficient. The method by which the computer device determines the similarity between each second and first in-vehicle application is not limited here.

[0034] Step S140: Based on the driving stage corresponding to the target user and the predicted score, recommend the second vehicle-mounted application to the client corresponding to the target user.

[0035] In this embodiment, the predicted rating value for each second in-vehicle application determined by the computer device can, to some extent, characterize the frequency with which the second in-vehicle application might be used if the target user were to use it. Since the predicted rating value is based on the actual rating value, as the above analysis shows, the predicted rating value can also be positive or negative, corresponding to whether the driving stage corresponding to the second in-vehicle application is the novice or experienced driving stage. The larger the absolute value of the predicted rating value for the second in-vehicle application, the greater the probability that the target user will use the second in-vehicle application at the corresponding driving stage. Therefore, the computer device can determine the second in-vehicle application recommended to the client corresponding to the target user based on the predicted rating value for each second in-vehicle application. Specifically, the computer can determine a subset of in-vehicle applications suitable for the target user's current driving stage based on the target user's driving stage. That is, it selects second in-vehicle applications that match the target user's driving stage from all second in-vehicle applications. Then, based on the absolute value of the predicted rating value for each in-vehicle application in the selected subset of second in-vehicle applications, it determines the second in-vehicle application recommended to the client corresponding to the target user.

[0036] The application recommendation method provided in this application embodiment obtains the driving factors, target usage counts, and total usage counts of multiple first vehicle-mounted applications; based on the driving factors, total usage counts, and target usage counts, it determines the target user's actual rating for each first vehicle-mounted application; based on the target user's actual rating for each first vehicle-mounted application and the similarity between each second vehicle-mounted application and each first vehicle-mounted application, it determines the target user's predicted rating for each second vehicle-mounted application; and based on the target user's corresponding driving stage and predicted rating, it recommends second vehicle-mounted applications to the target user's corresponding client. Thus, by using the target user's driving stage and the actual ratings of the first vehicle-mounted applications, it selectively recommends unused second vehicle-mounted applications, thereby making the recommended applications more in line with the user's usage habits.

[0037] Please see Figure 3 , Figure 3 This paper illustrates a flowchart of an application recommendation method provided in another embodiment of this application. The following will focus on... Figure 3 The process shown will be described in detail. The application recommendation method may specifically include the following steps:

[0038] Step S201: Obtain the driving factor of each of the multiple first vehicle infotainment applications, the total number of times the multiple first vehicle infotainment applications are used, and the target number of times each first vehicle infotainment application is used. The first vehicle infotainment application is the vehicle infotainment application used by the target user. The driving factor is used to characterize whether the driving stage corresponding to the vehicle infotainment application is the novice stage or the experienced stage.

[0039] In this embodiment, step S210 can be referred to the content of other embodiments, and will not be repeated here.

[0040] In some implementations, such as Figure 4 As shown, the method for obtaining the driving factor of each of the multiple first vehicle-mounted applications in step S201 may include the following steps:

[0041] Step S2011: Obtain the first number of times the target vehicle infotainment application is used in the novice stage and the second number of times it is used in the experienced stage, wherein the target vehicle infotainment application is any one of the plurality of first vehicle infotainment applications.

[0042] In this embodiment, the computer device can determine whether a target vehicle infotainment application is more frequently used when the user is a novice or an experienced driver by measuring the number of times the application is used in the first stage (novice phase) and the number of times it is used in the second stage (experienced driver phase). Based on these different usage counts, the computer device can assign different driving factors to the target application. The actual rating value of the target application, determined by these different driving factors, can then characterize whether the target application corresponds to the novice or experienced driver stage. Clearly, a higher number of first-time uses of the target application in the novice phase indicates that the application is more suitable for novice users; similarly, a higher number of second-time uses in the experienced driver phase indicates that the application is more suitable for experienced users. Therefore, the computer device can obtain the number of first-time uses and the number of second-time uses of the target application in the novice and experienced driver phases to determine different driving factors based on these two counts.

[0043] The target in-vehicle application refers to any one of the multiple first in-vehicle applications that the target user has already used. In other words, only the first in-vehicle applications that have been used will correspond to a driving factor. Obviously, for any second in-vehicle application that the target user has not used, the computer device cannot obtain the number of times the target user has used that second in-vehicle application, and therefore cannot obtain its corresponding driving factor.

[0044] Step S2012: If the first number of uses is greater than or equal to the second number of uses, then the driving factor of the target vehicle application is determined to be the first driving factor, and the first driving factor is used to characterize the driving stage corresponding to the target vehicle application as the novice stage.

[0045] In this embodiment of the application, if the first number of uses is greater than or equal to the second number of uses, that is, the number of times the target vehicle application is used in the novice stage is greater than or equal to the number of times it is used in the experienced stage, the computer device can determine that the target vehicle application is used more frequently in the novice stage. Therefore, the driving factor corresponding to the target vehicle application can be set as the first driving factor to characterize the driving stage corresponding to the target vehicle application as the novice stage.

[0046] Step S2013: If the first number of uses is less than the second number of uses, then the driving factor of the target vehicle application is determined to be the second driving factor, and the second driving factor is used to characterize the driving stage corresponding to the target vehicle application as the experienced driver stage.

[0047] In this embodiment of the application, if the first number of uses is less than the second number of uses, that is, the number of times the target vehicle application is used in the novice stage is less than the number of times it is used in the experienced stage, the computer device can determine that the target vehicle application is used more frequently in the experienced stage. Therefore, the driving factor corresponding to the target vehicle application can be set as the first driving factor so that the driving stage corresponding to the target vehicle application is the experienced stage.

[0048] Obviously, the first driving factor should be significantly different from the second driving factor, so that after obtaining the real score value corresponding to the first vehicle-mounted application based on the driving factor, the computer device can also directly determine the driving stage corresponding to the first vehicle-mounted application based on the real score value.

[0049] Step S202: Obtain the ratio of the target number of times each first vehicle-mounted application is used to the total number of times it is used, and obtain the effective usage ratio of each first vehicle-mounted application.

[0050] In this embodiment, the computer device determines the true rating value corresponding to the first in-vehicle infotainment application by accurately and intuitively reflecting the frequency of the target user's use of the first in-vehicle infotainment application. Therefore, the computer device can use the ratio of the target usage frequency of each first in-vehicle infotainment application to the total usage frequency as the effective usage ratio of the first in-vehicle infotainment application. This effective usage ratio reflects the usage frequency of the first in-vehicle infotainment application among multiple first in-vehicle infotainment applications, thereby determining the magnitude of the true rating value of the first in-vehicle infotainment application. Obviously, if the usage frequency of the first in-vehicle infotainment application is higher, that is, if the effective usage ratio of the first in-vehicle infotainment application is larger, then the absolute value of the true rating value of the first in-vehicle infotainment application will also be larger; conversely, if the usage frequency of the first in-vehicle infotainment application is lower, that is, if the effective usage ratio of the first in-vehicle infotainment application is smaller, then the absolute value of the true rating value of the first in-vehicle infotainment application will also be smaller.

[0051] In some implementations, as the above analysis shows, the computer device determines the total number of times a target user uses multiple first vehicle-mounted applications and the target number of times each first vehicle-mounted application can be based on a preset duration. That is, the total number of uses and the target number of uses are updated at the last moment of each preset duration. Specifically, the total number of uses determined by the computer device can be the average of the total number of uses of multiple first vehicle-mounted applications within the preset duration, or it can be the sum of the number of uses of multiple first vehicle-mounted applications within each preset duration before the data update time. For example, if the preset duration is 10 days, the computer device will update the total number of uses and the target number of uses at the last moment of these 10 days. Furthermore, if the current time is the last moment of the third preset duration, the total number of uses of multiple first vehicle-mounted applications determined by the computer device can be the number of uses of multiple first vehicle-mounted applications within these 10 days, or it can be the total number of uses of multiple first vehicle-mounted applications within the previous 30 days.

[0052] Step S203: Based on the effective usage ratio of each first vehicle-mounted application and the driving factor, determine the target user's true rating value for each first vehicle-mounted application. The driving factor represents the positive or negative value of the true rating value during the novice stage, which is opposite to the positive or negative value of the true rating value during the experienced stage.

[0053] In this embodiment, the computer device can determine whether the driving stage corresponding to each first vehicle-mounted application belongs to the novice stage or the experienced stage through the above steps, that is, determine whether the driving factor corresponding to each first vehicle-mounted application belongs to the first driving factor or the second driving factor; at the same time, the computer device also determines the effective usage ratio of each first vehicle-mounted application, that is, determine the usage frequency of each first vehicle-mounted application among multiple first vehicle-mounted applications. Based on this, the computer device determines the true score value of each first vehicle-mounted application through the effective usage ratio of each first vehicle-mounted application and the driving factor. In order to make the true score value more intuitively represent the driving stage corresponding to the first vehicle-mounted application, the computer device can make the true score value include positive and negative values, and correspond the positive or negative value of the true score value to the novice stage or experienced stage represented by the driving factor. Moreover, the positive or negative value of the true score value when the driving factor represents the novice stage is opposite to the positive or negative value of the true score value when the driving factor represents the experienced stage.

[0054] In some implementations, the method for determining the true score in step S203 can be implemented in the following ways:

[0055] The product of the effective usage percentage of each first vehicle infotainment application and the driving factor of each first vehicle infotainment application is obtained as the target user's true rating value for each first vehicle infotainment application.

[0056] Specifically, the computer device can set the driving factor to +1 or -1 to represent a positive or negative value, thus ensuring that the driving factor, representing the actual rating value during the novice stage, is the opposite of the driving factor, representing the actual rating value during the experienced stage. For example, the computer device can set a driving factor of +1 to represent the driving stage corresponding to the first vehicle infotainment application as the novice stage, and a driving factor of -1 to represent the driving stage corresponding to the first vehicle infotainment application as the experienced stage. If one of the first vehicle infotainment applications corresponds to the novice stage, the computer device can multiply the driving factor of +1 by the effective usage percentage corresponding to that first vehicle infotainment application. The absolute value of this product not only represents the actual usage frequency of the first vehicle infotainment application, but also, through the positive sign of the product, represents the usage stage corresponding to the first vehicle infotainment application as the novice stage, thus achieving a correspondence between the positive or negative value of the actual rating value of each first vehicle infotainment application and the driving factor.

[0057] Step S204: Obtain the actual rating value of each of the multiple first users for each of the first vehicle infotainment applications and each of the second vehicle infotainment applications, wherein the first users are users who have used the first vehicle infotainment application and the second vehicle infotainment application.

[0058] In this embodiment, the computer device can determine the similarity between any two in-vehicle infotainment applications by obtaining the actual ratings of each in-vehicle infotainment application from all first users who have used both the first and second applications. Here, the first user is different from the target user; all in-vehicle applications used by the target user are considered first applications, and all in-vehicle applications not used are considered second applications. However, all first users can include multiple different first users, where any one first user may have only used some of the first or some of the second applications. Nevertheless, the actual ratings obtained by the computer device from all first users for all in-vehicle applications should cover the actual ratings of multiple first and second applications.

[0059] In some implementations, the method by which the computer device obtains the actual rating values ​​of each first user for each in-vehicle application can be the same as the method for obtaining the actual rating values ​​of the target user for the first in-vehicle application. First, the driving factor corresponding to each target in-vehicle application used by the first user is obtained. Specifically, the driving factor of the target in-vehicle application can be determined as either the first driving factor or the second driving factor by comparing the number of times the target in-vehicle application is used in the novice stage with the number of times it is used in the experienced stage. Next, the ratio of the target number of times the target in-vehicle application is used to the total number of times all target in-vehicle applications are used is obtained as the effective usage percentage of the target in-vehicle application. Finally, the product of the driving factor and the effective usage percentage is taken as the actual rating value of the target in-vehicle application.

[0060] Step S205: Based on the actual rating values ​​of each first user for each first vehicle infotainment application and each second vehicle infotainment application, determine the similarity between each second vehicle infotainment application and each first vehicle infotainment application.

[0061] In this embodiment, the computer device can obtain the actual ratings of each first user for all the in-vehicle infotainment applications they have used. Since each first user's in-vehicle infotainment applications cover multiple first in-vehicle infotainment applications and all second in-vehicle infotainment applications, the computer device can obtain multiple sets of actual ratings for each first in-vehicle infotainment application and each second in-vehicle infotainment application. That is, each first in-vehicle infotainment application and each second in-vehicle infotainment application may include different actual ratings given by multiple different first users. The computer device can determine the similarity between two in-vehicle infotainment applications based on the multiple sets of actual ratings corresponding to any two in-vehicle infotainment applications. Specifically, to facilitate in-vehicle infotainment application recommendations for target users, the computer device can obtain the similarity between each second in-vehicle infotainment application and each first in-vehicle infotainment application, and use this similarity, along with the target user's actual rating for each first in-vehicle infotainment application, to determine the target user's predicted rating for each second in-vehicle infotainment application.

[0062] In some implementations, when determining the similarity between a target second in-vehicle infotainment application and a target first in-vehicle infotainment application in a first in-vehicle infotainment application, the computer device can filter all first users who simultaneously use both the target first in-vehicle infotainment application and the target second in-vehicle infotainment application from among all first users. Based on the actual ratings given by these filtered first users to the target first in-vehicle infotainment application and the target second in-vehicle infotainment application, the similarity between the target first in-vehicle infotainment application and the target second in-vehicle infotainment application is determined. By repeating the above method, the computer device can obtain the similarity between each second in-vehicle infotainment application and each first in-vehicle infotainment application.

[0063] In some implementations, such as Figure 5As shown, the method for determining the similarity between each first vehicle infotainment application and each second vehicle infotainment application in step S205 can be implemented through the following steps:

[0064] Step S2051: For each of the second vehicle infotainment applications, obtain the Euclidean distance between the actual rating value of each first user for the second vehicle infotainment application and the actual rating value of each first user for the first vehicle infotainment application.

