Push methods, devices, vehicles and storage media for in-vehicle applications

Abstract

This application relates to a method, apparatus, vehicle, and storage medium for pushing in-vehicle applications, comprising: inputting the acquired annotation information of the application to be pushed into a pre-built application model to obtain the type of the application to be pushed; inputting this type into a pre-built user model to obtain a first user set, a second user set, and a third user set corresponding to the application to be pushed; pushing the application to be pushed to all users in the first user set, target users in the second user set who meet a first preset push condition, and pushing the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push condition. Thus, by pushing services and content to users based on user habits and application types, this addresses the problems of uneven overall usage frequency and activity among numerous in-vehicle applications and user aversion to pushed content, thereby increasing user usage frequency and coverage, and maintaining user activity.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, device, vehicle, and storage medium for pushing in-vehicle applications. Background Technology

[0002] With the continuous development of the field of vehicle intelligence, vehicles are carrying more and more services and applications of various types. However, in reality, users rarely use or have never used many of the applications and services on the vehicle while driving. This situation will result in users not being able to obtain the corresponding services well, and the corresponding services and applications will not be able to obtain the corresponding benefits through user use. In order to improve the usage rate of in-vehicle applications, there are currently many recommendation and push methods.

[0003] In related technologies, there is an information push method that obtains the user's first data feature log, including user identifier, scene identifier, and user's historical behavior features. Based on the first data feature log, it extracts a first sample set with click features and a second sample set with sharing features from the database according to a set dimension. The first sample set is input into a deep learning model for training to obtain a click prediction model. The click prediction model is then transferred to a sharing prediction model, and combined with the second sample set for further training to obtain a trained sharing prediction model. The trained sharing prediction model is then used to predict online candidate users to obtain target users that meet preset conditions, thereby realizing the push of target advertising information to target users.

[0004] However, this method can only increase the usage rate of the corresponding applications to a certain extent. It is limited to recommending information on applications and services that users frequently use, and cannot improve the overall usage rate and activity of a wide range of applications. This issue urgently needs to be addressed. Summary of the Invention

[0005] This application provides a method, device, vehicle, and storage medium for pushing in-vehicle applications, in order to solve problems such as the imbalance in the overall usage frequency and activity of numerous in-vehicle applications and the aversion of users to pushed content, thereby increasing the frequency and coverage of user usage and maintaining user activity.

[0006] The first aspect of this application provides a method for pushing in-vehicle applications, comprising the following steps:

[0007] Obtain the labeling information of the application to be pushed;

[0008] The annotation information of the application to be pushed is input into a pre-built application model to obtain the type of the application to be pushed, and the type of the application to be pushed is input into a pre-built user model to obtain a first user set, a second user set, and a third user set corresponding to the application to be pushed; and

[0009] The application to be pushed is pushed to all users in the first user set, and the application to be pushed is pushed to target users in the second user set who meet the first preset push conditions. When any user in the third user set meets the second preset push conditions, the application to be pushed is pushed to all users in the third user set.

[0010] Based on the aforementioned technical means, this application can label and model users and applications before pushing applications, and cluster users and applications based on the information in the model. During the user's vehicle use, applications can be pushed to the user according to the relevant rules set by the operators, thereby increasing the user's usage frequency and coverage, and maintaining user activity.

[0011] Furthermore, before inputting the annotation information of the application to be pushed into the pre-built application model, the following steps are also included:

[0012] Obtain a target application set, wherein the target application set includes the annotation information of each target application and the type of each target application;

[0013] The first neural network is trained based on the annotation information and type of each target application to obtain the constructed application model.

[0014] Based on the aforementioned technical means, this application pre-constructs an application model according to the characteristics of the application, which can classify the applications to be pushed to users in terms of type, so as to reasonably push different types of applications to users and improve the activity of users using applications and services.

[0015] Furthermore, before inputting the type of the application to be pushed into the pre-built user model, the method also includes:

[0016] Obtain a set of users to be trained, wherein the set of users to be trained includes the interest information and the demand information of each user;

[0017] Based on the interest information and the demand information of each user, at least one application type is determined for each user;

[0018] The pre-built user model is obtained by training a preset second neural network based on the interest information and demand information of each user and at least one application type corresponding to each user.

[0019] Based on the aforementioned technical means, this application pre-constructs user models according to user characteristics, which can divide numerous users into different user clusters and use collaborative filtering to push applications to users, avoiding pushing application content that users are not interested in, thereby enhancing the user experience.

[0020] Further, after pushing the application to be pushed to all users in the first user set, pushing the application to be pushed to target users in the second user set who meet the first preset push condition, and pushing the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push condition, the method further includes:

[0021] Obtain the first feedback result of the first user set for the application to be pushed, the second feedback result of the second user set for the application to be pushed, and the third feedback result of the third user set for the application to be pushed;

[0022] Based on the first feedback result, the second feedback result, and the third feedback result, a fourth user set is selected to refuse to use the application to be pushed, and the interest information and demand information of all users in the fourth user set are adjusted, and the pre-built user model is updated according to the adjusted fourth user set.

[0023] Based on the aforementioned technical means, this application can record user feedback on different application push notifications, re-label some users, and build models to further improve the application push notification mechanism for different users.

[0024] Furthermore, after obtaining the first user set, the second user set, and the third user set corresponding to the application to be pushed, the method further includes:

[0025] If the type of the application to be pushed is an application strongly promoted by the operator and the application to be pushed corresponds to the third user set, then the incentive level of the application to be pushed is adjusted, wherein the incentive level is negatively correlated with the degree of interest of users in the first to third user sets in the application to be pushed.

[0026] Based on the aforementioned technical means, this application can increase the frequency and stickiness of users' use of certain applications by using an adjustable incentive system for some of the applications that are strongly promoted by the operators, thereby increasing users' enthusiasm for using in-vehicle applications.

[0027] A second aspect of this application provides a push device for in-vehicle applications, comprising:

[0028] The acquisition module is used to obtain the annotation information of the application to be pushed;

[0029] The input module is used to input the annotation information of the application to be pushed into a pre-built application model to obtain the type of the application to be pushed, and to input the type of the application to be pushed into a pre-built user model to obtain a first user set, a second user set, and a third user set corresponding to the application to be pushed; and

[0030] The push module is used to push the application to be pushed to all users in the first user set, push the application to be pushed to target users in the second user set who meet the first preset push conditions, and push the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push conditions.

[0031] Furthermore, before inputting the annotation information of the application to be pushed into the pre-built application model, the input module is also used for:

[0032] Obtain a target application set, wherein the target application set includes the annotation information of each target application and the type of each target application;

[0033] The first neural network is trained based on the annotation information and type of each target application to obtain the constructed application model.

[0034] Furthermore, before inputting the type of the application to be pushed into the pre-built user model, the input module is also used to:

[0035] Obtain a set of users to be trained, wherein the set of users to be trained includes the interest information and the demand information of each user;

[0036] Based on the interest information and the demand information of each user, at least one application type is determined for each user;

[0037] The pre-built user model is obtained by training a preset second neural network based on the interest information and demand information of each user and at least one application type corresponding to each user.

[0038] Further, after pushing the application to be pushed to all users in the first user set, pushing the application to be pushed to target users in the second user set who meet the first preset push condition, and pushing the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push condition, the push module is further configured to:

[0039] Obtain the first feedback result of the first user set for the application to be pushed, the second feedback result of the second user set for the application to be pushed, and the third feedback result of the third user set for the application to be pushed;

[0040] Based on the first feedback result, the second feedback result, and the third feedback result, a fourth user set is selected to refuse to use the application to be pushed, and the interest information and demand information of all users in the fourth user set are adjusted, and the pre-built user model is updated according to the adjusted fourth user set.

