CN111435377B

CN111435377B - Application recommendation method, device, electronic equipment and storage medium

Info

Publication number: CN111435377B
Application number: CN201910028705.7A
Authority: CN
Inventors: 池彦佳; 李玮; 李晶晶; 姚少棉; 翁乐腾; 林兴; 陈浩; 李顺; 曾名杨; 古思鑫; 陈鸿强; 李凯; 杨奕鸿; 胡豪俊; 黄吉生; 杜嘉辉
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-01-11
Filing date: 2019-01-11
Publication date: 2023-09-22
Anticipated expiration: 2039-01-11
Also published as: CN111435377A

Abstract

The invention discloses an application recommendation method, an application recommendation device, electronic equipment and a storage medium, and belongs to the technical field of networks. According to the method provided by the embodiment of the invention, the embedded application associated with the user and the entry capable of recommending the embedded application are provided on the application client through the interface display mode, a direct channel is provided for the use and recommendation of the embedded application, the embedded application can be found and used by the user through an active recommendation mode, and meanwhile, a channel capable of directly reaching a certain page in the embedded application is provided, so that the user can directly enter the page of interest through the recommendation, and the propagation rate of the embedded application is improved.

Description

Application recommendation method, device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of network technologies, and in particular, to an application recommendation method, an application recommendation device, an electronic device, and a storage medium.

Background

With the development of application functions, more and more applications can provide a platform for the operation of third party applications, when the third party applications are downloaded in the applications, the third party applications can be operated in the applications, users do not need to jump to the outside of the current applications, namely, the functions of using the third party applications can be seamlessly connected in the current applications, and for the third party applications, the third party applications can be called as embedded applications. For example, some social applications at present can provide downloading of applications such as sharing bicycles, purchasing movie tickets or online shopping by scanning two-dimensional codes, searching application names or clicking sharing messages, and after downloading is completed, the downloaded applications can be run in the social applications, so that the function of quickly using other applications in the applications is realized.

However, the current embedded applications are generally obtained by the above-mentioned methods of scanning, searching or clicking to share the messages, and the propagation rate of the embedded applications is very low, so a method for recommending the embedded applications is needed to improve the propagation rate of the embedded applications.

Disclosure of Invention

The invention provides an application recommendation method, an application recommendation device, electronic equipment and a storage medium, which can improve the propagation rate of embedded applications. The technical proposal is as follows:

in one aspect, an application recommendation method is provided, the method including:

when a first display instruction is received, acquiring a recommended card of at least one embedded application of a first user, wherein the first user is a current login user of an application client, and one recommended card is associated with one link address;

displaying a target function interface in the application client according to the received first display instruction, wherein the target function interface comprises a plurality of application aggregation display options and at least one recommendation card of an embedded application of the first user, and one application aggregation display option is used for aggregating and displaying application information of the embedded application with a type of association relation with the first user;

And when a second display instruction is received, displaying an embedded application interface corresponding to a target recommendation card based on a link address associated with the target recommendation card in the application client, wherein the target recommendation card is the recommendation card corresponding to the second display instruction.

acquiring user access behavior information of a plurality of embedded applications of an application, wherein the user access behavior information comprises user information for accessing the embedded applications;

when a recommendation request of a first user is received, user information of at least one second user associated with the first user is obtained, wherein the first user is a user of the application;

determining at least one embedded application according to user access behavior information of the plurality of embedded applications and user information of the at least one second user;

recommending the at least one embedded application to the first user.

In one aspect, an application recommendation apparatus is provided, the apparatus including:

the system comprises an acquisition module, a link address acquisition module and a link address generation module, wherein the acquisition module is used for acquiring at least one recommendation card of an embedded application of a first user when receiving a first display instruction, wherein the first user is a current login user of an application client, and one recommendation card is associated with one link address;

The display module is used for displaying a target function interface in the application client according to the received first display instruction, wherein the target function interface comprises a plurality of application aggregation display options and at least one recommendation card of the embedded application of the first user, and one application aggregation display option is used for aggregating and displaying application information of the embedded application with a type of association relation with the first user;

and the display module is also used for displaying an embedded application interface corresponding to the target recommendation card based on the link address associated with the target recommendation card in the application client when receiving a second display instruction, wherein the target recommendation card is the recommendation card corresponding to the second display instruction.

the system comprises an acquisition module, a recommendation module and a storage module, wherein the acquisition module is used for acquiring user access behavior information of at least one second user associated with a first user when receiving a recommendation request of the first user, wherein the user access behavior information is used for representing access behaviors of the user to at least one embedded application;

the determining module is used for determining at least one embedded application according to the user access behavior information of the at least one second user;

And the recommending module is used for recommending the at least one embedded application to the first user.

In one aspect, an electronic device is provided that includes a processor and a memory having at least one instruction stored therein that is loaded and executed by the processor to perform operations as performed by the application recommendation method described above.

In a possible implementation manner, the electronic device may be provided as a server to execute the following application recommendation method: acquiring user access behavior information of a plurality of embedded applications of an application, wherein the user access behavior information comprises user information for accessing the embedded applications; when a recommendation request of a first user is received, user information of at least one second user associated with the first user is obtained, wherein the first user is a user of the application; determining at least one embedded application according to user access behavior information of the plurality of embedded applications and user information of the at least one second user; recommending the at least one embedded application to the first user.

In a possible implementation manner, the electronic device may be provided as a terminal to execute the following application recommendation method: when a first display instruction is received, acquiring a recommended card of at least one embedded application of a first user, wherein the first user is a current login user of an application client, and one recommended card is associated with one link address; displaying a target function interface in the application client according to the received first display instruction, wherein the target function interface comprises a plurality of application aggregation display options and at least one recommendation card of an embedded application of the first user, and one application aggregation display option is used for aggregating and displaying application information of the embedded application with a type of association relation with the first user; and when a second display instruction is received, displaying an embedded application interface corresponding to the target recommendation card based on the link address associated with the target recommendation card in the application client.

In one aspect, a computer-readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement operations performed by an application recommendation method as described above is provided.

According to the technical scheme provided by the embodiment of the invention, the embedded application associated with the user and the entry capable of recommending the embedded application are provided on the application client through the interface display mode, a direct channel is provided for the use and recommendation of the embedded application, the embedded application can be found and used by the user through an active recommendation mode, and meanwhile, a channel capable of directly reaching a certain page in the embedded application is provided, so that the user can directly enter the page of interest through the recommendation, and the propagation rate of the embedded application is improved.

Drawings

FIG. 1 is a schematic diagram of an implementation environment of an application recommendation method according to an embodiment of the present invention;

FIG. 2 is a flowchart of an application recommendation method according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a target function interface provided by an embodiment of the present invention;

FIG. 4 is a schematic illustration showing a graphic type card according to an embodiment of the present invention;

FIG. 5 is a schematic illustration of a display of a recommended card of a first multimedia type, for example a video application;

FIG. 6 is a schematic illustration of a display of a recommended card of a second multimedia type, for example a video application;

FIG. 7 is a schematic illustration of a display of a recommended card of a second multimedia type, for example an audio application;

FIG. 8 is a schematic display of a recommended card for a commodity-type card, for example, a shopping application;

FIG. 9 is a schematic representation of a display of a recommended card for an account type card for example of a gaming application;

FIG. 10 is a schematic diagram showing a recommended card of an account type card for information-based applications;

FIG. 11 is a schematic diagram showing access statistics provided by an embodiment of the present invention;

FIG. 12 is a schematic illustration of a display of an embedded application interface according to an embodiment of the present invention;

FIG. 13 is a schematic diagram of a data generation flow provided by an embodiment of the present invention;

fig. 14 is a schematic structural diagram of an application recommendation device according to an embodiment of the present invention;

fig. 15 is a schematic structural diagram of an application recommendation device according to an embodiment of the present invention;

fig. 16 is a schematic structural diagram of a terminal according to an embodiment of the present invention;

fig. 17 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings.

An embedded application, which may also be referred to as an applet, may be installed on an application and may be supported by data provided by a server corresponding to the embedded application, and a user may implement data interaction with the server corresponding to the embedded application by running the embedded application in the application, so as to use functions provided by the embedded application. The embedded application is a new open capability, and a developer can quickly develop an embedded application in the application so as to realize functions provided by various other applications without jumping outside the application in one application. The embedded application can be conveniently acquired and propagated within the application, particularly the social application, and has excellent use experience.

Fig. 1 is a schematic diagram of an implementation environment of an application recommendation method according to an embodiment of the present invention. Referring to fig. 1, the implementation environment includes at least one terminal 101, at least one server 102, and at least one server 103 of an embedded application.

At least one terminal 101 may be installed with an application client that provides services by the server 102, and a user on the terminal 101 may implement functions such as data transmission, message interaction, and the like through the application client.

The at least one server 102 may be any server, such as a social application server or an instant messaging application server, and the server 102 may provide an interface for embedded applications, thereby enabling the provision of embedded applications by application clients.

The at least one server 103 of the embedded application may include servers of various embedded applications, and these servers may respectively provide background services for the embedded application, so that when any application client runs the embedded application, the server may interact with the server of the embedded application, or interact directly with the server of the embedded application, so as to obtain services provided by the embedded application, for example, information services, shopping services, audiovisual services, and so on, which are not limited by the embodiments of the present invention.

Fig. 2 is a flowchart of an application recommendation method provided in an embodiment of the present invention, and referring to fig. 2, the method includes the following steps.

200. The server obtains application data of a plurality of embedded applications of the application.

The application data may include, among other things, the page path of the embedded application and data generated by the page. The acquisition can be periodic, so that the real-time performance of the data can be ensured under the condition of saving server resources, and the data acquisition process can provide convenience for the acquisition of user information and recommendation information of the subsequent embedded application.

In some embodiments, when acquiring application data of multiple embedded applications of an application, this may be done in a manner that crawlers grab and structure the data. Crawler crawling refers to that a server accesses an embedded application by using a plurality of application accounts to traverse pages of the embedded application, records page paths obtained by traversing and data generated by the pages, and transmits the data to the server through structured data. The structured data refers to specific fields in the page of the embedded application, and the specific fields are transmitted to the application client in the form of an interface. For example, the server may pass fields for the type of page (e.g., information class page), title (e.g., living in XX), thumbnail (e.g., source address of article assignment drawing, l), etc. of the captured embedded application to the server.

It should be noted that, for the server, an embedded application queue to be crawled may be maintained, so that serial or concurrent crawling is performed based on the embedded application queue. In one possible implementation, the order of the embedded applications in the embedded application queue may be updated according to the hotness of the embedded application, or according to the priority of the embedded application (set by a technician or based on the accessed condition of the embedded application), or the like, and the embodiments of the present invention are not limited.

Further, after a preset number of users are detected to access a certain embedded application, the embedded application can be added into an embedded application queue, so that the use condition of the embedded application can be guaranteed to be followed in real time.

201. When any user accesses the embedded application in the application, the server acquires the user access behavior information of the user, and stores the user access behavior information of the user into an access behavior information database.

In one embodiment, the user access behavior information further comprises at least one of: user information of any user, access time point, page access depth, access duration, access entrance, geographic location of terminal, and operation type of the embedded application by the user. The user information may include user profile information, such as gender, occupation, age, and the like, the page access depth may include a page access path, the access portal may refer to an access scene, such as access in a multi-person session (access in group chat) or sweep access, and the like, the terminal geographic location may refer to a geographic location of the user's terminal when accessing the embedded application, and the operation type may be used to distinguish between different operations performed by the user on the embedded application, such as a browsing type (corresponding to a browsing operation), a playing type (corresponding to a playing operation), an interaction type (corresponding to an interaction operation such as praise, evaluation, and the like, which are not limited herein. By acquiring the user access behavior information, the access process of the embedded application of the user can be recorded. Further, in the access behavior information database, user access behavior information may be stored, and corresponding to each user, the user access behavior information of the user may be stored in association with the user.

The access user of the embedded application in this step may be a user who has installed the embedded application in the application client, or may be a user who has not installed the embedded application in the application client, so long as the access user is not limited to this embodiment of the present invention.

Optionally, the server may define a storage duration of the stored user access behavior information, for example, if the stored user access behavior information is greater than a preset duration from the current date, the user access behavior information is discarded, so that the server can maintain the newer user access behavior information all the time, and thus, on the basis of saving the storage resource pair, more accurate recommendation can be achieved in a subsequent recommendation process.

In the embodiment of the invention, the access behavior information database can be an offline system, so that the normal operation of the server is not affected.

202. The server determines an event model hit by the acquired user access behavior information based on the event model of at least one dimension every preset time period.

The event model is used to represent event characteristics of access behavior, and the event model includes at least one event element, for example, the event model may define a time period and an operation type (accessed in a time of day, or may be accessed recently), or the event model may define a user gender and an operation type (accessed by a user with a gender of interest), and different event models may define different event elements, which are not shown in one embodiment of the present invention.

As can be seen from the foregoing examples, the event model may have a plurality of different dimensions, specifically referring to the examples in table 1, there are dimensions divided based on time periods, dimensions divided based on user information, and the like, and the dimensions may be any specified time period of the last 1 days, the last 7 days, the last 30 days, and the like, where the last refers to a period of time before the current time with the current time as an end point, and the setting of a specific time span is not limited in the embodiments of the present invention.

TABLE 1

In the embodiment of the invention, when judging whether the user access behavior information hits or not based on the event model of any dimension and the user access behavior information, at least one event element in the event model of the dimension can be correspondingly compared with the information of the corresponding dimension in the user access behavior information, and if the information of the corresponding dimension is consistent with the at least one event element, the user access behavior information is determined to hit the event model.

In one possible implementation manner, taking an event model as an example, when determining whether to hit, an access time point and an operation type in the user access behavior information are acquired, the access time point and the time period are compared, the operation type of the event model is compared with the operation type of the user, and if the access time point is within the time period and the operation type of the event model is the same as the operation type of the user (or the operation type of the user is one of the operation types of the event model), it is determined that the user access behavior information hits the event model. When the time period is limited by a certain numerical range, the comparison success can be determined when the information of the corresponding dimension is in the numerical range, otherwise the comparison fails, and when the information of the corresponding dimension is the same as the point value, the comparison success can be determined when the specific point value class is limited, otherwise the comparison fails. Of course, how to compare may also be implemented in other manners, and the content specifically defined according to the event model may be changed, which is not limited by the embodiment of the present invention.

Of course, this step 202 is actually an optional step, and for the server, after the access behavior information of the user is obtained, it may not determine whether the event model hits, but rather determine whether the event model hits or directly recommend according to the access information of the user when a recommendation request of any user is received, which is not limited in the embodiment of the present invention.

It should be noted that, the judgment of whether to hit may be performed based on a certain period, where the preset period is a period duration, so as to ensure that quick recommendation can be performed after a recommendation request is received, thereby improving recommendation efficiency.

203. And when the terminal receives the first display instruction, sending a recommendation request to the server, wherein the recommendation request is used for acquiring recommendation information of the at least one embedded application.

The application client may have a main interface, and the main interface may provide a display entry of the embedded application, when the terminal detects a triggering operation on the display entry, a first display instruction is triggered, and when the application client receives the first display instruction, the application client may jump to a target function interface, as shown in fig. 3, where the target function interface may include a plurality of application aggregation display options and a recommendation card of at least one embedded application of the first user, and one application aggregation display option is used for aggregating and displaying application information of the embedded application having a type of association relationship with the first user. In order to display the target function interface, recommendation information for at least one embedded application needs to be obtained from the server.

204. When the server receives a recommendation request of a first user, the server acquires user access behavior information of at least one second user associated with the first user.

The user information may be a user identifier, and specifically, the server may obtain, according to a first user identifier carried in the received recommendation request, at least one second user identifier associated with the first user identifier, where the associated may refer to that the second user identifier is included in a user relationship chain of the first user identifier. For example, the association of the first user identifier and the second user identifier may refer to that the first user and the second user are friends, or may refer to that the first user is interested in (a) or subscribed to (a) the second user, which is not limited in the embodiment of the present invention.

205. The server performs deduplication on the embedded application accessed by the at least one second user to obtain the at least one embedded application.

In the process, the user access behavior information of each second user can be traversed to determine which embedded applications are accessed by the second users, an initial table can be obtained in the form of a list, the initial table comprises a plurality of embedded applications accessed by the second users, and because overlapping embedded applications are possible to appear, the initial table can be de-duplicated, so that for the overlapping embedded applications, only one embedded application is reserved, and the embedded applications in the de-duplicated table are used as the embedded applications to be recommended, so that redundancy of data is avoided.

The steps 204-205 are processes of determining at least one embedded application according to the user access behavior information of the at least one second user, and if there is no coincidence, the embedded applications accessed by the plurality of second users may be directly used as the embedded applications to be recommended.

206. The server determines access statistics for the at least one embedded application based on an event model hit by the user access behavior information of the at least one second user.

The hit event model may be stored in the access behavior information database in correspondence with the user access behavior information, for example, the hit event model number is stored, the event model itself is stored, etc., so that when the user access behavior information of the at least one second user is acquired, the event model hit by the user access behavior information of the at least one second user may also be acquired.

In one possible implementation, the process of step 206 may include:

and step 1, the server determines a target second user according to an event model hit by the user access behavior information of the at least one second user, wherein the target second user is the second user hit the same event model for the same embedded application.

Specifically, for an embedded application, it is possible to count the second users that hit the same event model among the second users corresponding to the embedded application. Of course, for an embedded application, there may be multiple second users hitting one event model, and there may be multiple second users that are the same or different and also hitting another event model, i.e., an embedded application may correspond to multiple event models, and groups of users corresponding to the hit event models.

And step 2, the server acquires access statistical information of the same embedded application based on the target second user.

After determining the target second user of each embedded application, access statistics for each embedded application may be obtained based on the hit event model and the target second user of each embedded application.

In one possible implementation, the number of second users hitting the same event model may be counted for each embedded application and based on the number and event model, an access statistic for the embedded application may be generated. For an embedded application, at least one access statistic may be generated. In addition, for the embedded application, if the user access behavior information of a certain second user corresponding to the embedded application hits one event model, and no other second user hits the same event model, one piece of access statistics information of the embedded application may be generated according to the number 1 and the event model.

The process of determining the recommendation reason of the user to be recommended for the first user by hitting the event model can greatly improve the referential of recommendation, and can also arouse the interests of the user from different dimensions, so that the success rate of recommendation can be improved.

207. The server obtains recommendation information of the at least one embedded application based on the at least one embedded application and access statistics of the at least one embedded application.

Wherein, the recommendation information may include the following: recommendation reason information, wherein the recommendation reason information is access statistical information of a second user associated with the first user to the embedded application; at least one piece of recommended content of the embedded application; and, an application name of the embedded application.

For an embedded application, the access statistics may be one of the access statistics obtained in step 206, and when determining which access statistics is added to the recommendation information to recommend, the access statistics may be determined according to the weight of the event model used for generating the access statistics, and the higher the weight is, the greater the likelihood of being selected, for example, the access statistics with the largest weight may be obtained from multiple access statistics according to the weight, which is not limited in particular by the embodiment of the present invention. Specifically, the weights may be set and adjusted in the server by a technician, which is not limited by the embodiment of the present invention.

Wherein, for an embedded application, in order to obtain at least one recommended content of the embedded application, the method may further comprise any of the following steps: (1) The release content acquired by the embedded application in the last acquisition process is acquired from the application data of the embedded application, so that at least one recommended content of the embedded application is the release content acquired by the embedded application in the last acquisition process, and the application data acquired in the acquisition process are stored in a database, so that the influence on the normal operation of a server can be avoided. (2) And acquiring the content published once, which is the shortest in the current time interval, of the embedded application from the application data of the embedded application in real time, so that at least one piece of recommended content of the embedded application is the published content acquired last time from the embedded application, and the real-time performance of the displayed content is ensured. (3) And acquiring release contents accessed by the second user during the embedded application from application behavior data of the second user corresponding to the embedded application, so that at least one piece of recommended content of the embedded application is the release contents accessed by the second user, and the attention content of friends of the first user is provided, thereby increasing the recommendation strength.

In some embodiments, for some embedded applications, the server may not have captured the application data of the embedded application, and therefore, the server may acquire the link address of the application description page of the embedded application, so that the first user may access the application description page through the link address, where the recommended card may be displayed as shown in fig. 9 and 10.

Of course, the recommendation information may also include application related information, such as an application icon, which is not limited in the embodiment of the present invention.

In addition, in order to display on the terminal, in step 207, the embedded applications may be further ranked to determine the display order on the terminal, for example, in the plurality of embedded applications to be recommended, the ranking may be performed according to the heat of each embedded application or the second user number corresponding to each embedded application, so that the display may be performed according to the ranking when the display is performed on the application client, so as to achieve the purpose of improving the recommendation accuracy.

208. The server transmits recommendation information of the at least one embedded application to the terminal of the first user.

209. The terminal generates a recommendation card of the at least one embedded application of the first user according to the recommendation information of the at least one embedded application of the first user and a preset card form, wherein one recommendation card is associated with one link address.

After receiving the recommendation information of the at least one embedded application, the terminal can generate a recommendation card of the at least one embedded application of the first user according to various information in the recommendation information of the at least one embedded application of the first user and a preset card form. The recommendation information includes a link address associated with the recommendation card, where the link address may correspond to any one of a content detail page, a multimedia content, a multimedia detail page, an item detail page, and an application introduction page, and a specific link address is an address corresponding to which page, and may be determined based on recommendation content delivered by an embedded application to be recommended.

The preset card form may be used to define a specific display mode of the card, for example, in which area of the card the access statistics of the second user are displayed, in which area the recommended content is displayed, and so on.

Optionally, the preset card form may correspond to a card type, and the card type may be different according to application types of the embedded applications, that is, when the recommended card is generated, the recommended card of the at least one embedded application may be generated according to the application type of the at least one embedded application, the recommendation information, and the preset card form of the card type corresponding to each application type, where the card type of the recommended card corresponds to the application type of the embedded application, so as to adapt to specific features of different embedded applications, and achieve maximization of the recommendation effect.

Optionally, the preset card form may correspond to a card type, and the card type may be different according to the recommendation content types in the recommendation information of the embedded application, that is, when the recommendation card is generated, the recommendation card of the at least one embedded application may be generated according to the recommendation content types in the recommendation information of the at least one embedded application and the preset card form of the card type corresponding to each recommendation content type, where the card type of the recommendation card corresponds to the recommendation content type in the recommendation information of the embedded application, so as to adapt to specific features of different embedded applications, and achieve maximization of the recommendation effect.

Based on different embedded applications or different recommended content types, different types of recommended cards can be generated, wherein the card types can comprise graphic-text type cards, first multimedia type cards, second multimedia type cards, commodity type cards, account type cards and the like, and various card types are respectively described below:

(1) The graphic type card may correspond to an informative application or an informative page, as shown in fig. 4.

(2) The first multimedia type card and the second multimedia type card may each correspond to a multimedia application. The multimedia application may be a video application or an audio application, both differing in that the first multimedia type card is generated based on a link address of the multimedia content, and the second multimedia type card is generated based on a multimedia detail page of the multimedia content. When such recommended cards are generated, the link address contained in the recommendation information may be analyzed to determine which multimedia type card is generated. Fig. 5 to 7 show, in which fig. 5 is a schematic view showing a recommended card of a first multimedia type, for example, a video application, fig. 6 is a schematic view showing a recommended card of a second multimedia type, for example, a video application, and fig. 7 is a schematic view showing a recommended card of a second multimedia type, for example, an audio application.

(3) The merchandise type card may correspond to a shopping application as shown in fig. 8.

(4) The account type card may correspond to any one of applications, such as a game application, etc., as shown in fig. 9 and 10.

210. And the terminal displays a target function interface in the application client according to the received first display instruction, wherein the target function interface comprises a plurality of application aggregation display options and at least one recommendation card of the embedded application of the first user.

In one possible implementation, the plurality of application aggregation display options includes a first application aggregation display option, a second application aggregation display option, and a third application aggregation display option; the first application aggregation display option is used for aggregating and displaying application information of the embedded application downloaded by the first user; the second application aggregation display option is used for aggregating and displaying application information of the embedded application which is not downloaded by the first user but is used; the third application aggregation display option is for aggregate displaying application information for the embedded application determined based on the geographic location of the application client. Referring to fig. 3, the first application aggregation display option may be "my applet" in fig. 3, the second application aggregation display option may be "applet recently used", and the third application aggregation display option may be "applet nearby".

The recommendation card of any one of the recommendation cards of the at least one embedded application of the first user includes:

recommendation reason information, wherein the recommendation reason information is access statistical information of a second user associated with the first user to the embedded application;

at least one piece of recommended content of the embedded application;

application name of the embedded application.

Still taking fig. 3 as an example, the recommended card 300 includes a recommended reason information display area 301, a recommended content display area 302, and an application name display area 303, which are respectively used to display corresponding information.

In some embodiments, the access statistics of the second user to the embedded application may be different according to different dimensions adopted when aggregating, and may specifically be referred to as the example of table 1, and may include the following:

in one possible implementation, the access statistics include the number of second users that accessed the embedded application, as shown in fig. 4-7.

Further, the number of the second users accessing the embedded application may be the number of users accessing the embedded application in a certain time span, as shown in table 1, so that the real-time performance of recommendation may be improved.

In one possible implementation, the access statistics include the number of second users that interacted with the embedded application, as shown in FIG. 9. The interactive operation can reflect some feedback of the user to the embedded application, such as praise, comment and the like, so that the access statistical information based on the interactive operation has higher reference provided for the user, thereby improving the probability of successful recommendation.

In one possible implementation, the access statistics include the number of second users that have performed any type of operation with the embedded application, as shown in FIG. 8. The specific use condition of the embedded application, such as reading, watching or hearing, etc., of the user can be reflected by performing certain operation, so that the access statistical information based on the operation has higher referential property for the user, thereby improving the success possibility of recommendation and effectively informing the user what specific function is provided by the embedded application.

In one possible implementation, the access statistics include the number of second users who accessed the embedded application and the persistent access condition, as shown in fig. 11. The continuous access condition can be that access is continuously performed for a plurality of times within a certain period of time, and by taking the information as access statistical information, the preference of friends for the embedded application can be displayed, the reference provided for users is higher, and therefore the possibility of successful recommendation can be improved.

In one possible implementation, the access statistics include the number of second users that have used any of the services of the embedded application, as shown in FIG. 8. For an embedded application providing a certain kind of special service, whether the user uses the service provided by the embedded application is a standard for measuring the popularity or reliability of the embedded application, so that the access statistical information of whether the user uses the service is higher in reference to the possibility of providing the user, thereby improving the success probability of recommendation and effectively informing the user what the specific service provided by the embedded application is.

The different access statistical information expression modes can describe the accessed condition of the embedded application from different dimensions, and can distinguish content and service by distinguishing and refining access to interactive operation, operation type, service use and the like so as to improve the accuracy of recommendation.

Of course, the access statistics information is specific to what kind of information, and the embodiment of the present invention is not limited.

The at least one recommended content of the embedded application may be a content published once, that is, a content published last time, of the embedded application with the shortest current time interval, so as to ensure real-time performance of recommendation. Of course, the at least one recommended content of the embedded application may be a post content acquired from the embedded application last time, for example, a post content acquired from the embedded application during the last crawling process by the server, and may also be a post content accessed by the second user, for example, a browsed page, a played video, a purchased commodity, and so on.

211. And when a second display instruction is received, the terminal displays an embedded application interface corresponding to a target recommendation card in the application client based on a link address associated with the target recommendation card, wherein the target recommendation card is a recommendation card corresponding to the second display instruction.

The second display instruction can be triggered by the triggering operation of the user on any recommended card on the target function interface, and the target recommended card selected by the user is determined according to the second display instruction, so that the user jumps from the target function interface to the embedded application interface corresponding to the target recommended card for display based on the link address associated with the target recommended card.

Since the content linked by the link address corresponding to the different card types may be different in type, different processes may be performed after being triggered, and several card type-based display processes are provided below by way of example.

(1) And when a second display instruction is received, if the target recommendation card is a graphic-text type card, displaying a content detail page corresponding to the link address in the application client based on the link address associated with the target recommendation card. For example, when the user clicks on a recommended card as in fig. 4, a display interface as in fig. 12 may be displayed in the application client.

(2) And when a second display instruction is received, if the target recommendation card is the first multimedia type card, playing the multimedia content corresponding to the link address in the current page of the application client based on the link address associated with the target recommendation card.

(3) And when a second display instruction is received, if the target recommendation card is a second multimedia type card, displaying a multimedia detail page corresponding to the link address in the application client based on the link address associated with the target recommendation card.

(4) And when a second display instruction is received, if the target recommended card is a commodity type card, displaying a commodity detail page corresponding to the link address in the application client based on the link address associated with the target recommended card.

(5) And when a second display instruction is received, if the target recommended card is an account type card, displaying an application introduction page of the embedded application corresponding to the target recommended card in the application client based on the link address associated with the target recommended card.

It should be noted that in the displaying of the foregoing (1) to (5), most of the page jumps, that is, jumps from the current target function interface to the page in the embedded application, and the displaying process (2) is relatively special, because the link address associated with the target recommendation card is the link address of the multimedia content, the playing of the multimedia content may be directly performed in the target function interface without the jump of the page, specifically, the application client may access the link address according to the multimedia content in the background, and obtain the data of the multimedia content from the link address, so that the playing of the multimedia content is performed based on the native player of the application client and the obtained data.

In some embodiments, for an embedded application interface displayed based on a recommendation card, a processing option, such as a sharing option or a target type file generation option, of the embedded application interface may also be displayed through a specific operation, as shown in fig. 12, where the "sharing to friends" is a sharing option, and may be used for sharing to an application or other applications, and the "generating a poster" option is a target type file generation option, and may generate a target type file based on a certain composition rule and based on the content of the current embedded application interface, so as to store or share.

The technical scheme can be implemented in an application carrying any system type, for example, an IOS system or an Android system, and in a specific implementation, the implementation can be implemented through interaction between an application client and a server, for example, a certain social application client and a background server of the client.

According to the method provided by the embodiment of the invention, the embedded application associated with the user and the entry capable of recommending the embedded application are provided on the application client through the interface display mode, a direct channel is provided for the use and recommendation of the embedded application, the embedded application can be found and used by the user through an active recommendation mode, and meanwhile, a channel capable of directly reaching a certain page in the embedded application is provided, so that the user can directly enter the page of interest through the recommendation, and the propagation rate of the embedded application is improved.

As shown in fig. 13, from the data generation flow of the whole recommendation process, the method can be divided into application information acquisition, user access behavior information acquisition, background aggregation and sequencing, and application client presentation, wherein the application information acquisition can be implemented by the content capturing and structuring data of the crawler system as described in step 200, the acquisition of the user access behavior information can be implemented by an access behavior information database, the access behavior information database can be used for recording the user access behavior information, the record can be stored based on the form of a user relationship chain, further, the method can be further used for analyzing the user access behavior information, and the background aggregation and sequencing can be actually a data statistics and sequencing process. The server aggregates the related access information of the user according to a certain aggregation rule (for example, whether the user hits or not by adopting an event model) and stores the information in an offline system, and finally, the client applies sorting during recommendation to display the recommended cards. In the process, when a user enters a target function interface, a recommendation request is initiated to a server, and the server generates a sequencing result based on all embedded applications and pages used by friends of the user in a last period of time and simultaneously sequences and displays the sequencing result for the client. Through the above process, the user can find and use some good-quality embedded applications that have been used by friends. Meanwhile, the content of the embedded application can be directly consumed, and the floor detail page of the embedded application content is reached.

Since the above-described display of the recommendation card is not based on a mechanism of centralized recommendation, but is based on recommendation for users based on a relationship between users and a content generation form, such recommendation may be referred to as a decentralised recommendation. In the method provided by the embodiment of the invention, a certain application is taken as a platform for bearing the embedded application, and the embedded application used by friends of a user is recommended and displayed in a content mode in a decentralization mode, so that the user can quickly browse and use the embedded application interested by the user, and the efficiency and experience of the user are improved.

Fig. 14 is a schematic structural diagram of an application recommendation device provided in an embodiment of the present invention, referring to fig. 14, the device includes:

the obtaining module 1401 is configured to obtain, when receiving a first display instruction, a recommended card of at least one embedded application of a first user, where the first user is a current login user of an application client, and one recommended card is associated with one link address;

a display module 1402, configured to display, according to the received first display instruction, a target function interface in the application client, where the target function interface includes a plurality of application aggregation display options and a recommendation card of at least one embedded application of the first user, and one application aggregation display option is used to aggregate and display application information of the embedded application having a type of association relationship with the first user;

The display module 1402 is further configured to display, in the application client, an embedded application interface corresponding to a target recommendation card based on a link address associated with the target recommendation card when a second display instruction is received, where the target recommendation card is a recommendation card corresponding to the second display instruction.

In one possible implementation manner, the obtaining module is configured to obtain recommendation information of at least one embedded application of the first user when receiving a first display instruction; and generating a recommendation card of the at least one embedded application of the first user according to the recommendation information of the at least one embedded application of the first user and a preset card form.

In one possible implementation, the recommendation card of any one of the recommendation cards of the at least one embedded application of the first user includes:

at least one piece of recommended content of the embedded application;

application name of the embedded application.

In one possible implementation, the access statistics include a number of second users that accessed the embedded application;

Or alternatively, the first and second heat exchangers may be,

the access statistical information comprises the number of second users who perform interactive operation on the embedded application;

or alternatively, the first and second heat exchangers may be,

the access statistical information comprises the number of second users who access the embedded application and the continuous access condition;

or alternatively, the first and second heat exchangers may be,

the access statistics include the number of second users that have used any of the services of the embedded application.

In one possible implementation, the at least one recommended piece of content of the embedded application is a piece of content published once for which the embedded application has the shortest time interval from the current time;

or at least one piece of recommended content of the embedded application is release content acquired from the embedded application last time;

or, at least one recommended content of the embedded application is release content accessed by the second user.

In one possible implementation, the display module is configured to:

when a second display instruction is received, if the target recommendation card is a graphic-text type card, displaying a content detail page corresponding to a link address based on the link address associated with the target recommendation card;

or alternatively, the first and second heat exchangers may be,

when a second display instruction is received, if the target recommendation card is a first multimedia type card, playing multimedia content corresponding to a link address in a current page of the application client based on the link address associated with the target recommendation card;

Or alternatively, the first and second heat exchangers may be,

when a second display instruction is received, if the target recommendation card is a second multimedia type card, displaying a multimedia detail page corresponding to the link address in the application client based on the link address associated with the target recommendation card;

or alternatively, the first and second heat exchangers may be,

when a second display instruction is received, if the target recommended card is a commodity type card, displaying a commodity detail page corresponding to the link address in the application client based on the link address associated with the target recommended card;

or alternatively, the first and second heat exchangers may be,

and when a second display instruction is received, if the target recommended card is an account type card, displaying an application introduction page of the embedded application corresponding to the target recommended card in the application client based on the link address associated with the target recommended card.

In one possible implementation, the plurality of application aggregation display options includes a first application aggregation display option, a second application aggregation display option, and a third application aggregation display option;

the first application aggregation display option is used for aggregating and displaying application information of the embedded application downloaded by the first user;

The second application aggregation display option is used for aggregating and displaying application information of the embedded application which is not downloaded by the first user but is used;

the third application aggregation display option is used for aggregating and displaying application information of the embedded application determined based on the geographic position of the application client.

Any combination of the above-mentioned optional solutions may be adopted to form an optional embodiment of the present disclosure, which is not described herein in detail.

It should be noted that: in the application recommendation device provided in the above embodiment, only the division of the above functional modules is used for illustration, and in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the application recommendation device and the application recommendation method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the application recommendation device and the application recommendation method are detailed in the method embodiments and are not repeated herein.

Fig. 15 is a schematic structural diagram of an application recommendation device according to an embodiment of the present invention, referring to fig. 15, the device includes:

an obtaining module 1501, configured to obtain, when a recommendation request of a first user is received, user access behavior information of at least one second user associated with the first user, where the user access behavior information is used to represent access behavior of the user to at least one embedded application;

A determining module 1502, configured to determine at least one embedded application according to user access behavior information of the at least one second user;

a recommending module 1503, configured to recommend the at least one embedded application to the first user.

In one possible implementation, the obtaining module is configured to obtain user information of the accessing user when any embedded application is accessed.

In one possible implementation, the user access behavior information further includes at least one of:

user information, access time point, page access depth, access duration, access portal, terminal geographic location, number of accesses, and type of user operation on the embedded application.

In one possible implementation manner, the determining module is configured to determine, according to user access behavior information of the at least one second user, an embedded application that is accessed by the at least one second user; and de-duplicating the embedded application accessed by the at least one second user to obtain the at least one embedded application.

In one possible implementation, the apparatus further includes: and the storage module is used for acquiring the user access behavior information of the user when any user accesses the embedded application in the application, and storing the user access behavior information of the user into the access behavior information database.

In one possible implementation, the apparatus further includes: the event model determining module is used for determining an event model hit by the acquired user access behavior information based on the event model of at least one dimension every preset time period.

In one possible implementation, the recommendation module is configured to:

a determining unit, configured to determine access statistics of the at least one embedded application according to an event model hit by the user access behavior information of the at least one second user;

an obtaining unit, configured to obtain recommendation information of the at least one embedded application based on the at least one embedded application and access statistics information of the at least one embedded application;

triggering the sending module to send the recommendation information of the at least one embedded application to the terminal of the first user.

In one possible implementation manner, the determining unit is configured to determine, according to an event model hit by the user access behavior information of the at least one second user, a target second user, where the target second user is a second user hit on the same event model for the same embedded application; and acquiring access statistical information of the same embedded application based on the target second user.

In the embodiment of the present invention, the electronic device may be provided in a terminal or server form, and fig. 16 is a schematic structural diagram of a terminal provided in the embodiment of the present invention. The terminal 1600 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion picture expert compression standard audio plane 3), an MP4 (Moving Picture Experts Group Audio Layer IV, motion picture expert compression standard audio plane 4) player, a notebook computer, or a desktop computer. Terminal 1600 may also be referred to by other names of user devices, portable terminals, laptop terminals, desktop terminals, etc.

In general, terminal 1600 includes: a processor 1601, and a memory 1602.

Processor 1601 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 1601 may be implemented in at least one hardware form of a DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 1601 may also include a host processor, which is a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit ); a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 1601 may be integrated with a GPU (Graphics Processing Unit, image processor) for use in responsible for rendering and rendering of content to be displayed by the display screen. In some embodiments, the processor 1601 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.

Memory 1602 may include one or more computer-readable storage media, which may be non-transitory. Memory 1602 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 1602 is used to store at least one instruction for execution by processor 1601 to implement the application recommendation method provided by the method embodiments of the present invention.

In some embodiments, terminal 1600 may also optionally include: a peripheral interface 1603, and at least one peripheral. The processor 1601, memory 1602, and peripheral interface 1603 may be connected by bus or signal lines. The individual peripheral devices may be connected to the peripheral device interface 1603 by buses, signal lines, or circuit boards. Specifically, the peripheral device includes: at least one of radio frequency circuitry 1604, a display screen 1605, a camera 1606, audio circuitry 1607, and a power supply 1609.

Peripheral interface 1603 may be used to connect I/O (Input/Output) related at least one peripheral to processor 1601 and memory 1602. In some embodiments, the processor 1601, memory 1602, and peripheral interface 1603 are integrated on the same chip or circuit board; in some other embodiments, either or both of the processor 1601, memory 1602, and peripheral interface 1603 may be implemented on separate chips or circuit boards, which is not limited in this embodiment.

The Radio Frequency circuit 1604 is used for receiving and transmitting RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1604 communicates with a communication network and other communication devices via electromagnetic signals. The radio frequency circuit 1604 converts an electrical signal into an electromagnetic signal for transmission, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1604 includes: antenna systems, RF transceivers, one or more amplifiers, tuners, oscillators, digital signal processors, codec chipsets, subscriber identity module cards, and so forth. The radio frequency circuit 1604 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (Wireless Fidelity ) networks. In some embodiments, the radio frequency circuit 1604 may also include NFC (Near Field Communication ) related circuits, which the present invention is not limited to.

The display screen 1605 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 1605 is a touch display, the display 1605 also has the ability to collect touch signals at or above the surface of the display 1605. The touch signal may be input to the processor 1601 as a control signal for processing. At this point, the display 1605 may also be used to provide virtual buttons and/or virtual keyboards, also referred to as soft buttons and/or soft keyboards. In some embodiments, the display 1605 may be one, providing a front panel of the terminal 1600; in other embodiments, the display 1605 may be at least two, each disposed on a different surface of the terminal 1600 or in a folded configuration; in still other embodiments, the display 1605 may be a flexible display disposed on a curved surface or a folded surface of the terminal 1600. Even more, the display screen 1605 may be arranged in an irregular pattern other than rectangular, i.e., a shaped screen. The display 1605 may be made of LCD (Liquid Crystal Display ), OLED (Organic Light-Emitting Diode) or other materials.

The camera assembly 1606 is used to capture images or video. Optionally, camera assembly 1606 includes a front camera and a rear camera. Typically, the front camera is disposed on the front panel of the terminal and the rear camera is disposed on the rear surface of the terminal. In some embodiments, the at least two rear cameras are any one of a main camera, a depth camera, a wide-angle camera and a tele camera, so as to realize that the main camera and the depth camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize a panoramic shooting and Virtual Reality (VR) shooting function or other fusion shooting functions. In some embodiments, camera assembly 1606 may also include a flash. The flash lamp can be a single-color temperature flash lamp or a double-color temperature flash lamp. The dual-color temperature flash lamp refers to a combination of a warm light flash lamp and a cold light flash lamp, and can be used for light compensation under different color temperatures.

Audio circuitry 1607 may include a microphone and a speaker. The microphone is used for collecting sound waves of users and environments, converting the sound waves into electric signals, and inputting the electric signals to the processor 1601 for processing, or inputting the electric signals to the radio frequency circuit 1604 for voice communication. The microphone may be provided in a plurality of different locations of the terminal 1600 for stereo acquisition or noise reduction purposes. The microphone may also be an array microphone or an omni-directional pickup microphone. The speaker is used to convert electrical signals from the processor 1601 or the radio frequency circuit 1604 into sound waves. The speaker may be a conventional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only the electric signal can be converted into a sound wave audible to humans, but also the electric signal can be converted into a sound wave inaudible to humans for ranging and other purposes. In some embodiments, audio circuitry 1607 may also include a headphone jack.

A power supply 1609 is used to power the various components in the terminal 1600. The power supply 1609 may be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1609 includes a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 1600 also includes one or more sensors 1610. The one or more sensors 1610 include, but are not limited to: acceleration sensor, gyro sensor, pressure sensor optical sensor and proximity sensor.

Those skilled in the art will appreciate that the structure shown in fig. 16 is not limiting and that more or fewer components than shown may be included or certain components may be combined or a different arrangement of components may be employed.

Fig. 17 is a schematic structural diagram of a server according to an embodiment of the present invention, where the server 1700 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 1701 and one or more memories 1702, where at least one instruction is stored in the memories 1702, and the at least one instruction is loaded and executed by the processors 1701 to implement the application recommendation method provided in the foregoing method embodiments. Of course, the server may also have a wired or wireless network interface, a keyboard, an input/output interface, and other components for implementing the functions of the device, which are not described herein.

The embodiment of the invention also provides a computer readable storage medium, in which at least one instruction, at least one section of program, code set or instruction set is stored, the instruction, the program, the code set or the instruction set is loaded and executed by a processor to implement the operations performed by the server or the terminal in the application recommendation method of the above embodiment.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.

Claims

1. An application recommendation method, the method comprising:

when a first display instruction is received, acquiring a recommended card of at least one embedded application of a first user, wherein the first user is a current login user of an application client, one recommended card is associated with a link address, and the link address is a page address corresponding to recommended content of the embedded application; the recommended content comprises release content accessed by a second user in the embedded application, which is acquired from behavior data of the second user corresponding to the embedded application, wherein the second user is a user associated with the first user;

when a second display instruction is received, displaying an embedded application interface corresponding to a target recommendation card based on a link address associated with the target recommendation card in the application client, wherein the target recommendation card is a recommendation card corresponding to the second display instruction;

wherein different ones of the recommended card types correspond to different types of the recommended content; when a second display instruction is received, if the target recommendation card is an image-text type card, displaying a content detail page corresponding to the link address in the application client; when a second display instruction is received, if the target recommended card is a first multimedia type card, playing the multimedia content corresponding to the link address in the current page of the application client; when a second display instruction is received, if the target recommended card is a second multimedia type card, displaying a multimedia detail page corresponding to the link address in the application client; when a second display instruction is received, if the target recommended card is a commodity type card, displaying a commodity detail page corresponding to the link address in the application client; and when a second display instruction is received, if the target recommended card is an account type card, displaying an application introduction page of the embedded application corresponding to the target recommended card in the application client.

2. The method of claim 1, wherein the obtaining a recommended card for the at least one embedded application for the first user when the first display instruction is received comprises:

when a first display instruction is received, acquiring recommendation information of at least one embedded application of the first user;

and generating a recommendation card of the at least one embedded application of the first user according to the recommendation information of the at least one embedded application of the first user and a preset card form.

3. The method of claim 1, wherein any one of the recommendation cards for the first user's at least one embedded application comprises:

at least one piece of recommended content of the embedded application;

application name of the embedded application.

4. The method of claim 3, wherein the step of,

the access statistics include a number of second users having accessed the embedded application;

or alternatively, the first and second heat exchangers may be,

Or alternatively, the first and second heat exchangers may be,

or alternatively, the first and second heat exchangers may be,

5. An application recommendation method, the method comprising:

when a recommendation request of a first user is received, user access behavior information of at least one second user associated with the first user is obtained, wherein the user access behavior information is used for representing access behaviors of the user to at least one embedded application;

determining at least one embedded application according to the user access behavior information of the at least one second user;

recommending the at least one embedded application to the first user, wherein each embedded application corresponds to a recommended card, the recommended card is associated with a link address, and the link address is a page address corresponding to recommended content of the embedded application; the recommended content comprises release content accessed by a second user in the embedded application, wherein the release content is acquired from behavior data of the second user corresponding to the embedded application, and different types of recommended cards correspond to different types of recommended content; when an application client receives a second display instruction and displays the recommended content, if a target recommended card is an image-text type card, displaying a content detail page corresponding to the link address, wherein the target recommended card is a recommended card corresponding to the second display instruction; if the target recommendation card is a first multimedia type card, playing the multimedia content corresponding to the link address in the current page of the application client; if the target recommendation card is a second multimedia type card, displaying a multimedia detail page corresponding to the link address in the application client; if the target recommended card is a commodity type card, displaying a commodity detail page corresponding to the link address in the application client; and if the target recommended card is an account type card, displaying an application introduction page of the embedded application corresponding to the target recommended card in the application client.

6. The method of claim 5, wherein determining at least one embedded application based on user access behavior information of the at least one second user comprises:

determining the embedded application accessed by the at least one second user according to the user access behavior information of the at least one second user;

and de-duplicating the embedded application accessed by the at least one second user to obtain the at least one embedded application.

7. The method of claim 6, wherein the method further comprises:

when any user accesses the embedded application in the application, the user access behavior information of the user is acquired, and the user access behavior information of the user is stored in an access behavior information database.

8. The method of claim 6, wherein the method further comprises:

and determining an event model hit by the acquired user access behavior information based on the event model of at least one dimension at preset time intervals.

9. The method of claim 6, wherein the recommending the at least one embedded application to the first user comprises:

Determining access statistics of the at least one embedded application according to an event model hit by the user access behavior information of the at least one second user;

acquiring recommendation information of the at least one embedded application based on the at least one embedded application and access statistics of the at least one embedded application;

and sending the recommendation information of the at least one embedded application to the terminal of the first user.

10. The method of claim 9, wherein determining access statistics for the at least one embedded application based on the event model hit by the user access behavior information of the at least one second user comprises:

determining a target second user according to an event model hit by the user access behavior information of the at least one second user, wherein the target second user is the second user hit the same event model for the same embedded application;

and acquiring access statistical information of the same embedded application based on the target second user.

11. An application recommendation device, the device comprising:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a recommended card of at least one embedded application of a first user when receiving a first display instruction, wherein the first user is a current login user of an application client, one recommended card is associated with a link address, and the link address is a page address corresponding to recommended content of the embedded application; the recommended content comprises release content accessed by a second user in the embedded application, which is acquired from behavior data of the second user corresponding to the embedded application, wherein the second user is a user associated with the first user;

the display module is further used for displaying an embedded application interface corresponding to a target recommendation card based on a link address associated with the target recommendation card in the application client when a second display instruction is received, wherein the target recommendation card is the recommendation card corresponding to the second display instruction;

12. The apparatus of claim 11, wherein the acquisition module is configured to:

13. The apparatus of claim 11, wherein any one of the recommendation cards for the first user's at least one embedded application comprises:

at least one piece of recommended content of the embedded application;

application name of the embedded application.

14. The apparatus of claim 13, wherein the device comprises a plurality of sensors,

or alternatively, the first and second heat exchangers may be,

Or alternatively, the first and second heat exchangers may be,

or alternatively, the first and second heat exchangers may be,

15. An electronic device comprising a processor and a memory having stored therein at least one instruction that is loaded and executed by the processor to implement the operations performed by the application recommendation method as provided in any one of claims 1 to 10.

16. A computer readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement the operations performed by the application recommendation method as provided in any one of claims 1 to 10.