[0065] In this embodiment, after determining the actual rating values ​​of each first user for the second vehicle infotainment application and the actual rating values ​​of each first user for the first vehicle infotainment application, the computer device can determine the similarity between the first and second vehicle infotainment applications by obtaining the Euclidean distance between their actual rating values. It is understood that the actual rating value of a first user for a particular vehicle infotainment application can characterize the frequency of the first user's use of that application, as well as whether the driving stage corresponding to that application is the novice or experienced driving stage. Therefore, if the Euclidean distance between the actual rating values ​​of the first and second vehicle infotainment applications is small, it indicates that the two applications are relatively similar. This includes not only the possibility that users may use the two applications similarly, but also the greater likelihood that users will use both applications simultaneously at the same driving stage. Similarly, if the Euclidean distance between the actual rating values ​​of the two applications is large, it indicates that the two applications differ significantly, including in terms of usage frequency and driving stage.

[0066] Specifically, the actual ratings of each first user for the first in-vehicle infotainment application can be represented as (x1, x2, x3, ..., x...). n The actual ratings of each first user for the second vehicle infotainment application can be represented as (y1, y2, y3, ..., y...). n Then, the Euclidean distance between the actual ratings of the first and second in-vehicle infotainment applications can be calculated using the following formula:

[0067]

[0068] If N out of all first users simultaneously use both the first vehicle infotainment application and the second vehicle infotainment application, then the computer device can obtain the N-dimensional real score value corresponding to the first vehicle infotainment application and the N-dimensional real score value corresponding to the second vehicle infotainment application.

[0069] Step S2052: Based on the Euclidean distance, determine the similarity between each second vehicle-mounted application and each first vehicle-mounted application.

[0070] In this embodiment, after obtaining the Euclidean distance between the actual rating values ​​of each first vehicle infotainment application and each second vehicle infotainment application, the computer device can convert the Euclidean distance and reduce the result to the range [0, 1], thus obtaining the similarity between the second vehicle infotainment applications and the first vehicle infotainment applications. Specifically, the conversion of Euclidean distance to similarity can be performed using the following formula:

[0071] S

[0072] Where d is the Euclidean distance between the actual rating of the first vehicle infotainment application and the actual rating of the second vehicle infotainment application. Using the above formula, the computer device can convert the Euclidean distance between these two actual ratings into the similarity between two vehicle infotainment applications within a certain range.

[0073] Step S206: Based on the similarity between each second vehicle infotainment application and each first vehicle infotainment application, determine the weight of the actual rating value of each first vehicle infotainment application to the predicted rating value of each second vehicle infotainment application.

[0074] In this embodiment, the similarity between each second vehicle-mounted application and each first vehicle-mounted application can characterize the probability that a target user would accept using the second vehicle-mounted application if they were using the first vehicle-mounted application. A higher similarity indicates a greater probability that the target user would also use the second vehicle-mounted application. Therefore, the computer device can determine the weight of the actual rating value of each first vehicle-mounted application to the predicted rating value of each second vehicle-mounted application based on the similarity between the second and first vehicle-mounted applications. The greater the similarity between the second and first vehicle-mounted applications, the greater the weight of the actual rating value to the predicted rating value. Thus, the computer device can further determine the predicted rating value of the second vehicle-mounted application based on the weight, making the predicted rating value of the second vehicle-mounted application closer to the actual rating value of the first vehicle-mounted application, which has a larger weight.

[0075] In some implementations, the computer device can directly use the similarity between the second in-vehicle application and the first in-vehicle application as the weight of the first in-vehicle application's actual rating value to the predicted rating value of the second in-vehicle application. It is understood that the similarity between the first and second in-vehicle applications is between [0, 1], and the actual rating value of the first in-vehicle application, which is the frequency of use of the first in-vehicle application by the target user, is also between [-1, 1]. Therefore, the computer device can directly use the similarity between the two in-vehicle applications as the weight of the actual rating value to the predicted rating value, and the calculated predicted rating value will still be between [-1, 1].

[0076] Step S207: For each second vehicle infotainment application, based on the weight of the actual rating value of each first vehicle infotainment application to the predicted rating value of each second vehicle infotainment application, perform a weighted calculation on the actual rating value of each first vehicle infotainment application to obtain the predicted rating value of the target user for each second vehicle infotainment application.

[0077] In this embodiment, after determining the weight of the actual rating value of each first vehicle-mounted application to the predicted rating value of each second vehicle-mounted application, the computer device can obtain the predicted rating value of each second vehicle-mounted application based on the actual rating value of each first vehicle-mounted application. The predicted rating value can be obtained by weighted summation of each actual rating value.

[0078] Understandably, each first in-vehicle infotainment application's actual rating includes both positive and negative values. When calculating the predicted rating for the second in-vehicle infotainment application, the sign of the actual rating is also taken into account, resulting in a predicted rating that is also positive or negative. Similar to the actual rating, a positive or negative predicted rating can also indicate whether the second in-vehicle infotainment application corresponds to a novice or experienced driving stage. If the second in-vehicle infotainment application has a high similarity to a first in-vehicle infotainment application at the novice stage—meaning the actual rating of the first in-vehicle infotainment application at the novice stage carries a larger weight in the predicted rating of the second in-vehicle infotainment application—then the calculated predicted rating of the second in-vehicle infotainment application will be closer to the actual rating of the first in-vehicle infotainment application at the novice stage.

[0079] Step S208: Based on whether the predicted score value of each second vehicle-mounted application is positive or negative, determine the second vehicle-mounted application that matches the driving stage corresponding to the target user, and use it as the filtered second vehicle-mounted application.

[0080] In this embodiment of the application, as can be seen from the above analysis, the predicted score calculated by the second vehicle-mounted application also includes positive or negative values. Furthermore, the positive or negative value of the predicted score is based on the positive or negative value of the actual score. That is, if the actual score is positive and has a significant impact on the predicted score (i.e., a large weight), then the predicted score is very likely to be positive as well. Moreover, the positive value of the predicted score and the positive value of the actual score should represent the same meaning. In other words, if the actual score is positive, indicating that the driving stage of the corresponding first vehicle-mounted application is the novice stage, then the predicted score obtained based on the actual score will also be positive, indicating that the driving stage corresponding to the second vehicle-mounted application is also the novice stage. Similarly, if the predicted score of the second vehicle-mounted application is negative, it can indicate that the driving stage corresponding to the second vehicle-mounted application is the experienced stage.

[0081] Clearly, all second-stage in-vehicle infotainment applications can include some for novice drivers and some for experienced drivers. Therefore, after determining the meaning of the positive or negative sign of the predicted rating, the computer device can filter all second-stage applications, selecting those that match the target user's current driving stage. This ensures that the final recommended second-stage applications are appropriate for the target user's driving stage. For example, if a positive predicted rating indicates that the second-stage application corresponds to a novice driver, and the target user is also currently a novice driver, then the computer device can discard any second-stage applications with non-positive predicted ratings.

[0082] In some implementations, the computer device can determine the current driving stage of the target user based on the mileage in the embedded data. The mileage is used to represent the total distance the vehicle traveled during the data collection. If the mileage is less than a preset value, the computer device can determine that the target user's driving stage is the novice stage; if the mileage is greater than or equal to the preset value, the target user's driving stage is determined to be the experienced stage.

[0083] Step S209: Based on the predicted score value corresponding to the second vehicle infotainment application after screening, determine the second vehicle infotainment application to be recommended.

[0084] In this embodiment, after selecting all second vehicle-mounted applications matching the target user's driving stage based on the sign of the predicted rating, the computer device can further select the second vehicle-mounted applications most likely to be used by the target user based on the absolute value of their predicted ratings. Clearly, the absolute value of the predicted rating characterizes the frequency with which the second vehicle-mounted application is used by the target user. A larger absolute value indicates a higher probability of use by the target user; therefore, the computer device can prioritize recommending second vehicle-mounted applications with larger absolute predicted ratings to the target user.

[0085] In some implementations, the computer device can determine the number of second in-vehicle applications to be recommended based on the limitations of the target user's client. For example, if the target user's client is limited by screen size and only allows 10 second in-vehicle applications to be recommended, the computer device can select the top ten second in-vehicle applications with the highest absolute values ​​of their predicted ratings as the second in-vehicle applications to be recommended.

[0086] Step S210: Recommend the second in-vehicle application to be recommended to the client corresponding to the target user.

[0087] In this embodiment, after determining the second in-vehicle infotainment application to be recommended, the computer device can recommend all the second in-vehicle infotainment applications to be recommended to the client corresponding to the target user. The client corresponding to the target user can receive all the second in-vehicle infotainment applications to be recommended and display the icons of all the second in-vehicle infotainment applications in a specific recommendation area, so that the user can distinguish the second in-vehicle infotainment applications from the commonly used first in-vehicle infotainment applications when receiving the recommended second in-vehicle infotainment applications.

[0088] In some implementations, the computer device can also send the predicted score values ​​of all the second in-vehicle applications to be recommended to the target user's client. The target user's client can arrange all the second in-vehicle applications to be recommended according to the absolute value of the predicted score value, and arrange them in the recommended application area on the in-vehicle display screen according to the order of the arrangement.

[0089] In some implementations, the computer device can also send the actual rating values ​​of multiple first vehicle-mounted applications to the client corresponding to the target user. The client corresponding to the target user can arrange the multiple first vehicle-mounted applications according to the absolute value of the actual rating values ​​and display them in the frequently used application area of ​​the vehicle-mounted screen.

[0090] The application recommendation method provided in this application embodiment uses the ratio of the target usage frequency to the total usage frequency of a first vehicle infotainment application as the effective usage ratio of the first vehicle infotainment application. Based on the effective usage ratio and driving factors, the true rating value of the target user for the first vehicle infotainment application is determined. Based on the true rating values ​​of each first user for each first vehicle infotainment application and each second vehicle infotainment application, the similarity between each second vehicle infotainment application and each first vehicle infotainment application is determined, and then the weight of the true rating value of each first vehicle infotainment application for the predicted rating value of each second vehicle infotainment application is determined. The true rating values ​​of each first vehicle infotainment application are weighted to obtain the predicted rating value of each second vehicle infotainment application. Based on whether the predicted rating value of each second vehicle infotainment application is positive or negative, the second vehicle infotainment application matching the driving stage corresponding to the target user is determined as the filtered second vehicle infotainment application. Based on the predicted rating values ​​corresponding to the filtered second vehicle infotainment applications, the second vehicle infotainment applications to be recommended are determined, and the second vehicle infotainment applications to be recommended are recommended to the client corresponding to the target user. Therefore, by characterizing the driving factors corresponding to the driving stage of the first vehicle infotainment application, the positive or negative values ​​of the calculated real scores of multiple first vehicle infotainment applications are correlated with the driving factors. In turn, the predicted scores of all second vehicle infotainment applications determined based on the real scores can also be correlated with the driving stage of the second vehicle infotainment application through positive and negative values. Thus, recommending second vehicle infotainment applications to target users based on the predicted scores can make the recommended second vehicle infotainment applications more targeted and more in line with the user habits of the target users.

[0091] Please see Figure 6 The diagram shows a structural block diagram of an application recommendation device 200 provided in an embodiment of this application. The application recommendation device 200 includes: a data acquisition module 210, a scoring determination module 220, a score prediction module 230, and an application recommendation module 240. The data acquisition module 210 is used to acquire the driving factor, the total number of uses of the multiple first vehicle-mounted applications, and the target number of uses of each first vehicle-mounted application. The first vehicle-mounted applications are those used by the target user. The driving factor is used to characterize whether the driving stage corresponding to the vehicle-mounted application is the novice stage or the experienced stage. The rating determination module 220 is used to determine the target user's true rating value for each first vehicle-mounted application based on the driving factor, the total number of uses, and the target number of uses. The driving factor represents the positive or negative value of the true rating value in the novice stage, which is opposite to the positive or negative value of the true rating value in the experienced stage. The score prediction module 230 is used to determine the target user's predicted rating value for each second vehicle-mounted application based on the target user's true rating value for each first vehicle-mounted application and the similarity between each second vehicle-mounted application and each first vehicle-mounted application. The second vehicle-mounted applications are those not used by the target user. The application recommendation module 240 is used to recommend the second vehicle-mounted applications to the client corresponding to the target user based on the target user's driving stage and the predicted rating value.

[0092] As one possible implementation, the rating determination module 220 includes a percentage determination unit and a score determination unit. The percentage determination unit is used to obtain the ratio of the target usage count to the total usage count for each first vehicle-mounted application, thus obtaining the effective usage percentage for each first vehicle-mounted application. The score determination unit is used to determine the target user's true rating value for each first vehicle-mounted application based on the effective usage percentage and a driving factor, where the driving factor represents the positive or negative value of the true rating value during the novice stage, and is opposite to the positive or negative value of the true rating value during the experienced user stage.

[0093] As one possible implementation, the driving factor is 1 or -1, and the score determination unit is also used to obtain the product of the effective usage ratio of each first vehicle-mounted application and the driving factor of each first vehicle-mounted application, as the target user's true score value for each first vehicle-mounted application.

[0094] As one possible implementation, the data acquisition module 210 includes a factor acquisition unit, used to acquire the first number of times the target vehicle infotainment application is used in the novice stage and the second number of times it is used in the experienced stage. The target vehicle infotainment application is any one of a plurality of first vehicle infotainment applications. If the first number of times of use is greater than or equal to the second number of times of use, the driving factor of the target vehicle infotainment application is determined to be the first driving factor, which is used to characterize the driving stage corresponding to the target vehicle infotainment application as the novice stage. If the first number of times of use is less than the second number of times of use, the driving factor of the target vehicle infotainment application is determined to be the second driving factor, which is used to characterize the driving stage corresponding to the target vehicle infotainment application as the experienced stage.

[0095] As one possible implementation, the application recommendation device 200 further includes a score acquisition module and a similarity determination module. The score acquisition module is used to acquire the actual rating values ​​of each first user for each first vehicle-mounted application and each second vehicle-mounted application, where each first user is a user who has used both the first and second vehicle-mounted applications. The similarity determination module is used to determine the similarity between each second vehicle-mounted application and each first vehicle-mounted application based on the actual rating values ​​of each first user for each first and second vehicle-mounted application.

[0096] As one possible implementation, the similarity determination module is also used to obtain, for each second vehicle infotainment application, the Euclidean distance between each first user's actual rating value for the second vehicle infotainment application and each first user's actual rating value for the first vehicle infotainment application; and based on the Euclidean distance, determine the similarity between each second vehicle infotainment application and each first vehicle infotainment application.

[0097] As one possible implementation, the score prediction module 230 is further configured to determine the weight of the actual score of each first vehicle-mounted application to the predicted score of each second vehicle-mounted application based on the similarity between each second vehicle-mounted application and each first vehicle-mounted application; and for each second vehicle-mounted application, to perform a weighted calculation on the actual score of each first vehicle-mounted application based on the weight of the actual score of each first vehicle-mounted application to the predicted score of each second vehicle-mounted application, thereby obtaining the predicted score of the target user for each second vehicle-mounted application.

[0098] As one possible implementation, the application recommendation module 240 is further configured to determine, based on whether the predicted score value of each second vehicle-mounted application is positive or negative, a second vehicle-mounted application that matches the driving stage corresponding to the target user, and thus a filtered second vehicle-mounted application; based on the predicted score value corresponding to the filtered second vehicle-mounted applications, determine the second vehicle-mounted applications to be recommended; and recommend the second vehicle-mounted applications to be recommended to the client corresponding to the target user.

[0099] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0100] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0101] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0102] In summary, the solution provided in this application obtains the driving factors, target usage counts, and total usage counts of multiple first in-vehicle infotainment applications; based on the driving factors, total usage counts, and target usage counts, it determines the target user's actual rating for each first in-vehicle infotainment application; based on the target user's actual rating for each first in-vehicle infotainment application and the similarity between each second in-vehicle infotainment application and each first in-vehicle infotainment application, it determines the target user's predicted rating for each second in-vehicle infotainment application; and based on the target user's driving stage and predicted rating, it recommends second in-vehicle infotainment applications to the target user's corresponding client. Thus, by using the target user's driving stage and the actual ratings of the first in-vehicle infotainment applications, it selectively recommends second in-vehicle infotainment applications that the target user has not used, thereby making the recommended in-vehicle infotainment applications more in line with the user's usage habits.

[0103] Please refer to Figure 7 This diagram illustrates a structural block diagram of a computer device 300 provided in an embodiment of this application. The computer device 300 can be a physical server, a cloud server, or the like. The computer device 300 in this application may include one or more of the following components: a processor 310, a memory 320, and one or more application programs. The one or more application programs may be stored in the memory 320 and configured to be executed by the one or more processors 310. The one or more programs are configured to perform the methods described in the foregoing method embodiments.

[0104] Processor 310 may include one or more processing cores. Processor 310 connects to various parts of the computer device using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 320, and by calling data stored in memory 320. Optionally, processor 310 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 310 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 310 and may be implemented separately using a communication chip.

[0105] The memory 320 may include random access memory (RAM) or read-only memory (ROM). The memory 320 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 320 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created during the use of the computer device (such as phonebook data, audio and video data, chat log data, etc.).

[0106] Please refer to Figure 8 This diagram illustrates a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. The computer-readable medium 800 stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0107] The computer-readable storage medium 800 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 800 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 800 has storage space for program code 810 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 810 may be compressed, for example, in a suitable form.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An application recommendation method, characterized in that, The method includes: The system acquires the driving factor of each of a plurality of first in-vehicle infotainment applications, the total number of uses of the plurality of first in-vehicle infotainment applications, and the target number of uses of each first in-vehicle infotainment application; the first in-vehicle infotainment applications are those used by the target user, and the driving factor is used to characterize whether the driving stage corresponding to the in-vehicle infotainment application is the novice stage or the experienced stage; the process of acquiring the driving factor includes: acquiring the first number of uses of the target in-vehicle infotainment application in the novice stage and the second number of uses in the experienced stage, wherein the target in-vehicle infotainment application is any one of the plurality of first in-vehicle infotainment applications; if the first number of uses is greater than or equal to the second number of uses, then the driving factor of the target in-vehicle infotainment application is determined to be the first driving factor, which characterizes the driving stage corresponding to the target in-vehicle infotainment application as the novice stage; if the first number of uses is less than the second number of uses, then the driving factor of the target in-vehicle infotainment application is determined to be the second driving factor, which characterizes the driving stage corresponding to the target in-vehicle infotainment application as the experienced stage; The ratio of the target number of times each first vehicle-mounted application is used to the total number of times is obtained to obtain the effective usage ratio of each first vehicle-mounted application. Based on the effective usage ratio of each first vehicle-mounted application and the driving factor, the target user's true rating value for each first vehicle-mounted application is determined. The driving factor represents the positive or negative value of the true rating value during the novice stage, which is opposite to the positive or negative value of the true rating value during the experienced stage. Based on the target user's actual rating for each first in-vehicle application and the similarity between each second in-vehicle application and each first in-vehicle application, the predicted rating for each second in-vehicle application by the target user is determined, wherein the second in-vehicle application is an in-vehicle application that the target user has not used. Based on the driving stage corresponding to the target user and the predicted score, the second in-vehicle application is recommended to the client corresponding to the target user.

2. The method according to claim 1, characterized in that, The driving factor can be positive or negative, and the driving factor represents the positive or negative value of the actual score during the novice stage, which is opposite to the positive or negative value of the actual score during the experienced stage. The determination of the target user's true rating for each of the first in-vehicle applications based on the effective usage percentage of each first in-vehicle application and the driving factor includes: The product of the effective usage percentage of each first vehicle infotainment application and the driving factor of each first vehicle infotainment application is obtained as the target user's true rating value for each first vehicle infotainment application.

3. The method according to claim 1, characterized in that, Before determining the predicted rating of each second in-vehicle application based on the target user's actual rating of each first in-vehicle application and the similarity between each second in-vehicle application and each first in-vehicle application, the method further includes: Obtain the actual rating value of each of the first users for each of the first in-vehicle applications and each of the second in-vehicle applications, where the first users are users who have used the first in-vehicle applications and the second in-vehicle applications; Based on the actual rating values ​​of each first user for each first vehicle infotainment application and each second vehicle infotainment application, the similarity between each second vehicle infotainment application and each first vehicle infotainment application is determined.

4. The method according to claim 3, characterized in that, The step of determining the similarity between each second vehicle-mounted application and each first vehicle-mounted application based on the actual rating values ​​of each first user for each first vehicle-mounted application and each second vehicle-mounted application includes: For each of the second vehicle infotainment applications, obtain the Euclidean distance between the actual rating of each first user for the second vehicle infotainment application and the actual rating of each first user for the first vehicle infotainment application; Based on the Euclidean distance, the similarity between each second vehicle-mounted application and each first vehicle-mounted application is determined.

5. The method according to any one of claims 1-4, characterized in that, The step of determining the predicted rating of each second in-vehicle application by the target user based on the target user's actual rating of each first in-vehicle application and the similarity between each second in-vehicle application and each first in-vehicle application includes: Based on the similarity between each second vehicle infotainment application and each first vehicle infotainment application, the weight of the actual rating value of each first vehicle infotainment application to the predicted rating value of each second vehicle infotainment application is determined. For each second vehicle infotainment application, the actual rating of each first vehicle infotainment application is weighted and calculated based on the weight of the actual rating of each first vehicle infotainment application to the predicted rating of each second vehicle infotainment application, so as to obtain the predicted rating of the target user for each second vehicle infotainment application.

6. The method according to any one of claims 1-4, characterized in that, The step of recommending the second in-vehicle application to the client corresponding to the target user based on the driving stage corresponding to the target user and the predicted score includes: Based on whether the predicted score of each second vehicle-mounted application is positive or negative, the second vehicle-mounted application that matches the driving stage corresponding to the target user is determined as the filtered second vehicle-mounted application. Based on the predicted score value corresponding to the second in-vehicle application after screening, a second in-vehicle application to be recommended is determined. The second in-vehicle application to be recommended is recommended to the client corresponding to the target user.

7. An application recommendation device, characterized in that, The device includes: The data acquisition module is used to acquire the driving factor of each of the multiple first in-vehicle applications, the total number of uses of the multiple first in-vehicle applications, and the target number of uses of each first in-vehicle application; the first in-vehicle applications are those used by the target user, and the driving factor is used to characterize whether the driving stage corresponding to the in-vehicle application is the novice stage or the experienced stage; the process of acquiring the driving factor includes: acquiring the first number of uses of the target in-vehicle application in the novice stage and the second number of uses in the experienced stage, wherein the target in-vehicle application is any one of the multiple first in-vehicle applications; if the first number of uses is greater than or equal to the second number of uses, then the driving factor of the target in-vehicle application is determined to be the first driving factor, which characterizes the driving stage corresponding to the target in-vehicle application as the novice stage; if the first number of uses is less than the second number of uses, then the driving factor of the target in-vehicle application is determined to be the second driving factor, which characterizes the driving stage corresponding to the target in-vehicle application as the experienced stage; The rating determination module is used to obtain the ratio of the target usage times to the total usage times of each first vehicle-mounted application, thereby obtaining the effective usage ratio of each first vehicle-mounted application; based on the effective usage ratio of each first vehicle-mounted application and the driving factor, the module determines the target user's true rating value for each first vehicle-mounted application, wherein the driving factor represents the positive or negative value of the true rating value during the novice stage, and is opposite to the positive or negative value of the true rating value during the experienced stage. The score prediction module is used to determine the predicted score of the target user for each second vehicle infotainment application based on the target user's actual score for each first vehicle infotainment application and the similarity between each second vehicle infotainment application and each first vehicle infotainment application, wherein the second vehicle infotainment application is a vehicle infotainment application that the target user has not used. The application recommendation module is used to recommend the second in-vehicle application to the client corresponding to the target user based on the driving stage corresponding to the target user and the predicted score.

8. A computer device, characterized in that, The computer device includes: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that can be invoked by a processor to execute the method as described in any one of claims 1-6.

Images