CN111191143A - Application recommendation method and device - Google Patents
Application recommendation method and device Download PDFInfo
- Publication number
- CN111191143A CN111191143A CN201910647590.XA CN201910647590A CN111191143A CN 111191143 A CN111191143 A CN 111191143A CN 201910647590 A CN201910647590 A CN 201910647590A CN 111191143 A CN111191143 A CN 111191143A
- Authority
- CN
- China
- Prior art keywords
- application
- user
- recommended
- associated user
- target user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000011156 evaluation Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 20
- 230000003993 interaction Effects 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000006855 networking Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000001960 triggered effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 239000003999 initiator Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides an application recommendation method and device. The method comprises the following steps: acquiring the intimacy between a target user and an associated user thereof; determining the interest degree of the associated user for the application to be recommended according to the feature data of the associated user; determining a recommendation index of the application to be recommended for the associated user according to the intimacy between the target user and the associated user and the interestingness of the associated user in the application to be recommended; recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user. The technical scheme of the embodiment of the application can realize efficient recommendation of the application.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to an application recommendation method, an application recommendation apparatus, a terminal device, and a computer-readable storage medium.
Background
At present, applications suitable for terminal devices (such as smart phones, tablet computers, personal computers, or the like) are increasing, and in order to enable applications in which a user is interested to accurately reach the user and expand the user area of the applications, it is necessary to recommend the applications to more users.
In the existing implementation, in order to reduce interference of application recommendation on a user, generally, experience invitation of an application to be recommended is sent to friends of the user, so that popularization of the application to be recommended is achieved according to mutual propagation between the user and the friends of the user, but the number of the friends of the user is often large, whether the application to be recommended can be accurately recommended to the friends with high possibility of accepting the experience invitation is determined, and the recommendation efficiency of the application to be recommended is determined.
Disclosure of Invention
In order to accurately recommend an application to be recommended to a user with a high acceptance degree, embodiments of the application provide an application recommendation method, an application recommendation device, a terminal device, and a computer-readable storage medium, so as to improve recommendation efficiency of the application to be recommended.
Wherein, the technical scheme who this application adopted does:
an application recommendation method comprising: acquiring the intimacy between a target user and an associated user thereof; determining the interest degree of the associated user for the application to be recommended according to the feature data of the associated user; determining a recommendation index of the application to be recommended for the associated user according to the intimacy between the target user and the associated user and the interestingness of the associated user in the application to be recommended; recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user.
An application recommendation apparatus comprising: the intimacy acquiring module is used for acquiring intimacy between the target user and the associated user; the interest degree acquisition module is used for determining the interest degree of the associated user for the application to be recommended according to the characteristic data of the associated user; a recommendation index obtaining module, configured to determine, according to the intimacy between the target user and the associated user and the interest degree of the associated user in the application to be recommended, a recommendation index of the application to be recommended for the associated user; and the application recommending module is used for recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user.
A terminal device comprising a processor and a memory, said memory having stored thereon computer readable instructions which, when executed by said processor, implement an application recommendation method as described above.
A computer readable storage medium having stored thereon computer readable instructions which, when executed by a processor of a computer, cause the computer to execute an application recommendation method as described above.
In the technical scheme, the intimacy between the target user and the associated user is obtained, and the interestingness of the associated user for the application to be recommended is determined according to the characteristic data of the associated user, so that the recommendation index of the application to be recommended for the associated user is determined according to the intimacy between the target user and the associated user and the interestingness of the associated user for the application to be recommended. Because the recommendation index of the application to be recommended for the associated user is combined with the affinity between the associated user and the target user and the interestingness of the associated user for the application to be recommended, the recommendation index of the associated user for the application to be recommended can accurately reflect the acceptance degree of the associated user for the application to be recommended, namely the possibility that the associated user accepts the experience invitation initiated by the target user, so that the application to be recommended is recommended to the associated user based on the recommendation index of the application to be recommended for the associated user, and the high-efficiency recommendation of the application to be recommended can be realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 is a schematic illustration of an implementation environment to which embodiments of the present application relate;
FIG. 2 is a hardware block diagram of one embodiment of the intelligent terminal 100 in the implementation environment shown in FIG. 1;
FIG. 3 is a flow diagram illustrating a method of application recommendation in accordance with an exemplary embodiment;
FIG. 4 is a schematic diagram illustrating an application recommendation interface in accordance with an illustrative embodiment;
FIG. 5 is a schematic illustration of an application recommendation interface, according to another exemplary embodiment;
FIG. 6 is a flow diagram for one embodiment of step 210 shown in FIG. 3;
FIG. 7 is a flow diagram illustrating a method of application recommendation in accordance with another illustrative embodiment;
FIG. 8 is a flow diagram illustrating a method of application recommendation in accordance with another illustrative embodiment;
FIG. 9 is a schematic diagram of an application scenario shown in accordance with an illustrative example;
fig. 10 is a block diagram illustrating an application recommendation device according to an example embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
Referring to FIG. 1, FIG. 1 is a schematic diagram of an implementation environment in accordance with the present application. As shown in FIG. 1, the implementation environment is a social network including a plurality of intelligent terminals 100 (only 4 are shown in FIG. 1).
The intelligent terminal 100 is configured to run various applications, for example, the intelligent terminal 100 may run social applications such as WeChat and QQ, game applications such as Royal and joy mahjong, or other types of applications, which are not limited herein.
Wired or wireless network connection is pre-established between the intelligent terminals 100 through communication modules configured by the intelligent terminals, so that communication between the intelligent terminals 100 is realized through the network connection, and users corresponding to the intelligent terminals 100 are associated through the pre-established network connection between the intelligent terminals 100.
The smart terminal 100 may be a smart phone, a tablet computer, a notebook computer, a computer, or any other electronic device that can be operated by the above-mentioned application, which is not limited herein.
In order to expand the user plane that can be reached by the application to be recommended, the application to be recommended is generally propagated among the associated users by means of the association among different users, so that the popularization of the application to be recommended is realized. As shown in fig. 1, users 2 to 4 are all associated users of user 1, for example, users 2 to 4 are all friends of user 1 on a certain social application, and user 1 can recommend an application to be recommended to users 2 to 4, that is, recommend an application to be recommended to an associated user of user 1, by sending an experience invitation of the application to be recommended to users 2 to 4.
In an actual application scenario, the number of other users associated with a certain user is often very large, for example, the number of WeChat friends of an ordinary user can reach several hundreds, and when a user sends an experience invitation of an application to be recommended to an associated user, in order to give consideration to the recommendation will of the user, the application recommendation efficiency, and device resources consumed by application recommendation, only the experience invitation of the application to be recommended is sent to some associated users, rather than the application to be recommended is recommended to all associated users.
If the acceptance degree of the associated user who sends the experience invitation of the application to be recommended to the application to be recommended is higher, the possibility that the associated user uses the application to be recommended is higher, and therefore a better recommendation effect is achieved. Therefore, if the application to be recommended is recommended to the associated user with a high acceptance degree, the recommendation efficiency of the application to be recommended can be greatly improved.
Referring to fig. 2, fig. 2 is a block diagram illustrating an intelligent terminal according to an exemplary embodiment.
It should be noted that the smart terminal 100 is only an example adapted to the present application and should not be considered as providing any limitation to the scope of the application. The smart terminal cannot be interpreted as having to rely on or have to have one or more components of the exemplary mobile terminal 100 shown in fig. 2.
As shown in fig. 2, the mobile terminal 100 includes a memory 101, a memory controller 103, one or more processors 105, a peripheral interface 107, a radio frequency module 109, a positioning module 111, a camera module 113, an audio module 115, a touch screen 117, and a key module 119. These components communicate with each other via one or more communication buses/signal lines 121.
The memory 101 may be used to store computer programs and modules, such as computer readable instructions and modules corresponding to the method and apparatus for controlling a multi-party call in the exemplary embodiment of the present application, and the processor 105 executes the computer readable instructions stored in the memory 101 to perform various functions and data processing, i.e., to complete the application recommendation method.
The memory 101, as a carrier of resource storage, may be random access memory, e.g., high speed random access memory, non-volatile memory, such as one or more magnetic storage devices, flash memory, or other solid state memory. The storage means may be a transient storage or a permanent storage.
The peripheral interface 107 may include at least one wired or wireless network interface, at least one serial-to-parallel conversion interface, at least one input/output interface, at least one USB interface, and the like, for coupling various external input/output devices to the memory 101 and the processor 105, so as to realize communication with various external input/output devices.
The rf module 109 is configured to receive and transmit electromagnetic waves, and achieve interconversion between the electromagnetic waves and electrical signals, so as to communicate with other devices through a communication network. Communication networks include cellular telephone networks, wireless local area networks, or metropolitan area networks, which may use various communication standards, protocols, and technologies.
The positioning module 111 is used for acquiring the current geographic position of the intelligent terminal 100. Examples of the positioning module 111 include, but are not limited to, a global positioning satellite system (GPS), a wireless local area network-based positioning technology, or a mobile communication network-based positioning technology.
The camera module 113 is attached to a camera and is used for taking pictures or videos. The shot pictures or videos can be stored in the memory 101 and also can be sent to an upper computer through the radio frequency module 109.
The touch screen 117 provides an input/output interface between the smart terminal 100 and a user. Specifically, the user may perform an input operation, such as a gesture operation, e.g., clicking, touching, sliding, etc., through the touch screen 117, so that the smart terminal 100 responds to the input operation. The intelligent terminal 100 displays and outputs the output content formed by any one or combination of the text, the picture or the video to the user through the touch screen 117.
The key module 119 includes at least one key for providing an interface for a user to input to the smart terminal 100, and the user can perform different functions by pressing different keys on the smart terminal 100. For example, the sound adjustment key may allow the user to adjust the volume of sound played by the smart terminal 100.
It is to be understood that the configuration shown in fig. 2 is merely exemplary, and the smart terminal 100 may include more or less components than those shown in fig. 2, or different components than those shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
Referring to fig. 3, fig. 3 is a flowchart illustrating an application recommendation method according to an exemplary embodiment. The method is suitable for the intelligent terminal 100 in the implementation environment shown in fig. 1, and the structure of the intelligent terminal 100 can be as shown in fig. 2.
As shown in fig. 3, the application recommendation method may include the steps of:
As described above, in order to enable an application in which a user is interested to accurately reach the user while enlarging the user plane of the application, it is necessary to recommend the application to more users.
For an application to be recommended, the application to be recommended is generally propagated among the associated users by means of the association among different users, so that the application to be recommended is popularized among the associated users.
The target user is used as a recommendation initiator of the application to be recommended, and needs to recommend the application to be recommended to its associated user, for example, an experience invitation of the application to be recommended is sent to the associated user, so as to invite the associated user to experience the application to be recommended.
The associated user of the target user may be a user associated with the target user in one or more other applications run by the intelligent terminal, and it should be understood that the other applications described in the present embodiment are applications other than the application to be recommended.
For example, in the implementation environment shown in fig. 1, if the user 1 is taken as a target user in an application to be recommended, the users 2 to 4 may be not only friend users of the user 1 in some other application, but also friend users of the user 1 on different applications, respectively.
Because the number of associated users associated with the target user is large, the target user usually sends experience invitations of the applications to be recommended to some or a few associated users, and in order to improve the recommendation effect of the applications to be recommended, it is necessary to accurately recommend the applications to be recommended to the associated users with high acceptance for the applications to be recommended. Therefore, how to obtain the acceptance degree of the associated user of the target user on the application to be recommended is a key for accurately and efficiently recommending the application to be recommended.
In this embodiment, the higher the affinity between the target user and the associated user thereof, the higher the possibility that the two users use the same type of application, the higher the possibility that the associated user experiences the application to be recommended after receiving the experience invitation of the application to be recommended sent by the target user, and the higher the willingness of the target user to recommend the application to be recommended to the associated user.
Therefore, in consideration of the fact that the intimacy between the target user and the associated user has a great influence on the recommendation efficiency of the application to be recommended, the intimacy between the target user and the associated user is obtained for the target user to be recommended.
And step 230, determining the interest degree of the associated user for the application to be recommended according to the feature data of the associated user.
The interest degree of the associated user for the application to be recommended refers to the interest degree of the associated user for the application to be recommended.
In view of the fact that the associated user has a higher interest level in the to-be-recommended application, the associated user has a higher possibility of using the to-be-recommended application after receiving the experience invitation of the to-be-recommended application sent by the target user, and therefore in this embodiment, it is necessary to obtain the interest level of the associated user in the to-be-recommended application so as to comprehensively consider the acceptance level of each associated user in the to-be-recommended application in combination with the affinity between the target user and the associated user.
The characteristic data of the associated user may include attribute information of the associated user and usage data of the associated user for other applications. For example, the attribute information of the associated user may include user basic attributes such as gender, age, and region of the associated user, which is not limited herein.
The usage data of the associated user for the other applications may include user social data such as the number of friends of the associated user in the other applications, the number of instant messages sent and received in the other applications, and the like, user fund flow data such as the amount and times of receipt and payment, the amount and times of red packet sending and receiving, and the like of the associated user in the other applications, data such as the name of the user of the associated user in the other applications, the usage time, and application types of the other applications, and the like, which is not limited herein.
Therefore, the feature data of the associated user can be collected from the application run by the intelligent terminal, and the interest degree of the associated user for the application to be recommended can be determined based on the collected feature data of the associated user. For example, if the application to be recommended is a game application and the feature data of the associated user indicates that the associated user has used another game application, the interest level of the associated user in the application to be recommended should be higher, and the possibility that the associated user uses the application to be recommended after receiving the experience invitation of the user to be recommended initiated by the target user is higher.
In an exemplary embodiment, the interest degree of the associated user for the application to be recommended, which is obtained by predicting through the interest degree prediction model, can be obtained by inputting the feature data of the associated user into a pre-trained interest degree prediction model.
In this embodiment, the interest prediction of the application to be recommended by the associated user may be abstracted into a two-class Machine learning problem, so that the interest prediction model may be a common Machine learning model such as a Logistic Regression model (LR), a Support Vector Machine (SVM), a Decision Tree model (DT), and the like, and is not limited in this place.
And step 250, determining a recommendation index of the application to be recommended for the associated user according to the intimacy between the target user and the associated user and the interestingness of the associated user in the application to be recommended.
The recommendation index of the application to be recommended for the associated user corresponds to the possibility that the associated user accepts the experience invitation for using the application to be recommended after receiving the experience invitation, which is initiated by the target user, about the application to be recommended, that is, the acceptance degree of the associated user for the application to be recommended.
As described above, the affinity between the target user and the associated user and the interestingness of the associated user in relation to the application to be recommended both affect the acceptance degree of the associated user in relation to the application to be recommended, and therefore after the affinity between the target user and the associated user and the interestingness of the associated user in relation to the user to be recommended are respectively obtained, the recommendation index of the application to be recommended in relation to the associated user can be determined by combining the obtained affinity and interestingness.
In an exemplary embodiment, the recommendation index of the application to be recommended for the associated user is obtained based on a pre-trained recommendation index prediction model. The recommendation index predicted by the recommendation index prediction model for the associated user can be obtained by inputting the intimacy between the target user and the associated user obtained in step 210 and the interest degree of the associated user for the application to be recommended obtained in step 230 into a pre-trained recommendation index prediction model as feature data.
In this embodiment, the recommendation index prediction model is also a machine learning model trained in advance, and is used for predicting the recommendation index of the application to be recommended for the associated user according to the input feature data. Considering that linear superposition of the intimacy between the target user and the associated user and the interestingness of the associated user to the application to be recommended is not significant, the method is more suitable for performing condition combination on the intimacy between the target user and the associated user and the interestingness of the associated user to the application to be recommended to obtain the recommendation index of the application to be recommended to the associated user. Therefore, in this embodiment, the recommendation index prediction model may be a decision tree model.
The recommendation index obtained by the recommendation index prediction model aiming at the associated user is correspondingly graded according to the acceptance degree of the associated user about the application to be recommended by the recommendation index prediction model, for example, the grading result is usually between 0 and 1, the higher the grading result is, the higher the acceptance degree of the associated user about the application to be recommended is, and otherwise, the lower the acceptance degree of the associated user about the application to be recommended is.
Therefore, for each associated user of the target user, the recommendation index of the application to be recommended for the associated user is determined through the pre-trained recommendation index prediction model, and therefore the acceptance degree of the application to be recommended for each associated user is obtained.
And step 270, recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user.
As described above, according to the recommendation index of the application to be recommended for the associated user, the acceptance degree of each associated user of the target user for the application to be recommended can be definitely known.
Therefore, based on the recommendation index of the application to be recommended for the associated user, the user to be recommended can be recommended to the associated user with a higher acceptance degree, so that accurate recommendation of the application to be recommended is achieved, and a better recommendation effect is achieved.
For example, when the target user selects the associated user, the intelligent terminal may select the associated user with the designated rank as a candidate user to be displayed to the target user according to the recommendation index ranking of the associated user, for example, the associated user with the recommendation index ranking of the top ten is displayed as a candidate user, and the target user may determine the candidate user to be subjected to application recommendation by selecting all or part of the displayed associated users, so that the intelligent terminal triggers the selected candidate user to recommend the application to be recommended to the target user, for example, sends an experience invitation of the application to be recommended to the candidate users. In another embodiment, the selection of the associated users may also be automatically completed by the intelligent terminal, and the intelligent terminal may directly select the associated users with the specified rank according to the recommendation index ranking of the associated users and send experience invitations of the applications to be recommended to the associated users. That is to say, the associated user selected by the intelligent terminal does not need to be displayed to the target user, so that the triggering and selecting operation of the associated user by the target user is omitted, and the recommendation process of the application to be recommended is more intelligent.
It should be noted that the sending of the experience invitation of the application to be recommended to the associated user by the target user may be performed based on other applications for which the association relationship between the target user and the associated user is established. For example, in the implementation environment shown in fig. 1, the user 1 is still used as a target user in the application to be recommended, and if the users 2 to 4 are WeChat friends of the user 1, the user 1 sends WeChat messages to the users 2 to 4 to invite the users 2 to 4 to experience the application to be recommended; if the user 4 is a QQ friend of the user 1, the user 1 sends a corresponding QQ message to the user 4.
Therefore, in the method provided by the embodiment, because the associated users who perform application recommendation have higher acceptance degrees for the applications to be recommended, the associated users have higher possibility of responding to the recommendation of the applications to be recommended initiated by the target user, and thus a good recommendation effect can be achieved.
The recommendation of the target user for the application to be recommended is usually initiated through a triggering recommendation of the target user for the application to be recommended, so in an exemplary embodiment, the application recommendation method should further include, before the step 210, a step of monitoring whether the target user triggers the recommendation of the application to be recommended, and if it is monitored that the user triggers the recommendation of the application to be recommended, it indicates that the target user needs to initiate the recommendation of the application to be recommended, so that the application to be recommended is recommended to an associated user with a higher acceptance degree by executing the content described in the step 210 and 270.
The recommendation monitoring of the application to be recommended is triggered by the target user or not by the intelligent terminal, and the recommendation monitoring can be realized based on the application to be recommended running on the intelligent terminal. For example, in the process that a target user uses an application to be recommended, if it is monitored that the application to be recommended jumps into a set application recommendation interface or an application recommendation button set in the application recommendation interface is triggered, it is monitored that the target user triggers recommendation of the application to be recommended.
In one embodiment, the intelligent terminal monitors that the application to be recommended jumps into an application recommendation interface through the operation of a target user, then the intimacy between the target user and the associated user is obtained, the interest degree of the associated user for the application to be recommended is determined according to the feature data of the associated user, then the recommendation index of the application to be recommended for each associated user is determined according to the intimacy between the target user and the associated user and the interest degree of the associated user for the application to be recommended, and the associated users with the specified rank are selected as candidate users to be displayed to the target user.
As shown in fig. 4, a display area of the application recommendation interface displays a plurality of candidate users for the target user to select, the arrangement order of the candidate users corresponds to the ranking of the recommendation index, the target user can check more candidate users by clicking a "previous page" or "next page" button, and select a candidate user by clicking the display area of the candidate user, or click a selected candidate user again to cancel the selection of the candidate user. In addition, the selected candidate user is correspondingly displayed with a selected identifier, as shown in fig. 5. After the selected candidate user is determined, the target user clicks a 'determination' button, and then the experience invitation of the application to be recommended can be triggered to be sent to the selected candidate user.
Referring to FIG. 6, FIG. 6 is a flow chart of step 210 in one embodiment.
As shown in fig. 6, in an exemplary embodiment, the associated users are friend users of the target user on a specified social application, for example, the associated users are all WeChat friends of the target user, and step 210 may include the following steps:
and step 211, obtaining evaluation values of the target user and the associated user in each social dimension of the specified social application.
In this embodiment, the associated user is a friend user of the target user on the specified social application, and indicates that both the associated user and the target user are users on the specified social application, and therefore, the target user initiates the experience invitation of the application to be recommended to the associated user based on the specified social application. In the recommendation of the application to be recommended, attention should be paid to the intimacy between the target user and the associated user in the specified social application.
The target user and the associated user correspond to different social modes in the specified social application in the various social dimensions of the specified social application. For example, the social dimension of the specified social application may include at least one of a messaging dimension for instant messaging, an interaction dimension on a content sharing platform provided by the specified social application, an article reading dimension, and an application usage dimension.
It should be noted that the sending and receiving dimensions of the instant messaging messages correspond to the instant messaging of the target user and the associated user on the designated social application, for example, if the designated social application is a WeChat, the sending and receiving dimensions of the instant messaging messages correspond to the WeChat messages sent and received between the target user and the associated user.
The interaction dimension on the content sharing platform provided by the specified social application corresponds to content sharing initiated by the associated user participating in the target user in the content sharing platform, the specified social application is still used as WeChat for example, the provided content sharing platform is a friend circle, and the content sharing initiated by the associated user participating in the target user comprises approval of the target user or comment on a dynamic message published by the target user in the friend circle.
The article reading dimension corresponds to article reading by the target user and the associated user on a specified social application, which may be, for example, an article read in a WeChat subscription number.
The application usage dimension then corresponds to the usage of other applications by the target user and associated users that should be associated with the specified social application. Still taking the social platform as an example for wechat, the application used by the target user and the associated user may be a wechat applet or other application that logs in using a wechat account, which is not limited herein.
The evaluation values of the target user and the associated user in each social dimension of the specified social application correspond to the intimacy degree of the target user and the associated user in each social dimension.
In one exemplary embodiment, in the case where the social dimension includes a messaging dimension of the instant messaging message, the evaluation value of the messaging dimension of the instant messaging message may be calculated according to message data sent by the target user to the associated user and the number of messages sent by the associated user to the target user. For example, the calculation formula of the evaluation value of the transceiving dimension of the instant communication message is as follows:
wherein, A represents a target user in the application to be recommended, and B represents a related user of the target user. Adding 1 to the number of instant messages sent by a to B is to avoid a situation where the number of instant messages sent by the target user a to the associated user B is zero. If chat (a to b) is greater than 1, the evaluation value of the transceiving dimension of the instant messaging message can be obtained as 1. If the number of instant messaging messages sent by the associated user B to the target user a is greater than twice the number of instant messaging messages sent by the target user a to the associated user B, the quotient of the two is multiplied by 0.5, so that chat (a to B) takes a value of 1.
If the more replies of the associated user B to the instant messaging message sent by the target user A, the greater the evaluation value of the transceiving dimension of the instant messaging message between the associated user B and the target user A, and the greater the intimacy between the target user A and the associated user B.
In another exemplary embodiment, in a case that the social dimension includes an interaction dimension on a content sharing platform provided by a specific social application, the evaluation value of the interaction dimension may be calculated according to the number of content shares initiated by the target user and the number of content shares initiated by the associated users participating in the target user. For example, the calculation formula of the evaluation value of the interaction dimension on the content sharing platform provided by the specified social application is as follows:
as mentioned above, the reason for adding 1 to the number of content shares initiated by the target user a is to avoid the situation where the number of content shares initiated by the target user a is zero. If the participation degree of the associated user B in the content sharing initiated by the target user A is higher, the higher the evaluation value of the interaction dimension of the associated user B and the target user A on the content sharing platform provided by the specified social application is, the greater the intimacy degree between the target user A and the associated user B is.
In another exemplary embodiment, in a case where the social dimension includes an article reading dimension, the evaluation value of the article reading dimension may be calculated according to the number of articles read by the target user and the number of articles read by the associated user in common with the target user. For example, the calculation formula of the evaluation value of the article reading dimension is as follows:
as described above, the addition of 1 to the number of articles read by the target user a is also to avoid the situation where the number of articles read by the target user a is zero. If the associated user B has a greater proportion of reading the articles read by the target user A, the greater the intimacy between the target user A and the associated user B is.
In yet another exemplary embodiment, in a case where the social dimension includes an application use dimension, the evaluation value of the application use dimension may be calculated according to the number of applications used by the target user and the number of applications used by the associated user and the target user in common. Illustratively, the calculation formula of the evaluation value of the application using the dimension is as follows:
wherein, adding 1 to the number of applications used by the target user a is still to avoid the situation that the number of applications used by the target user a is zero. The greater the proportion of the associated user B using the application used by the target user a, the greater the intimacy between the target user a and the associated user B.
Therefore, the affinity of the target user and the associated user in each social dimension of the designated social application is obtained by obtaining the evaluation values of the target user and the associated user in each social dimension. Based on the affinities of the target user and the associated user in each social dimension, the affinities of the target user and the associated user in the designated social application as a whole can be obtained.
And step 213, calculating the intimacy between the target user and the associated user based on the weight of each social dimension and the evaluation value of the target user and the associated user in each social dimension.
Wherein the weight of each social dimension is configured in advance and is used for representing the importance of each social dimension on the intimacy degree between the target user and the associated user. Therefore, based on the weight of each social dimension, the intimacy degree between the target user and the associated user about the specified social application can be obtained by weighting and calculating the evaluation values of the target user and the associated user in each social dimension.
For example, the calculation formula for calculating the affinity between the target user and the associated user for a given social application is as follows:
close(A to B)＝α*Chat(A to B)+β*Sns(A to B)+γ*Read(A to B)
+δ*App(A to B)
wherein α represents the weight corresponding to the sending and receiving dimension of the instant messaging message, β represents the weight corresponding to the interaction dimension on the content sharing platform provided by the specified social application, γ represents the weight corresponding to the article reading dimension, and δ represents the weight corresponding to the application use dimension.
Therefore, the embodiment considers the intimacy degree between the target user and the associated user in each social dimension of the specified social application, and can accurately obtain the intimacy degree between the target user and the associated user about the specified social application by weighting and calculating the evaluation values of the target user and the associated user in each social dimension respectively.
In a further exemplary embodiment, as shown in fig. 7, the application recommendation method may further include the steps of:
and step 330, training the interestingness prediction model according to the positive sample data and the negative sample data.
In order to obtain an accurate interestingness prediction model, suitable training data needs to be found to train the interestingness prediction model.
In this embodiment, a user of an application to be recommended is taken as a positive sample which is interested in the application to be recommended, and a user of an application which is not to be recommended is taken as a negative sample which is not interested in the application to be recommended, so that user data which is interested in the application to be recommended is obtained as positive sample data, and user data which is not interested in the application to be recommended is obtained as negative sample data.
It should be noted that the user data that is interested or not interested in the application to be recommended refers to the feature data corresponding to the user, and as described above, the feature data may include attribute information of the user and usage data of the user on other applications, which is not described herein again.
Therefore, in the embodiment, the interest degree prediction model is trained by respectively selecting the positive sample data which are interested in the application to be recommended and the negative sample data which are not interested in the application to be recommended, so that the interest degree prediction model obtained by training can accurately predict the interest degree of the associated user for the application to be recommended according to the input feature data of the associated user.
In a further exemplary embodiment, as shown in fig. 8, the application recommendation method may further include the steps of:
Similar to the training of the interestingness prediction model, in order to obtain an accurate recommendation index prediction model, proper training data also needs to be selected to train the recommendation index prediction model.
In this embodiment, historical data of recommending applications to be recommended by a user is collected, the user data of receiving the recommendation of the applications to be recommended is acquired as positive sample data of successful recommending of the applications to be recommended, and the user data of not receiving the recommendation of the applications to be recommended is acquired as negative sample data of failed recommending of the applications to be recommended.
It should be noted that the user data for recommending the application to be recommended should include the interest level of the user in the application to be recommended and the affinity between the user and the user associated with the user.
Therefore, in the embodiment, the recommendation index prediction model is trained by respectively selecting the positive sample data of the application to be recommended which is successfully recommended and the negative sample data of the application to be recommended which is unsuccessfully recommended, so that the recommendation index prediction model obtained by training can be used for training the recommendation index of the application to be recommended, which is specific to the associated user, according to the input intimacy between the target user and the associated user and the interestingness of the associated user in the application to be recommended.
In another embodiment, after recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user, feedback data of application recommendation initiated by the associated user to the target user may be collected, so as to update the training interestingness prediction model and the recommendation index prediction model according to the feedback data, thereby improving the subsequent recommendation effect on the application to be recommended or other applications.
For example, the user data of the application to be recommended used by the associated user to accept the recommendation of the target user may be used as sample data of the interestingness prediction model to update the training interestingness prediction model. The intimacy between the target user and the associated user and the interestingness of the associated user in the application to be recommended can be used as sample data of the recommendation index prediction model to update the training recommendation index prediction model.
The method provided by the present application will be described in detail in a specific application scenario.
As shown in fig. 9, in an exemplary embodiment, an application to be recommended is a game application, and when a target user uses the game application, if the game application is triggered to jump into a game recommendation page or a recommendation button in the game recommendation page is triggered, it is considered to trigger recommendation of the game application, at this time, intimacy between the target user and a WeChat friend of the target user is obtained, and feature data of the WeChat user is input into a trained interestingness prediction model to predict interestingness of the WeChat friend for the game application, and intimacy between the target user and the WeChat friend of the WeChat friend and interestingness of the WeChat friend for the game application are input into the trained recommendation index prediction model to predict recommendation index of the game application for the WeChat friend. And after the recommendation index of the WeChat friend of the target user is obtained, the WeChat friend with the top five ranks is displayed to the target user as a candidate recommendation user according to the ranking of the recommendation index, so that the target user can select the displayed WeChat friend. After the target user selects the WeChat friend to be recommended, the target user sends a WeChat message to the WeChat friend selected by the target user to invite the WeChat friends to experience the game application.
After the experience invitation of the game application is sent to the WeChat friends selected by the target user, the training interestingness prediction model and the recommendation index prediction model are updated by collecting feedback data recommended by the WeChat friends for the game application, so that the updated training interestingness prediction model and the recommendation index prediction model are used for subsequent application recommendation, and the recommendation effect of the subsequent application recommendation is improved.
Referring to fig. 10, fig. 10 is a block diagram illustrating an application recommendation device 500 according to an exemplary embodiment. As shown in fig. 10, in an exemplary embodiment, the application recommendation apparatus 500 may include an affinity obtaining module 510, an interestingness obtaining module 530, a recommendation index obtaining module 550, and an application recommendation module 570.
The affinity obtaining module 510 is configured to obtain, for a target user of an application to be recommended, an affinity between the target user and a user associated with the target user.
The interestingness obtaining module 530 is configured to determine, according to the feature data of the associated user, the interestingness of the associated user for the application to be recommended.
The recommendation index obtaining module 550 is configured to determine a recommendation index of the to-be-recommended application for the associated user according to the intimacy between the target user and the associated user and the interestingness of the to-be-recommended application for the associated user.
The application recommendation module 570 is configured to recommend the application to be recommended to the associated user based on the recommendation index of the application to be recommended for the associated user.
In another exemplary embodiment, the intimacy degree acquisition module 510 includes an evaluation value acquisition unit and an intimacy degree comprehensive acquisition unit.
The evaluation value acquisition unit is used for acquiring evaluation values of the target user and the associated user in each social dimension of the specified social application, wherein each social dimension of the specified social application comprises at least one of a receiving and sending dimension of an instant messaging message, an interaction dimension on a content sharing platform provided by the specified social application, an article reading dimension and an application program using dimension.
The affinity comprehensive acquisition unit is used for calculating the affinity between the target user and the associated user based on the weight of each social dimension and the evaluation value of the target user and the associated user in each social dimension.
In another exemplary embodiment, the interestingness acquisition module 530 includes a feature data collection unit and an interestingness prediction model prediction unit.
The characteristic data collecting unit is used for collecting characteristic data of the associated user, and the characteristic data comprises attribute information of the associated user and usage data of other applications of the associated user
The interestingness prediction model prediction unit is used for inputting the characteristic data into a pre-trained interestingness prediction model to obtain the interestingness of the associated user on the application to be recommended, wherein the interestingness is obtained by predicting through the interestingness prediction model.
In another exemplary embodiment, the recommendation index obtaining module 550 is configured to input the intimacy between the target user and the associated user and the interestingness of the associated user for the application to be recommended as feature data into a recommendation index prediction model trained in advance, and obtain a recommendation index predicted by the recommendation index prediction model for the associated user.
In another exemplary embodiment, the application recommendation device 500 further includes an interestingness sample data acquisition module and an interestingness prediction model training module.
The interest sample data acquisition module is used for generating positive sample data according to the user data which is interested in the application to be recommended and generating negative sample data according to the user data which is not interested in the application to be recommended.
The interestingness prediction model training module is used for training the interestingness prediction model according to the positive sample data and the negative sample data.
In another exemplary embodiment, the application recommendation device 500 further includes an application recommendation sample data acquisition module and a recommendation index prediction model training module.
The application recommendation sample data acquisition module is used for generating positive sample data according to user data successfully recommended to the application to be recommended and generating negative sample data according to user data unsuccessfully recommended to the application to be recommended, wherein the user data comprises the interest degree of the user to the application to be recommended and the intimacy between the user and the associated user.
And the recommendation index prediction model training module is used for training the recommendation index prediction model according to the positive sample data and the negative sample data.
In another exemplary embodiment, the application recommendation module 570 is configured to display the associated users according to the recommendation index rankings of the associated users, and recommend the applications to be recommended to the associated users selected by the target user, or recommend the applications to be recommended to the associated users with specified rankings according to the recommendation index rankings of the associated users.
It should be noted that the apparatus provided in the foregoing embodiment and the method provided in the foregoing embodiment belong to the same concept, and the specific manner in which each module and unit execute operations has been described in detail in the method embodiment, and is not described again here.
In another exemplary embodiment, the present application further provides a terminal device, which includes a processor and a memory, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, implement the application recommendation method as described above.
In another exemplary embodiment, the present application further provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor implements the application recommendation method as described above. The computer-readable storage medium may be included in the terminal device described in the above embodiment, or may exist separately without being assembled into the terminal device.
The above description is only a preferred exemplary embodiment of the present application, and is not intended to limit the embodiments of the present application, and those skilled in the art can easily make various changes and modifications according to the main concept and spirit of the present application, so that the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An application recommendation method, characterized in that the method comprises:
acquiring the intimacy between a target user and an associated user thereof;
determining the interest degree of the associated user for the application to be recommended according to the feature data of the associated user;
determining a recommendation index of the application to be recommended for the associated user according to the intimacy between the target user and the associated user and the interestingness of the associated user in the application to be recommended;
recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user.
2. The method of claim 1, wherein the associated user is a friend user of the target user on a specified social application, and the obtaining of the affinity between the target user and the associated user comprises:
obtaining evaluation values of the target user and the associated user in each social dimension of the specified social application;
and calculating the intimacy between the target user and the associated user based on the weight of each social dimension and the evaluation value of the target user and the associated user in each social dimension.
3. The method of claim 2, wherein the respective social dimensions comprise at least one of:
the social networking service comprises a transceiving dimension of instant messaging messages, an interaction dimension on a content sharing platform provided by the specified social application, an article reading dimension and an application program using dimension.
4. The method of claim 3, wherein the obtaining the evaluation values of the target user and the associated user in the respective social dimensions of the specified social application comprises:
under the condition that the social dimension comprises a receiving and sending dimension of the instant messaging message, calculating an evaluation value of the receiving and sending dimension of the instant messaging message according to the number of messages sent to the associated user by the target user and the number of messages sent to the target user by the associated user;
under the condition that the social dimension comprises an interaction dimension on a content sharing platform provided by the specified social application, calculating an evaluation value corresponding to the interaction dimension according to the number of content sharing initiated by the target user and the number of content sharing initiated by the target user participated by the associated user;
under the condition that the social dimension comprises an article reading dimension, calculating an evaluation value of the article reading dimension according to the number of articles read by the target user and the number of articles read by the associated user and the target user together;
and in the case that the social dimension comprises an application program using dimension, calculating an evaluation value of the application program using dimension according to the number of the application programs used by the target user and the number of the application programs used by the associated user and the target user together.
5. The method according to claim 1, wherein the determining the interest level of the associated user in the application to be recommended according to the feature data of the associated user comprises:
collecting feature data of the associated user, wherein the feature data comprises attribute information of the associated user and usage data of other applications by the associated user;
and inputting the characteristic data into a pre-trained interest degree prediction model to obtain the interest degree of the associated user for the application to be recommended, which is obtained by prediction of the interest degree prediction model.
6. The method of claim 5, further comprising:
generating positive sample data according to the user data which is interested in the application to be recommended, and generating negative sample data according to the user data which is not interested in the application to be recommended;
and training the interestingness prediction model according to the positive sample data and the negative sample data.
7. The method according to claim 1, wherein the determining the recommendation index of the application to be recommended for the associated user according to the intimacy between the target user and the associated user and the interest degree of the associated user in the application to be recommended comprises:
and inputting the intimacy between the target user and the associated user and the interestingness of the associated user to the application to be recommended into a pre-trained recommendation index prediction model by using as characteristic data, and acquiring the recommendation index predicted by the recommendation index prediction model for the associated user.
8. The method of claim 1, wherein prior to said obtaining affinity between the target user and its associated user, the method further comprises:
monitoring whether the target user triggers the recommendation of the application to be recommended or not;
and if so, skipping to execute the step of acquiring the intimacy between the target user and the associated user.
9. The method according to claim 1, wherein recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user comprises: selecting the associated users with the specified rank as candidate users to display to the target user according to the recommendation index ranks of the associated users;
and recommending the application to be recommended to the candidate user selected by the target user trigger.
10. An application recommendation apparatus, characterized in that the apparatus comprises:
the intimacy acquiring module is used for acquiring intimacy between the target user and the associated user;
the interest degree acquisition module is used for determining the interest degree of the associated user for the application to be recommended according to the characteristic data of the associated user;
a recommendation index obtaining module, configured to determine, according to the intimacy between the target user and the associated user and the interest degree of the associated user in the application to be recommended, a recommendation index of the application to be recommended for the associated user;
and the application recommending module is used for recommending the application to be recommended to the associated user based on the recommendation index of the application to be recommended to the associated user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910647590.XA CN111191143B (en) | 2019-07-17 | 2019-07-17 | Application recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910647590.XA CN111191143B (en) | 2019-07-17 | 2019-07-17 | Application recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111191143A true CN111191143A (en) | 2020-05-22 |
| CN111191143B CN111191143B (en) | 2023-10-24 |
Family
ID=70709030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910647590.XA Active CN111191143B (en) | 2019-07-17 | 2019-07-17 | Application recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111191143B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861635A (en) * | 2020-06-17 | 2020-10-30 | 北京邮电大学 | Friend recommendation method, device and equipment for commodity sharing |
| CN111949861A (en) * | 2020-07-14 | 2020-11-17 | 五八有限公司 | Information recommendation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880691A (en) * | 2012-09-19 | 2013-01-16 | 北京航空航天大学深圳研究院 | User closeness-based mixed recommending system and method |
| CN105959365A (en) * | 2016-04-26 | 2016-09-21 | 中国联合网络通信集团有限公司 | Application recommendation method and application recommendation device |
| CN106126537A (en) * | 2016-06-14 | 2016-11-16 | 中国联合网络通信集团有限公司 | Method and device is recommended in a kind of application |
| CN107436914A (en) * | 2017-06-06 | 2017-12-05 | 北京小度信息科技有限公司 | Recommend method and device |
| CN108874821A (en) * | 2017-05-11 | 2018-11-23 | 腾讯科技（深圳）有限公司 | A kind of application recommended method, device and server |
-
2019
- 2019-07-17 CN CN201910647590.XA patent/CN111191143B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880691A (en) * | 2012-09-19 | 2013-01-16 | 北京航空航天大学深圳研究院 | User closeness-based mixed recommending system and method |
| CN105959365A (en) * | 2016-04-26 | 2016-09-21 | 中国联合网络通信集团有限公司 | Application recommendation method and application recommendation device |
| CN106126537A (en) * | 2016-06-14 | 2016-11-16 | 中国联合网络通信集团有限公司 | Method and device is recommended in a kind of application |
| CN108874821A (en) * | 2017-05-11 | 2018-11-23 | 腾讯科技（深圳）有限公司 | A kind of application recommended method, device and server |
| CN107436914A (en) * | 2017-06-06 | 2017-12-05 | 北京小度信息科技有限公司 | Recommend method and device |
Non-Patent Citations (1)
| Title |
|---|
| 吴昊等: "社交网络中的好友推荐方法研究", 《现代图书情报技术》, no. 01, pages 1 - 7 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861635A (en) * | 2020-06-17 | 2020-10-30 | 北京邮电大学 | Friend recommendation method, device and equipment for commodity sharing |
| CN111861635B (en) * | 2020-06-17 | 2022-10-25 | 北京邮电大学 | Friend recommendation method, device and equipment for commodity sharing |
| CN111949861A (en) * | 2020-07-14 | 2020-11-17 | 五八有限公司 | Information recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111191143B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11128582B2 (en) | Emoji recommendation method and apparatus | |
| CN111339327B (en) | Work recommendation method and device, server and storage medium | |
| CN109347722B (en) | Interaction system, method, client and background server | |
| US10868789B2 (en) | Social matching | |
| US20130110992A1 (en) | Electronic device management using interdomain profile-based inferences | |
| CN107995370B (en) | Call control method, device, storage medium and mobile terminal | |
| US10726087B2 (en) | Machine learning system and method to identify and connect like-minded users | |
| CN108875993B (en) | Invitation behavior prediction method and device | |
| US10439974B2 (en) | Sharing of activity metadata via messaging systems | |
| CN113810732B (en) | Live content display method, device, terminal, storage medium and program product | |
| CN112395509A (en) | Information display method, information providing method, apparatus, and computer-readable medium | |
| US20200328907A1 (en) | Method, system, and non-transitory computer-readable record medium for providing multiple group calls in one chatroom | |
| US11765107B2 (en) | Method and system for providing relevance information between users | |
| CN112165390B (en) | Information processing method and device, electronic equipment and computer readable storage medium | |
| CN106255102A (en) | The authentication method of a kind of terminal unit and relevant device | |
| CN111191143B (en) | Application recommendation method and device | |
| CN111090877B (en) | Data generation and acquisition methods, corresponding devices and storage medium | |
| CN110909241A (en) | Information recommendation method, user identification recommendation method, device and equipment | |
| CN105653605A (en) | Method and system for mining network community cheating users as well as electronic equipment | |
| US10924568B1 (en) | Machine learning system for networking | |
| CN111125544A (en) | User recommendation method and device | |
| CN110209924B (en) | Recommendation parameter acquisition method, device, server and storage medium | |
| CN104991973A (en) | Method and apparatus for determining area of interest of users | |
| CN116561735B (en) | Mutual trust authentication method and system based on multiple authentication sources and electronic equipment | |
| CN116911928B (en) | Training method and device of advertisement recommendation model based on creative features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |