CN109040164B - Application recommendation method and device, storage medium and computer equipment - Google Patents
Application recommendation method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN109040164B CN109040164B CN201810486760.6A CN201810486760A CN109040164B CN 109040164 B CN109040164 B CN 109040164B CN 201810486760 A CN201810486760 A CN 201810486760A CN 109040164 B CN109040164 B CN 109040164B
- Authority
- CN
- China
- Prior art keywords
- application
- preference
- recommended
- matrix
- theme
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention provides an application recommendation method, an application recommendation device, a storage medium and computer equipment, wherein the method comprises the following steps: acquiring an application installed by a user, and generating an application set; acquiring an application preference matrix of an application theme corresponding to an application to be recommended; the application theme is a set consisting of a plurality of related applications, and elements in the application preference matrix represent preference values of the theme to the applications; obtaining a preference degree value of the user to the application to be recommended according to the application to be recommended, the application set and the application preference matrix; and recommending the application to the user according to the preference degree value. According to the application recommendation method, when the application is recommended to the user according to the preference degree value of the application, the application which the user is interested in can be recommended, and therefore market competitiveness of products is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an application recommendation method, an application recommendation device, a storage medium and computer equipment.
Background
With the development of internet technology and the increasing demand of people for various application programs, more and more application programs are provided for users by application program operation platforms. However, limited by the amount of memory of the user terminal, the user may not install the application indefinitely, but rather may choose some applications of interest for installation based on preferences.
Therefore, in the operation process of the application store, a high-quality application needs to be recommended to the user to meet the user's preference. However, how to recommend interesting applications to users to provide market competitiveness of products becomes a big problem for application operation.
Disclosure of Invention
The invention provides an application recommendation method, an application recommendation device, a storage medium and computer equipment, which are used for recommending interesting application programs for users and improving the market competitiveness of products.
The present invention provides the following scheme:
an application recommendation method comprising the steps of: acquiring an application installed by a user, and generating an application set; acquiring an application preference matrix of an application theme corresponding to an application to be recommended; the application theme is a set consisting of a plurality of related applications, and elements in the application preference matrix represent preference values of the theme to the applications; obtaining a preference degree value of the user to the application to be recommended according to the application to be recommended, the application set and the application preference matrix; and recommending the application to the user according to the preference degree value.
In one embodiment, the recommending an application to the user according to the preference degree value includes: acquiring preference degree values of all applications to be recommended in an application resource library by a user; sequencing all applications to be recommended from large to small according to the preference degree value of each application to be recommended in the application resource library by a user; and pushing a preset number of applications to be recommended which are ranked in the front to the user.
In one embodiment, obtaining the preference degree value of the user for the application to be recommended according to the application to be recommended, the application set, and the application preference matrix includes: acquiring preference values of the application to be recommended to different topics from the application preference matrix, and generating a topic vector of the application to be recommended; acquiring preference values of each application in the application set to different topics from the application preference matrix, and generating a topic vector corresponding to each application; and obtaining the preference degree value of the user to the application to be recommended according to the theme vector of the application to be recommended, the theme vector corresponding to each application in the application set and the application set.
In one embodiment, the obtaining, according to the theme vector of the application to be recommended, the theme vector corresponding to each application in the application set, and the application set, a preference degree value of the user for the application to be recommended includes: acquiring a preference degree value of the user to the application to be recommended according to the following formula:
wherein the application set of the user u is Su，|SuI represents the number of installed applications in the application set, the application to be recommended is an application a, and the theme vector of the application a is BaJ represents SuIn a topic vector of BjLike (u, a) represents a preference degree value of user u for application a, cos (B)j,Ba) Is to obtain BjAnd BaCosine value of (d).
In one embodiment, the application preference matrix of the application subject corresponding to the application to be recommended is obtained by the following method: acquiring installation application information of a preset number of sample users, and generating an application installation matrix; the installation application information of the sample user comprises installation information of the sample user for installing the application to be recommended; inputting the application installation matrix into a theme preference model to obtain an application preference matrix of an application theme corresponding to the application to be recommended; the theme preference model is used for representing the incidence relation between an application installation matrix and the application preference matrix.