[0041] Furthermore, after obtaining the first user set, the second user set, and the third user set corresponding to the application to be pushed, the input module is further configured to:

[0042] If the type of the application to be pushed is an application strongly promoted by the operator and the application to be pushed corresponds to the third user set, then the incentive level of the application to be pushed is adjusted, wherein the incentive level is negatively correlated with the degree of interest of users in the first to third user sets in the application to be pushed.

[0043] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the in-vehicle application push method as described in the above embodiments.

[0044] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the vehicle application push method as described in the above embodiments.

[0045] The beneficial effects of the embodiments of this application are as follows:

[0046] (1) It can increase the frequency of users’ use of infrequent and newly launched applications, increase users’ activity in different applications, avoid the situation where users can only enjoy some application services, and also avoid the phenomenon that applications are recommended more and more the more users use them, and become more and more “invisible” the less they use them.

[0047] (2) Expand the scope of users’ use of in-vehicle applications, use collaborative filtering to avoid recommending content that users do not like, and use an adjustable incentive system to increase the frequency and stickiness of users’ use of some applications, thereby increasing the enthusiasm of vehicle users to use application services and improving user activity.

[0048] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0049] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0050] Figure 1 This is a flowchart illustrating a method for pushing information from an in-vehicle application according to an embodiment of this application;

[0051] Figure 2 This is a flowchart illustrating the workflow of a push system for an in-vehicle application according to an embodiment of this application.

[0052] Figure 3 This is a block diagram of a push device for an in-vehicle application according to an embodiment of this application;

[0053] Figure 4 This is a structural schematic diagram of a vehicle according to an embodiment of this application.

[0054] Among them: 10-Push device for vehicle application, 100-Acquisition module, 200-Input module, 300-Push module, 401-Memory, 402-Processor, 403-Communication interface. Detailed Implementation

[0055] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0056] The following description, with reference to the accompanying drawings, describes a method, apparatus, vehicle, and storage medium for pushing in-vehicle applications according to embodiments of this application.

[0057] Before introducing the push method for in-vehicle applications proposed in the embodiments of this application, let's briefly introduce the information push methods in related technologies.

[0058] In related technologies, an information push method and apparatus are proposed. The method includes: acquiring feature values ​​of multiple historical behavioral features used to characterize a target user's selection and use of each push information; for each push information, inputting the feature values ​​of the multiple historical behavioral features corresponding to the push information into a selection probability prediction model corresponding to the information category of the push information, and obtaining the selection probability of the target user selecting the push information in that information category; determining the target push information category for the target user based on the selection probability of the target user selecting the push information in each information category, and determining the target push information based on the determined target push information category.

[0059] However, while this method can increase the frequency of users' use of the corresponding applications to some extent, it is limited to recommending information about the applications and services that users frequently use, and cannot improve the overall usage rate and activity of users across a wide range of applications.

[0060] Based on the aforementioned problems, this application provides a method for pushing in-vehicle applications. In this method, by inputting the acquired annotation information of the application to be pushed into a pre-built application model, the type of the application to be pushed can be obtained. This type is then input into a pre-built user model to obtain a first user set, a second user set, and a third user set corresponding to the application to be pushed. The application to be pushed is then pushed to all users in the first user set, to target users in the second user set who meet a first preset push condition, and to all users in the third user set when any user in the third user set meets the second preset push condition. Thus, by pushing services and content to users based on their usage habits and application types, this method solves the problems of uneven overall usage frequency and activity among numerous in-vehicle applications and user aversion to pushed content, thereby increasing user usage frequency and coverage, and maintaining user activity.

[0061] Specifically, Figure 1 This is a flowchart illustrating a method for pushing in-vehicle applications according to an embodiment of this application. Figure 2 This is a flowchart illustrating the workflow of an in-vehicle application push system according to one embodiment of this application.

[0062] Combination Figure 1 , Figure 2 As shown, the push notification method for this in-vehicle application includes the following steps:

[0063] In step S101, the annotation information of the application to be pushed is obtained.

[0064] It is understood that, in the embodiments of this application, the application to be pushed can be labeled before the relevant application is pushed to form label information. The label information of the application to be pushed may include the application category, the application launch time, etc.

[0065] In step S102, the annotation information of the application to be pushed is input into the pre-built application model to obtain the type of the application to be pushed, and the type of the application to be pushed is input into the pre-built user model to obtain the first user set, the second user set and the third user set corresponding to the application to be pushed.

[0066] Among them, the first user set corresponding to the application to be pushed can be the user set with a high degree of interest in the application to be pushed; the second user set corresponding to the application to be pushed can be the user set composed of all users; and the third user set corresponding to the application to be pushed can be the user set with a low frequency of use of the application to be pushed.

[0067] Specifically, by inputting the labeling information of the application to be pushed into a pre-built application model, the type of the application to be pushed can be output. The types of the applications to be pushed include newly launched applications, applications with low user frequency, and applications with high user interest. Then, by inputting the type of the application to be pushed into a pre-built user model, the user set corresponding to the application to be pushed can be output, namely the first user set, the second user set, and the third user set.

[0068] Furthermore, in some embodiments, before inputting the annotation information of the application to be pushed into the pre-built application model, the method further includes: obtaining a target application set, wherein the target application set includes the annotation information of each target application and the type of each target application; training a preset first neural network based on the annotation information of each target application and the type of each target application to obtain the constructed application model.

[0069] Specifically, in this application embodiment, an application model can be pre-constructed according to the characteristics of the application. First, a set of target applications including the annotation information of each target application and the type of each target application is obtained. The applications are clustered according to the annotation information and type of each target application, and a preset first neural network is trained to obtain the constructed application model.

[0070] Furthermore, in some other embodiments, before inputting the type of the application to be pushed into the pre-built user model, the method further includes: obtaining a user set to be trained, wherein the user set to be trained includes interest information and demand information of each user; determining at least one application type corresponding to each user based on the interest information and demand information of each user; and training a preset second neural network based on the interest information and demand information of each user and the at least one application type corresponding to each user to obtain the pre-built user model.

[0071] Specifically, in this application embodiment, a user model can be pre-constructed based on the characteristics of the user. First, a user set to be trained is obtained, including the interest information and the demand information of each user. The user's interest information may be basketball, music, entertainment news, etc., and the demand information may be weather forecast, navigation map, etc. Based on the interest information and demand information of each user, at least one application type corresponding to each user is determined. Based on the interest information, demand information and the at least one application type corresponding to each user, the users are clustered, and a preset second neural network is trained to obtain the pre-constructed user model.

[0072] In step S103, the application to be pushed is pushed to all users in the first user set, and the application to be pushed is pushed to target users in the second user set who meet the first preset push conditions. When any user in the third user set meets the second preset push conditions, the application to be pushed is pushed to all users in the third user set.

[0073] Specifically, since the types of applications to be pushed to the first user set are those that users are highly interested in, and these applications are frequently used by users in the first user set, when there is a push task, this application can directly push applications related to this application type to all users in the first user set. The types of applications to be pushed to the second user set are newly launched applications. When there is a push task, this application can determine the category of the application to be pushed (such as film and entertainment, education, etc.) through the labeling information of the application, and filter users interested in this category of application from the second user set. When users in the second user set meet the first preset push condition, that is, when users in the second user set are driving in a specific environment, such as being powered on, at a certain time, at a certain location, or when the vehicle condition reaches a certain threshold. When a user uses a related application, triggering an application push notification for that user, the newly launched application can be pushed to target users in the second user set who meet the first preset push conditions. The timing of the push can be preset by the operations personnel or a default push time can be set. The third user set corresponds to applications with low user frequency. When there is a push task, this application can filter the applications that users in the third user set are interested in by viewing the user's application categories. The applications that meet the second preset push conditions, i.e., those that belong to the application type with low user frequency, can be pushed to all users in the third user set when an application push is triggered.

[0074] Therefore, in this embodiment of the application, before pushing applications, users and applications to be pushed are labeled and models are built to filter and classify users and applications to be pushed. When a user clicks on an application or content, the content of the application can be pushed to other users in the same category (i.e., the same user set) in a timely manner. If other applications need to be pushed, applications can also be pushed to users who have used similar applications based on the characteristics of the application.

[0075] Furthermore, in some embodiments, after pushing the application to be pushed to all users in the first user set, pushing the application to be pushed to target users in the second user set who meet the first preset push conditions, and pushing the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push conditions, the method further includes: obtaining the first feedback result of the application to be pushed in the first user set, the second feedback result of the application to be pushed in the second user set, and the third feedback result of the application to be pushed in the third user set; based on the first feedback result, the second feedback result, and the third feedback result, filtering out a fourth user set that refuses to use the application to be pushed, adjusting the interest information and demand information of all users in the fourth user set, and updating the pre-built user model according to the adjusted fourth user set.

[0076] Specifically, after pushing the application to be pushed to users in the first to third user sets respectively, the system can obtain and record the feedback results of the first to third user sets on the application to be pushed, i.e., the first to third feedback results. The system can re-label users based on the user feedback results, filter out the fourth user set that ignores or refuses to use the application to be pushed, and perform calculation iterations in the subsequent recommendation process to adjust the interest and demand information of all users in the fourth user set, and update the pre-built user model based on the adjusted fourth user set.

[0077] Furthermore, in some embodiments, after obtaining the first user set, the second user set, and the third user set corresponding to the application to be pushed, the method further includes: if the type of the application to be pushed is an operationally promoted application and the application to be pushed corresponds to the third user set, then the incentive level of the application to be pushed is adjusted, wherein the incentive level is negatively correlated with the degree of interest of users in the first to third user sets in the application to be pushed.

[0078] It should be noted that, for the remaining applications with low user frequency awaiting push notifications, this application embodiment can categorize these applications into operationally promoted applications and operationally non-promoted applications. The classification criteria can be set by the operations personnel; that is, some applications, although not frequently used, are considered key applications, or some applications are expected to generate revenue, and these applications need to be strongly promoted to users at appropriate times.

[0079] Specifically, when the type of application to be pushed is a strongly promoted application and corresponds to a third user group, an incentive system is added to the recommendation of such applications. This involves ranking users in the third user group based on their interest in these applications and adjusting the incentive level for the application to be pushed. The incentive level is negatively correlated with the interest level of users in the first to third user groups, meaning different users will have different incentive levels for different applications. Incentive methods include, but are not limited to, points, badges, and coupons; the specific incentive methods can be defined by the operations staff.

[0080] It is understandable that this application uses collaborative filtering to push applications to users. Pushing applications that users do not use often may reduce users' comfort and satisfaction while riding in the car. This application embodiment can use incentive methods to adjust user activity, reduce users' aversion to pushed applications, thereby balancing the frequency of users' use of different applications, encouraging users to enjoy all in-vehicle application services as much as possible, and improving users' activity in using applications and services.

[0081] According to the in-vehicle application push method proposed in this application, by inputting the obtained annotation information of the application to be pushed into a pre-built application model, the type of the application to be pushed can be obtained. This type is then input into a pre-built user model to obtain a first user set, a second user set, and a third user set corresponding to the application to be pushed. The application to be pushed is then pushed to all users in the first user set, to target users in the second user set who meet the first preset push condition, and to all users in the third user set when any user in the third user set meets the second preset push condition. Thus, by pushing services and content to users based on their usage habits and application types, this method solves the problems of uneven overall usage frequency and activity among numerous in-vehicle applications and user aversion to pushed content, thereby increasing user usage frequency and coverage, and maintaining user activity.

[0082] Next, referring to the accompanying drawings, a push device for an in-vehicle application according to an embodiment of this application is described.

[0083] Figure 3 This is a block diagram of a push device for an in-vehicle application according to an embodiment of this application.

[0084] like Figure 3 As shown, the push device 10 for the vehicle application includes: an acquisition module 100, an input module 200, and a push module 300.

[0085] Among them, the acquisition module 100 is used to acquire the annotation information of the application to be pushed;

[0086] Input module 200 is used to input the annotation information of the application to be pushed into a pre-built application model to obtain the type of the application to be pushed, and input the type of the application to be pushed into a pre-built user model to obtain the first user set, the second user set, and the third user set corresponding to the application to be pushed; and

[0087] The push module 300 is used to push the application to be pushed to all users in the first user set, push the application to be pushed to target users in the second user set who meet the first preset push conditions, and push the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push conditions.

[0088] Furthermore, in some embodiments, before inputting the annotation information of the application to be pushed into the pre-built application model, the input module 200 is also used for:

[0089] Obtain the target application set, which includes the annotation information and type of each target application;

[0090] The first neural network is trained based on the annotation information and type of each target application to obtain the constructed application model.

[0091] Furthermore, in some embodiments, before inputting the type of the application to be pushed into the pre-built user model, the input module 200 is also used to:

[0092] Obtain the user set to be trained, which includes each user's interest information and each user's demand information;

[0093] Determine at least one application type for each user based on each user's interest information and each user's needs information;

[0094] A pre-built user model is obtained by training a pre-set second neural network based on each user's interest information, each user's needs information, and at least one application type corresponding to each user.

[0095] Furthermore, in some embodiments, after pushing the application to be pushed to all users in the first user set, pushing the application to be pushed to target users in the second user set who meet the first preset push condition, and pushing the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push condition, the push module 300 is further configured to:

[0096] Obtain the first feedback result of the first user set for the application to be pushed, the second feedback result of the second user set for the application to be pushed, and the third feedback result of the third user set for the application to be pushed;

[0097] Based on the first, second, and third feedback results, a fourth user set is selected who refuse to use the application to be pushed to. The interest and demand information of all users in the fourth user set are adjusted, and the pre-built user model is updated according to the adjusted fourth user set.

[0098] Furthermore, in some embodiments, after obtaining the first user set, the second user set, and the third user set corresponding to the application to be pushed, the input module 200 is further configured to:

[0099] If the type of application to be pushed is an application strongly promoted by the operation and the application to be pushed corresponds to the third user set, then the incentive level of the application to be pushed will be adjusted. The incentive level is negatively correlated with the interest level of users in the first to third user sets in the application to be pushed.

[0100] It should be noted that the foregoing explanation of the push method embodiment for in-vehicle applications also applies to the push device for in-vehicle applications in this embodiment, and will not be repeated here.

[0101] According to the vehicle application push device proposed in this application embodiment, by inputting the acquired annotation information of the application to be pushed into a pre-built application model, the type of the application to be pushed can be obtained. This type is then input into a pre-built user model to obtain a first user set, a second user set, and a third user set corresponding to the application to be pushed. The application to be pushed is then pushed to all users in the first user set, to target users in the second user set who meet the first preset push condition, and to all users in the third user set when any user in the third user set meets the second preset push condition. Thus, by pushing services and content to users based on their usage habits and application types, the device solves problems such as the imbalance in the overall usage frequency and activity of numerous vehicle applications and user aversion to pushed content, thereby increasing user usage frequency and coverage, and maintaining user activity.

[0102] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0103] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0104] When the processor 402 executes the program, it implements the vehicle application push method provided in the above embodiments.

[0105] Furthermore, the vehicle also includes:

[0106] Communication interface 403 is used for communication between memory 401 and processor 402.

[0107] The memory 401 is used to store computer programs that can run on the processor 402.

[0108] The memory 401 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0109] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0110] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0111] Processor 402 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0112] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for pushing in-vehicle applications.

[0113] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0114] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0115] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0116] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0117] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0118] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for pushing information to in-vehicle applications, characterized in that, Includes the following steps: Obtain the labeling information of the application to be pushed; The annotation information of the application to be pushed is input into the pre-built application model to obtain the type of the application to be pushed, and the type of the application to be pushed is input into the pre-built user model to obtain the first user set, the second user set and the third user set corresponding to the application to be pushed; as well as The application to be pushed is pushed to all users in the first user set, and the application to be pushed is pushed to target users in the second user set who meet the first preset push conditions. When any user in the third user set meets the second preset push conditions, the application to be pushed is pushed to all users in the third user set. After obtaining the first user set, the second user set, and the third user set corresponding to the application to be pushed, the method further includes: If the type of the application to be pushed is an application strongly promoted by the operator and the application to be pushed corresponds to the third user set, then the incentive level of the application to be pushed is adjusted, wherein the incentive level is negatively correlated with the degree of interest of users in the first to third user sets in the application to be pushed.

2. The method according to claim 1, characterized in that, Before inputting the annotation information of the application to be pushed into the pre-built application model, the following steps are also included: Obtain a target application set, wherein the target application set includes the annotation information of each target application and the type of each target application; The first neural network is trained based on the annotation information and type of each target application to obtain the constructed application model.

3. The method according to claim 1, characterized in that, Before inputting the type of the application to be pushed into the pre-built user model, the following steps are also included: Obtain a set of users to be trained, wherein the set of users to be trained includes the interest information and the demand information of each user; Based on the interest information and the demand information of each user, at least one application type is determined for each user; The pre-built user model is obtained by training a preset second neural network based on the interest information and demand information of each user and at least one application type corresponding to each user.

4. The method according to claim 1 or 3, characterized in that, After pushing the application to be pushed to all users in the first user set, pushing the application to be pushed to target users in the second user set who meet the first preset push condition, and pushing the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push condition, the method further includes: Obtain the first feedback result of the first user set for the application to be pushed, the second feedback result of the second user set for the application to be pushed, and the third feedback result of the third user set for the application to be pushed; Based on the first feedback result, the second feedback result, and the third feedback result, a fourth user set is selected to refuse to use the application to be pushed, and the interest information and demand information of all users in the fourth user set are adjusted, and the pre-built user model is updated according to the adjusted fourth user set.

5. A push device for in-vehicle applications, characterized in that, include: The acquisition module is used to obtain the annotation information of the application to be pushed; The input module is used to input the annotation information of the application to be pushed into a pre-built application model to obtain the type of the application to be pushed, and input the type of the application to be pushed into a pre-built user model to obtain the first user set, the second user set and the third user set corresponding to the application to be pushed; as well as The push module is used to push the application to be pushed to all users in the first user set, push the application to be pushed to target users in the second user set who meet the first preset push conditions, and push the application to be pushed to all users in the third user set when any user in the third user set meets the second preset push conditions. After obtaining the first user set, the second user set, and the third user set corresponding to the application to be pushed, the input module is further used for: If the type of the application to be pushed is an application strongly promoted by the operator and the application to be pushed corresponds to the third user set, then the incentive level of the application to be pushed is adjusted, wherein the incentive level is negatively correlated with the degree of interest of users in the first to third user sets in the application to be pushed.

6. The apparatus according to claim 5, characterized in that, Before inputting the annotation information of the application to be pushed into the pre-built application model, the input module is further configured to: Obtain a target application set, wherein the target application set includes the annotation information of each target application and the type of each target application; The first neural network is trained based on the annotation information and type of each target application to obtain the constructed application model.

7. The apparatus according to claim 5, characterized in that, Before inputting the type of the application to be pushed into the pre-built user model, the input module is further configured to: Obtain a set of users to be trained, wherein the set of users to be trained includes the interest information and the demand information of each user; Based on the interest information and the demand information of each user, at least one application type is determined for each user; The pre-built user model is obtained by training a preset second neural network based on the interest information and demand information of each user and at least one application type corresponding to each user.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the push method for an in-vehicle application as described in any one of claims 1-4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the push method for in-vehicle applications as described in any one of claims 1-4.

Images