In one embodiment, the theme preference model comprises a theme preference matrix model of the theme preference of the user and an application preference matrix model of the theme preference of the application; inputting the application installation matrix into a theme preference model to obtain an application preference matrix of an application theme corresponding to the application to be recommended, wherein the application preference matrix comprises the following steps: inputting the application installation matrix into a loss function which is constructed in advance according to the theme preference model; and solving the minimum value of the loss function through a preset algorithm to obtain a theme preference matrix corresponding to the theme preference matrix model and an application preference matrix corresponding to the application preference matrix model, and taking the application preference matrix as the application preference matrix of the application theme corresponding to the application to be recommended.
In one embodiment, the predetermined algorithm is a gradient descent method.
An application recommendation apparatus comprising: the generating module is used for acquiring the applications installed by the user and generating an application set; the system comprises a first acquisition module, a second acquisition module and a recommendation module, wherein the first acquisition module is used for acquiring an application preference matrix of an application theme corresponding to an application to be recommended; the application theme is a set consisting of a plurality of related applications, and elements in the application preference matrix represent preference values of the theme to the applications; the second obtaining module is used for obtaining a preference degree value of the user to the application to be recommended according to the application to be recommended, the application set and the application preference matrix; and the recommending module is used for recommending the application to the user according to the preference degree value.
A storage medium having a computer program stored thereon; when being executed by a processor, the computer program realizes the application recommendation method of any one of the above embodiments.
A computer apparatus, comprising: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to perform the application recommendation method according to any of the embodiments described above.
The application recommendation method provided in the above embodiment obtains the application set installed by the user and the application preference matrix of the application theme corresponding to the application to be recommended respectively, and further obtains the preference degree value of the application to be recommended by the user according to the application to be recommended, the application set installed by the user, and the application preference matrix of the application theme. The preference degree of the user to the application can be judged according to the preference degree value of the application, so that the application which the user is interested in can be recommended when the application is recommended to the user according to the preference degree value of the application, and the market competitiveness of application products is improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic diagram of interaction between a server and a client in an embodiment of an application recommendation method provided in the present invention;
FIG. 2 is a flowchart illustrating an embodiment of a method for recommending an application according to the present invention;
FIG. 3 is a flowchart of an embodiment of step S200 provided by the present invention;
FIG. 4 is a flowchart of an embodiment of step S230 provided by the present invention;
FIG. 5 is a flowchart of an embodiment of step S300 provided by the present invention;
FIG. 6 is a flowchart of another embodiment of an application recommendation method according to the present invention;
FIG. 7 is a schematic structural diagram of an embodiment of an application recommendation device according to the present invention;
fig. 8 is a schematic diagram of an embodiment of a computer device structure provided in the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise specified, the singular forms "a", "an", "the" and "the" may include the plural forms as well, and the "first" and "second" used herein are only used to distinguish one technical feature from another and are not intended to limit the order, number, etc. of the technical features. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
According to the application recommendation method, the application recommendation algorithm based on the theme model is provided, each user is supposed to have different preferences for different themes, each theme has different preferences for each application, and the preferences of the users for different applications can be obtained by multiplying the theme preference matrix of the users and the application preference matrix of the themes. The application recommendation method is applied to the application environment as shown in fig. 1.
As shown in fig. 1, the server 100 and the user terminal 300 are located in the same network 200 environment, and the server 100 and the user terminal 300 perform data information interaction through the network 200. The number of servers 100 and user terminals 300 is not limited, and is shown in fig. 1 for illustration only. The user terminal 300 has a client installed therein, and the client is third-party Application software, such as an APP (Application store). A user may perform information interaction with a corresponding server 100 through a client APP in a user terminal 300. The client corresponds to a Server (Server) end and follows the same set of data protocol together, so that the Server end and the client can mutually analyze the data of the other side and provide application recommendation service for users.
The server 100 may be, but is not limited to, a web server, a management server, an application server, a database server, a cloud server, and so on. The user terminal 300 may be, but is not limited to, a smart phone, a Personal Computer (PC), a tablet PC, a Personal Digital Assistant (PDA), a Mobile Internet Device (MID), and the like. The operating system of the user terminal 300 may be, but is not limited to, an Android system, an ios (internet operating system) system, a Windows phone system, a Windows system, and the like.
In an embodiment, as shown in fig. 2, the application recommendation method of the present invention includes the following steps:
s100, acquiring the applications installed by the user, and generating an application set.
In this embodiment, the server acquires applications installed by the user, and generates an application set including the applications installed by the user. Specifically, the server may determine the applications installed by the user by obtaining the application download installation records of the user in the application repository, and generate the corresponding application sets. The server can download the installation record according to the application of the user, and obtain the application installed by the user within a preset time period.
In one embodiment, the server may obtain the number of users who have accessed the application in the repository in the last day, assuming that the number of users here is n. The number of all applications in the resource pool is m.
The matrix y represents a matrix of all user installed application information, and has a size of n × m. Each row represents the installation of an application by one user, each column represents the user installation of each application, 0 represents no installation, 1 represents installation, for example:
s200, acquiring an application preference matrix of an application theme corresponding to an application to be recommended; the application theme is a set consisting of a plurality of related applications, and the elements in the application preference matrix represent preference values of the theme to the applications.
The server obtains an application preference matrix of an application theme corresponding to the application to be recommended. Wherein the application theme is a collection of multiple related applications. Related applications are applications under the same theme. The application preference matrix is represented in the matrix, and each element characterizes a preference value of the application theme for the application. Application preference matrix representation of application topics: and acquiring a preference degree value of the application theme to each application under the theme, and generating an application preference matrix containing a plurality of preference degree values.
In this embodiment, the application to be recommended corresponds to an application theme, and the application preference matrix of the application theme includes a preference degree value of the application theme to the application to be recommended.
In an embodiment, as shown in fig. 3, the application preference matrix of the application subject corresponding to the application to be recommended is obtained through the following steps:
s210, obtaining installation application information of a preset number of sample users, and generating an application installation matrix; the installation application information of the sample user comprises installation information of the sample user for installing the application to be recommended.
In this embodiment, the installation application information includes information of an application installed by the user terminal. The installation application information of the preset number of sample users comprises whether each sample user installs an application in the resource library and which applications in the resource library are installed. The server acquires and records the installation application information of each sample user, specifically acquires the name of the application installed by the user, and determines which application users are not installed in the resource library. Further, the server generates a corresponding application installation matrix according to the installation application information of the sample user. It should be noted that the installation application information of the sample user in this embodiment includes installation information of the sample user in which the application to be recommended is installed.
S230, inputting the application installation matrix into a theme preference model to obtain an application preference matrix of an application theme corresponding to the application to be recommended; the theme preference model is used for representing the incidence relation between an application installation matrix and the application preference matrix.
In this embodiment, the theme preference model is used to characterize an association relationship between an application installation matrix and an application preference matrix. That is, the application installation matrix is input into the theme preference model, and the application preference matrix of the corresponding application theme can be obtained.
In one embodiment, the theme preference model comprises a theme preference matrix model of the theme preference of the user and an application preference matrix model of the theme preference of the application. As shown in fig. 4, step S230 includes:
s231, inputting the application installation matrix into a loss function which is constructed in advance according to the theme preference model.
S233, solving the minimum value of the loss function through a preset algorithm to obtain a theme preference matrix corresponding to the theme preference matrix model and an application preference matrix corresponding to the application preference matrix model, and taking the application preference matrix as the application preference matrix of the application theme corresponding to the application to be recommended.
Wherein, the preset algorithm is a gradient descent method. The theme preference matrix model of the theme preference of the user characterizes different preference degrees of different themes of each user. The application preference matrix model of topic-to-application preferences characterizes different degrees of preference of each topic for each application. The theme preference model can be obtained by multiplying a theme preference matrix model of the theme preference of the user and an application preference matrix model of the theme preference of the application. And solving the minimum value of the loss function by constructing the loss function corresponding to the theme preference model to obtain the theme preference matrix and the application preference matrix. The application preference matrix is an application preference matrix of an application theme corresponding to the application to be recommended.
In the embodiment, the application installation matrix generated according to the installation application information of the sample user is input into the pre-constructed theme preference model, so that the application preference matrix of the application theme corresponding to the application to be recommended can be obtained.
S300, obtaining a preference degree value of the user to the application to be recommended according to the application to be recommended, the application set and the application preference matrix.
In this embodiment, through step S100 and step S200, the server obtains an application to be recommended, an application set formed by applications installed by a user, and an application preference matrix of an application theme corresponding to the application to be recommended. Further, the server can obtain the preference degree value of the application to be recommended by the user according to the three parameters.
In one embodiment, as shown in fig. 5, step S300 includes the following steps:
s310, obtaining preference values of the application to be recommended to different subjects from the application preference matrix, and generating a subject vector of the application to be recommended.
In this embodiment, the application preference matrix is an application preference matrix of an application theme corresponding to the application to be recommended. And the server acquires preference values of the applications to be recommended corresponding to different topics from the application preference matrix. And generating a theme vector of the application to be recommended according to each preference value.
S330, obtaining the preference value of each application in the application set to different themes from the application preference matrix, and generating a theme vector corresponding to each application.
In this embodiment, the application set includes applications installed by the user. Generally, the number of applications that the user has installed is plural. And the server respectively acquires the preference value of each application corresponding to different themes in the application set from the application preference matrix of the application theme, and generates a theme vector corresponding to the application. For example, applications that the user has installed include application a, application B, and application C. The server obtains preference values of different themes corresponding to the application A from the application preference matrix of the application theme, and generates a theme vector a corresponding to the application A. And acquiring preference values of different themes corresponding to the application B from the application preference matrix of the application theme, and generating a theme vector B corresponding to the application B. And acquiring preference values of different themes corresponding to the application C from the application preference matrix of the application theme, and generating a theme vector C corresponding to the application C.
S350, obtaining the preference degree value of the user to the application to be recommended according to the theme vector of the application to be recommended, the theme vector corresponding to each application in the application set and the application set.
In this embodiment, a theme vector of an application to be recommended by a server, a theme vector corresponding to an application installed by a user, and an application set corresponding to an application installed by a user obtain a preference degree value of the application to be recommended by the user. Specifically, the server obtains a preference degree value of the application to be recommended according to the quantity value of all the applications in the application set corresponding to the application installed by the user, the theme vector of the application to be recommended, and the theme vector corresponding to the application installed by the user.
In a specific embodiment, the server obtains the preference degree value of the user to the application to be recommended according to the following formula:
wherein the application set of the user u is Su，|SuI represents the number of installed applications in the application set, the application to be recommended is an application a, and the theme vector of the application a is BaJ represents SuIn a topic vector of BjLike (u, a) represents a preference degree value of user u for application a, cos (B)j,Ba) Is to obtain BjAnd BaCosine value of (d).
And S400, recommending the application to the user according to the preference degree value.
In this embodiment, the server may obtain preference degree values of a plurality of applications in the repository according to steps S100 to S300, and recommend an application to the user according to the preference degree value of each application.
In one embodiment, as shown in fig. 6, step S400 includes the following steps:
s410, acquiring preference degree values of the user to all applications to be recommended in the application resource library.
S430, sorting all the applications to be recommended from large to small according to the preference degree value of the user to each application to be recommended in the application resource library.
S450, pushing a preset number of applications to be recommended, which are ranked in the front, to the user.
In this embodiment, the server may obtain the preference value of each application for the user in the application resource library according to steps S100 to S300, further sort all applications from large to small according to the preference value of the user for each application, and recommend the preset number of applications sorted in the top to the user. The preset number may be 100, or may be other numbers. Or the server obtains the preset number of applications before the highest preference degree value and displays the applications on the terminal screen of the user according to the sequence of the preference degree values from large to small.
The application recommendation method provided in the above embodiment obtains the application set installed by the user and the application preference matrix of the application theme corresponding to the application to be recommended respectively, and further obtains the preference degree value of the application to be recommended by the user according to the application to be recommended, the application set installed by the user, and the application preference matrix of the application theme. The preference degree of the user to the application can be judged according to the preference degree value of the application, so that the application which the user is interested in can be recommended when the application is recommended to the user according to the preference degree value of the application, and the market competitiveness of the product is improved.
The following provides a specific embodiment to explain in detail that the server recommends an application to a user in an application environment as shown in fig. 1 by using the application recommendation method according to the present invention.
Step 1, a server acquires data information of application installed by a user and converts the application data information installed by the user into a real number matrix. The specific process is as follows:
variable definition:
n number of users who visited the application last 1 day
Number of all applications in m resource pool
The matrix y represents a matrix of all user installation application information, the size is n × m, each row represents the installation application condition of one user, each column represents the user installation condition of each application, 0 represents no installation, and 1 represents installation. For example:
and 2, defining a theme preference model.
Theme preference model definition: the theme preference model has the idea that the theme preference model assumes that each user has different preferences for different application themes and each application theme has different preferences for each application, and the preferences of the users for different applications can be obtained by multiplying the theme preference matrix of the users for different application themes by the application preference matrix of the themes for each application. It is assumed that the number k of application themes is preset manually, and is generally 100. The topic preference model is as follows:
Y＝UV
wherein, (1) the matrix Y represents a matrix formed by the preference degree values of the users for different applications.
(2) The matrix U represents a theme preference matrix of the user to the application theme, the size of the matrix is n x k, each row represents the preference degree of one user to different application themes, each column represents the preference degree of one application theme among different users, and the matrix needs to be solved through a model.
(3) The matrix V represents an application preference matrix of each application theme pair and each application, the size of the matrix is k × m, each row represents the preference degree of one application theme to different applications, each column represents the preference of one application between different application themes, and the matrix needs to be solved through a model.
And 3, solving the theme preference matrix and the application preference matrix by constructing a model function. In this embodiment, the topic preference matrix and the application preference matrix are solved by constructing a loss function. The method comprises the following specific steps:
the actual installation situation Y of the user can be obtained in step 1, the predicted installation application situation Y of the user can be calculated through the theme preference model in step 2, and the loss function is defined as follows:
wherein
Solving the U-U by the minimization loss functioni,},V＝{vl,jThe obtained model is obtained.
The model parameters are solved as follows:
solving U-U by gradient descent method for los functioni,},V＝{vl,j}
The gradient descent method is as follows:
step 1: all parameters of the model are uniformly recorded into a set and are not recorded as theta ═ thetaiRandomly giving a set of values between 0 and 1, set to theta(0)The number of initialization iteration steps k is 0
Step 2: iterative computation
Where ρ is used to control convergence rate, 0.01
And 3, step 3: judging whether to converge
If it is not
Then it returns to theta(k+1)Otherwise, go back to step 2 to continue the calculation, where α is a small value, and may be 0.01 · ρ
And 4, step 4: generating application topic vectors
The matrix V ═ { V } can be obtained by the method described abovel,jThe application topic vector is:
Bj＝{v1,,v2,,…,vk,}
and 5: calculating user preference for applications
Setting the application set installed by the user u as SuFor any application a, the topic vector of the application a can be calculated as B by the methodaCalculating the preference degree of the user u to the application a, wherein the formula is as follows:
where like (u, a) represents the preference degree value of user u for application a. cos (B)j,Ba) To solve vector BjAnd vector BaCosine value of (d). | Su | represents that the set of applications is SuThe number of applications in (c).
Step 6: and recommending the application to the user.
For a given user u, calculating like (u, a) for all the applications in the whole library through the formula, and displaying the top 100 applications with the highest preference degree values on a screen of the user according to the sequence of preference degrees from large to small.
The proposal provides an application recommendation algorithm based on an application topic model, and on one hand, the problem that manual recommendation consumes a large amount of labor cost is solved. On the other hand, compared with the traditional recommendation method based on the content, the method can complete application recommendation without labels, and has good effect in practical application.
The invention also provides an application recommendation device. As shown in fig. 7, the application recommendation apparatus includes a generation module 100, a first obtaining module 200, a second obtaining module 300, and a recommendation module 400.
The generating module 100 is configured to obtain applications installed by a user, and generate an application set. In this embodiment, the server acquires applications installed by the user, and generates an application set including the applications installed by the user. Specifically, the server may determine the applications installed by the user by obtaining the application download installation records of the user in the application repository, and generate the corresponding application sets. The server can download the installation record according to the application of the user, and obtain the application installed by the user within a preset time period.
In one embodiment, the server may obtain the number of users who have accessed the application in the repository in the last day, assuming that the number of users here is n. The number of all applications in the resource pool is m.
The matrix y represents a matrix of all user installed application information, and has a size of n × m. Each row represents the installation of an application by one user, each column represents the user installation of each application, 0 represents no installation, 1 represents installation, for example:
the first obtaining module 200 is configured to obtain an application preference matrix of an application theme corresponding to an application to be recommended; the application theme is a set consisting of a plurality of related applications, and the elements in the application preference matrix represent preference values of the theme to the applications. The server obtains an application preference matrix of an application theme corresponding to the application to be recommended. Wherein the application theme is a collection of multiple related applications. Related applications are applications under the same theme. The application preference matrix is represented in the matrix, and each element characterizes a preference value of the application theme for the application. Application preference matrix representation of application topics: and acquiring a preference degree value of the application theme to each application under the theme, and generating an application preference matrix containing a plurality of preference degree values.
In this embodiment, the application to be recommended corresponds to an application theme, and the application preference matrix of the application theme includes a preference degree value of the application theme to the application to be recommended.
The second obtaining module 300 is configured to obtain a preference degree value of the user for the application to be recommended according to the application to be recommended, the application set, and the application preference matrix. In this embodiment, through the generation module 100 and the first obtaining module 200, the server obtains an application to be recommended, an application set formed by applications installed by a user, and an application preference matrix of an application theme corresponding to the application to be recommended. Further, the server can obtain the preference degree value of the application to be recommended by the user according to the three parameters.
The recommending module 400 is configured to recommend an application to the user according to the preference degree value. In this embodiment, the server may obtain preference degree values of a plurality of applications in the repository according to the second obtaining module 300, and recommend an application to the user according to the preference degree value of each application.
In other embodiments, each module in the application recommendation device provided by the present invention is further configured to execute the operation executed in each step in the application recommendation method described in the present invention, and a detailed description thereof is omitted here.
The invention also provides a storage medium. The storage medium having stored thereon a computer program; when being executed by a processor, the computer program realizes the application recommendation method of any one of the above embodiments. The storage medium may be a memory. For example, internal memory or external memory, or both. The memory may comprise read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or random access memory. The external memory may include a hard disk, a floppy disk, a ZIP disk, a usb-disk, a magnetic tape, etc. The storage media disclosed herein include, but are not limited to, these types of memories. The disclosed memory is by way of example only and not by way of limitation.
The invention also provides computer equipment. A computer device comprising: one or more processors; a memory; one or more applications. Wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to perform the application recommendation method of any of the embodiments described above.
Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present invention. The computer device in this embodiment may be a server, a personal computer, and a network device. As shown in fig. 8, the apparatus includes a processor 803, a memory 805, an input unit 807, and a display unit 809. Those skilled in the art will appreciate that the device configuration means shown in fig. 8 do not constitute a limitation of all devices and may include more or less components than those shown, or some components in combination. The memory 805 may be used to store the application program 801 and various functional modules, and the processor 803 executes the application program 801 stored in the memory 805, thereby performing various functional applications of the device and data processing. The memory may be internal or external memory, or include both internal and external memory. The memory may comprise read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or random access memory. The external memory may include a hard disk, a floppy disk, a ZIP disk, a usb-disk, a magnetic tape, etc. The disclosed memory includes, but is not limited to, these types of memory. The disclosed memory is by way of example only and not by way of limitation.
The input unit 807 is used to receive input of signals and keywords input by a user. The input unit 807 may include a touch panel and other input devices. The touch panel can collect touch operations of a user on or near the touch panel (for example, operations of the user on or near the touch panel by using any suitable object or accessory such as a finger, a stylus and the like) and drive the corresponding connecting device according to a preset program; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., play control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like. The display unit 809 may be used to display information input by the user or information provided to the user and various menus of the computer apparatus. The display unit 809 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 803 is a control center of a computer device, connects various parts of the entire computer using various interfaces and lines, and performs various functions and processes data by operating or executing software programs and/or modules stored in the memory 803 and calling data stored in the memory.
In one embodiment, the device includes one or more processors 803, and one or more memories 805, one or more applications 801. Wherein the one or more application programs 801 are stored in the memory 805 and configured to be executed by the one or more processors 803, the one or more application programs 801 configured to perform the application recommendation method described in the above embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the storage medium may include a memory, a magnetic disk, an optical disk, or the like.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
It should be understood that each functional unit in the embodiments of the present invention may be integrated into one processing module, each unit may exist alone physically, or two or more units may be integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (9)
1. An application recommendation method, comprising the steps of:
acquiring an application installed by a user, and generating an application set;
the method comprises the steps of obtaining an application preference matrix of an application theme corresponding to an application to be recommended, wherein the application theme is a set formed by a plurality of related applications, elements in the application preference matrix represent preference values of the theme to the applications, and the application preference matrix of the application theme corresponding to the application to be recommended is obtained through the following modes:
acquiring installation application information of a preset number of sample users, generating an application installation matrix, wherein the installation application information of the sample users comprises installation information of the sample users for installing the applications to be recommended,
inputting the application installation matrix into a theme preference model to obtain an application preference matrix of an application theme corresponding to the application to be recommended, wherein the theme preference model is used for representing the incidence relation between the application installation matrix and the application preference matrix;
obtaining a preference degree value of the user to the application to be recommended according to the application to be recommended, the application set and the application preference matrix;
and recommending the application to the user according to the preference degree value.
2. The application recommendation method according to claim 1, wherein recommending the application to the user according to the preference degree value comprises:
acquiring preference degree values of all applications to be recommended in an application resource library by a user;
sequencing all applications to be recommended from large to small according to the preference degree value of each application to be recommended in the application resource library by a user;
and pushing a preset number of applications to be recommended which are ranked in the front to the user.
3. The method according to claim 1, wherein obtaining the preference degree value of the user for the application to be recommended according to the application to be recommended, the application set, and the application preference matrix comprises:
acquiring preference values of the application to be recommended to different topics from the application preference matrix, and generating a topic vector of the application to be recommended;
acquiring preference values of each application in the application set to different topics from the application preference matrix, and generating a topic vector corresponding to each application;
and obtaining the preference degree value of the user to the application to be recommended according to the theme vector of the application to be recommended, the theme vector corresponding to each application in the application set and the application set.
4. The method according to claim 3, wherein the obtaining the preference degree value of the user for the application to be recommended according to the topic vector of the application to be recommended and the topic vector corresponding to each application in the application set and the application set comprises: acquiring a preference degree value of the user to the application to be recommended according to the following formula:
wherein said set of applications for user u is Su，|SuI represents the number of installed applications in the application set, the application to be recommended is an application a, and the theme vector of the application a is BaJ represents SuIn a topic vector of BjLike (u, a) represents a preference degree value of user u for application a, cos (B)j,Ba) Is to obtain BjAnd BaCosine value of (d).
5. The method of claim 1, wherein the topic preference model comprises a topic preference matrix model of the user's preference for topics and an application preference matrix model of the preference of topics to applications; inputting the application installation matrix into a theme preference model to obtain an application preference matrix of an application theme corresponding to the application to be recommended, wherein the application preference matrix comprises the following steps:
inputting the application installation matrix into a loss function which is constructed in advance according to the theme preference model;
and solving the minimum value of the loss function through a preset algorithm to obtain a theme preference matrix corresponding to the theme preference matrix model and an application preference matrix corresponding to the application preference matrix model, and taking the application preference matrix as the application preference matrix of the application theme corresponding to the application to be recommended.
6. The method of claim 5, wherein the predetermined algorithm is a gradient descent method.
7. An application recommendation device, comprising:
the generating module is used for acquiring the applications installed by the user and generating an application set;
the first obtaining module is used for obtaining an application preference matrix of an application theme corresponding to an application to be recommended, wherein the application theme is a set formed by a plurality of related applications, elements in the application preference matrix represent preference values of the theme to the application, and the application preference matrix of the application theme corresponding to the application to be recommended is obtained through the following modes:
acquiring installation application information of a preset number of sample users, generating an application installation matrix, wherein the installation application information of the sample users comprises installation information of the sample users for installing the applications to be recommended,
inputting the application installation matrix into a theme preference model to obtain an application preference matrix of an application theme corresponding to the application to be recommended, wherein the theme preference model is used for representing the incidence relation between the application installation matrix and the application preference matrix;
the second obtaining module is used for obtaining a preference degree value of the user to the application to be recommended according to the application to be recommended, the application set and the application preference matrix;
and the recommending module is used for recommending the application to the user according to the preference degree value.
8. A storage medium, characterized in that a computer program is stored thereon; the computer program, when executed by a processor, implements the application recommendation method of any of claims 1-6 above.
9. A computer device, comprising:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to perform the application recommendation method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486760.6A CN109040164B (en) | 2018-05-21 | 2018-05-21 | Application recommendation method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486760.6A CN109040164B (en) | 2018-05-21 | 2018-05-21 | Application recommendation method and device, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109040164A CN109040164A (en) | 2018-12-18 |
| CN109040164B true CN109040164B (en) | 2021-11-26 |
Family
ID=64611616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810486760.6A Active CN109040164B (en) | 2018-05-21 | 2018-05-21 | Application recommendation method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040164B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113268655A (en) * | 2020-02-17 | 2021-08-17 | 北京搜狗科技发展有限公司 | Information recommendation method and device and electronic equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844724A (en) * | 2017-02-10 | 2017-06-13 | 广州优视网络科技有限公司 | It is a kind of that the method and apparatus applied to recommend application have been installed based on user |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7953676B2 (en) * | 2007-08-20 | 2011-05-31 | Yahoo! Inc. | Predictive discrete latent factor models for large scale dyadic data |
| CN103425799B (en) * | 2013-09-04 | 2016-06-15 | 北京邮电大学 | Individuation research direction commending system and recommend method based on theme |
| KR101620748B1 (en) * | 2014-12-10 | 2016-05-12 | 한양대학교 산학협력단 | Item recommendation method and apparatus |
| CN105635480B (en) * | 2016-01-19 | 2018-12-21 | 广州优视网络科技有限公司 | A kind of application program recommended method and related device |
| CN107305559A (en) * | 2016-04-21 | 2017-10-31 | 中国移动通信集团广东有限公司 | Method and apparatus are recommended in one kind application |
| CN107103036B (en) * | 2017-03-22 | 2020-05-08 | 广州优视网络科技有限公司 | Method and equipment for acquiring application downloading probability and programmable equipment |
| CN107239993B (en) * | 2017-05-24 | 2020-11-24 | 海南大学 | Matrix decomposition recommendation method and system based on expansion label |
| CN107885852B (en) * | 2017-11-13 | 2021-09-10 | 上海交通大学 | APP recommendation method and system based on APP usage record |
-
2018
- 2018-05-21 CN CN201810486760.6A patent/CN109040164B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844724A (en) * | 2017-02-10 | 2017-06-13 | 广州优视网络科技有限公司 | It is a kind of that the method and apparatus applied to recommend application have been installed based on user |
Non-Patent Citations (1)
| Title |
|---|
| "融合主题模型和协同过滤的多样化移动应用推荐";黄璐等;《软件学报》;20161129;正文2-4章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109040164A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106023015B (en) | Course learning path recommendation method and device | |
| US11216509B2 (en) | Dynamic faceting for personalized search and discovery | |
| AU2016225947B2 (en) | System and method for multimedia document summarization | |
| CN108769125B (en) | Application recommendation method and device, storage medium and computer equipment | |
| CN110020188A (en) | Recommended based on the Global Vector of implicit interactions and profile data | |
| WO2018121700A1 (en) | Method and device for recommending application information based on installed application, terminal device, and storage medium | |
| CN108520034B (en) | Application recommendation method and device and computer equipment | |
| KR20200030252A (en) | Apparatus and method for providing artwork | |
| CN112632403B (en) | Training method, recommendation method, device, equipment and medium for recommendation model | |
| CN108845806B (en) | Applet distributing method, device, server and storage medium | |
| Oberauer et al. | Hierarchical Bayesian measurement models for continuous reproduction of visual features from working memory | |
| CN107729473B (en) | Article recommendation method and device | |
| CN110880136A (en) | Recommendation method, system, equipment and storage medium for matched product | |
| WO2019061664A1 (en) | Electronic device, user's internet surfing data-based product recommendation method, and storage medium | |
| CN109117442B (en) | Application recommendation method and device | |
| CN111275205A (en) | Virtual sample generation method, terminal device and storage medium | |
| CN112135193A (en) | Video recommendation method and device | |
| CN112100221A (en) | Information recommendation method and device, recommendation server and storage medium | |
| Salituro | Learn Grafana 7.0: A beginner's guide to getting well versed in analytics, interactive dashboards, and monitoring | |
| CN116821475A (en) | Video recommendation method and device based on client data and computer equipment | |
| CN107944026A (en) | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation | |
| JP2012150563A (en) | Product recommendation device, method, and program | |
| CN109040164B (en) | Application recommendation method and device, storage medium and computer equipment | |
| CN108319444B (en) | Music drumbeat-based control terminal vibration method, storage device and computer device | |
| CN113626638A (en) | Short video recommendation processing method and device, intelligent terminal and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200424 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510640 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |