CN112650940A - Recommendation method and device of application program, computer equipment and storage medium - Google Patents
Recommendation method and device of application program, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112650940A CN112650940A CN201910960392.9A CN201910960392A CN112650940A CN 112650940 A CN112650940 A CN 112650940A CN 201910960392 A CN201910960392 A CN 201910960392A CN 112650940 A CN112650940 A CN 112650940A
- Authority
- CN
- China
- Prior art keywords
- users
- application program
- target
- user
- cluster
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001914 filtration Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000012163 sequencing technique Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 8
- 238000009434 installation Methods 0.000 claims description 6
- 239000013585 weight reducing agent Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 12
- 230000008569 process Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a recommendation method and device of an application program, computer equipment and a storage medium, wherein the method comprises the following steps: receiving a recommendation request of an application program initiated by a target user; determining a target cluster corresponding to a target user, wherein the target cluster is obtained by clustering the conditions of all users using application programs; and performing collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm to determine a recommendation result of the application program. The method determines the recommendation result by determining the target cluster corresponding to the target user after clustering processing and then performing collaborative filtering on the target user and the user in the target cluster. As the similar users are clustered into the cluster according to the clustering result of the users, and the users in the cluster are subjected to collaborative filtering, all data do not need to be calculated, the calculation performance is improved, and the precision ratio can be ensured.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a recommendation method and device of an application program, computer equipment and a storage medium.
Background
With the rapid development of internet technology, how to select a suitable APPlication program (APP for short) from a large number of APPlication programs (applications) needs an effective set of recommendation technical solutions. The application program may be application software on a computer side, or may be application software on a mobile terminal such as a mobile phone.
With the higher informatization degree of the whole society, people need to learn to read other people from big data, and people need to be taught to understand people from the big data, so that a plurality of application program personalized recommendation schemes appear on the market. At present, ETL (abbreviation of english Extract-Transform-Load) is generally directly performed on feature data, and is used to describe a process of extracting (Extract), converting (Transform), loading (Load) the data from a source end to a destination end, and a model or a related algorithm (open source algorithm library such as mahout or spark mllb) is used to implement collaborative filtering, so as to achieve personalized recommendation for APP.
However, in the recommendation schemes of the inventor, calculation is usually performed based on all data, when the amount of users is large, the amount of data for performing recommendation calculation is large, after the user inputs a recommendation request, the output delay of a recommendation result is large, and the user experience is poor.
Disclosure of Invention
The invention provides a recommendation method and device of an application program, computer equipment and a storage medium, and aims to solve the problems of high cost and high time delay caused by the fact that recommendation calculation needs to be carried out based on all data in the prior art.
In one aspect of the present invention, a recommendation method for an application program is provided, including: receiving a recommendation request of an application program initiated by a target user; determining a target cluster corresponding to the target user, wherein the target cluster is obtained by clustering the conditions of all users using application programs; and performing collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm to determine a recommendation result of the application program.
Optionally, the cooperatively filtering the target user and other users in the target cluster based on a preset cooperative filtering algorithm to determine a recommendation result of the application program includes: calculating the similarity between the target user and other users in the target cluster, wherein the similarity represents the similarity of application programs used between the users; and sequencing the application programs corresponding to the recommendation request based on the similarity to obtain the recommendation result of the application programs.
Optionally, calculating the similarity between the target user and other users in the target cluster includes:
determining all the application programs installed by the users in the target cluster, and constructing a matrix of the users and the application programs, wherein the matrix is used for representing the corresponding relation between the users and the installed application programs;
and calculating the similarity between the matrix of the target user and the matrixes of other users in the target cluster, and taking the similarity as the similarity between the target user and the other users in the target cluster.
Optionally, after receiving a recommendation request of an application initiated by a target user, the method further includes:
determining an application program corresponding to the recommendation request;
and increasing weight or reducing weight to part of the determined application programs by using a preset strong rule, wherein the weight is applied to the recommendation sequencing of the application programs.
Optionally, the strong rules include: and intervening the recommendation result of the application program based on the time for updating or installing the application program by the user, and/or performing weight reduction processing on the super application program, wherein the super application program refers to the application program with the installation amount reaching a preset threshold value.
Optionally, determining the target cluster corresponding to the target user includes:
and matching the target user with a user cluster obtained by pre-clustering to obtain a target cluster where the target user is located.
Optionally, determining the target cluster corresponding to the target user includes:
acquiring user data of all users using the application program;
clustering all users based on the user data by using a preset clustering algorithm to obtain a plurality of clusters;
and determining the cluster where the target user is located as the target cluster.
In another aspect of the present invention, an apparatus for recommending an application is provided, including: the receiving module is used for receiving a recommendation request of an application program initiated by a target user; the determining module is used for determining a target cluster corresponding to the target user, wherein the target cluster is obtained by clustering the conditions of all users using the application programs; and the recommendation module is used for performing collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm to determine a recommendation result of the application program.
Optionally, the recommendation module comprises: the calculating unit is used for calculating the similarity between the target user and other users in the target cluster, and the similarity represents the similarity of application programs used between the users; and the sequencing unit is used for sequencing the application programs corresponding to the recommendation requests based on the similarity to obtain the recommendation results of the application programs.
Optionally, the computing unit comprises: the determining subunit is used for determining the application programs installed by all the users in the target cluster and constructing a matrix of the users and the application programs, wherein the matrix is used for representing the corresponding relation between the users and the installed application programs; and the calculating subunit is used for calculating the similarity between the matrix of the target user and the matrices of other users in the target cluster, and taking the similarity as the similarity between the target user and other users in the target cluster.
Optionally, the recommendation device further comprises: the program determining module is used for determining an application program corresponding to a recommendation request after receiving the recommendation request of the application program initiated by a target user; and the intervention module is used for increasing weight or reducing weight to part of the determined application programs by using a preset strong rule, wherein the weight is acted on the recommendation sequencing of the application programs.
Optionally, the strong rules include: and intervening the recommendation result of the application program based on the time for updating or installing the application program by the user, and/or performing weight reduction processing on the super application program, wherein the super application program refers to the application program with the installation amount reaching a preset threshold value.
Optionally, the determining module is specifically configured to match the target user with a user cluster obtained by clustering in advance, so as to obtain a target cluster where the target user is located.
Optionally, the determining module includes:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring user data of all users using application programs;
the clustering unit is used for clustering all users based on the user data by utilizing a preset clustering algorithm to obtain a plurality of clusters;
and the cluster determining unit is used for determining the cluster where the target user is located as the target cluster.
In another aspect of the present invention, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In another aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, characterized in that: which when executed by a processor implements the steps of the above-described method.
According to the embodiment of the invention, after the recommendation request of the target user is received, the recommendation result is determined by determining the target cluster corresponding to the target user after clustering processing and then performing collaborative filtering on the user in the target cluster and the target user. As the similar users are clustered into the cluster according to the clustering result of the users, and the users in the cluster are subjected to collaborative filtering, all data do not need to be calculated, the calculation performance is improved, and the precision ratio can be ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart of a recommendation method for an application program according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an apparatus for recommending an application according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The embodiment of the invention provides a recommendation method of an application program, which can be applied to all software or websites recommended by the application program, such as application stores and other scenes. As shown in fig. 1, the method includes:
step S101, receiving a recommendation request of an application program initiated by a target user.
The target user is a user who inquires about the application program, and can be identified through user information logged in by the target user, for example, after the user logs in the application store, the user inputs related information in the search bar and clicks an inquiry key to complete a process of sending a recommendation request. The application store background can determine the target user by identifying the user information when the user logs in. The recommendation request carries keywords and user information of the application program to be queried. For example, when a user needs to install a browser, a keyword such as "browser" may be entered in the search bar.
Step S102, determining a target cluster corresponding to the target user, wherein the target cluster is obtained by clustering the conditions of all users using the application program.
In the embodiment of the invention, the users are clustered to obtain a plurality of clusters, and the target clusters corresponding to the target users are determined to be subjected to subsequent collaborative filtering processing.
Optionally, as an optional implementation manner, the determining the target cluster corresponding to the target user in this embodiment includes: acquiring user data of all users using the application program; clustering all users based on the user data by using a preset clustering algorithm to obtain a plurality of clusters; and determining the cluster where the target user is located as the target cluster.
The user data comprises characteristic data and historical behavior data, wherein the characteristic data can comprise the age, occupation, academic calendar, region, sex, hobby and the like of the user; the historical behavior data may include: APP browsed by the user, use duration, use period and the like. After the user data is obtained, clustering processing is carried out on the user by using a clustering algorithm to obtain a plurality of clusters, and labeling is carried out. The classification of the clustering process is unknown and is mainly determined according to user data, so that the result can better reflect the classification of the user. The Clustering Algorithm used in the embodiment of the present invention may be an AP Clustering Algorithm (Affinity mapping Clustering Algorithm).
The latest category between the current user and the target user can be determined by clustering the users by acquiring the user data, and the recommendation accuracy can be improved.
As an optional implementation manner, in the embodiment of the present invention, determining the target cluster corresponding to the target user includes: and matching the target user with a user cluster obtained by pre-clustering to obtain a target cluster where the target user is located.
In this embodiment, the users are clustered based on the characteristic data of the users in advance to obtain a plurality of user clusters, and each user cluster in the plurality of user clusters corresponds to a category of users. After receiving the recommendation request, a target user may be determined based on the user information in the request, and then a user cluster in which the target user is located is queried from a plurality of user clusters, thereby determining the target cluster. In the embodiment of the invention, because the calculation amount of the clustering process of the user cluster is large, and the characteristic data of the user can be acquired in advance, the condition that clustering processing is not needed when real-time recommendation is carried out can be avoided by a pre-clustering mode, only the pre-clustering result needs to be inquired, and then the target cluster corresponding to the user is determined, so that the performance overhead can be further reduced, and the calculation amount is reduced.
And step S103, performing collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm, and determining a recommendation result of the application program.
And cooperatively filtering and analyzing the user interests, finding out similar (interested) users of the specified user in the user group, and integrating the evaluation of the similar users on certain information to form preference degree prediction of the specified user on the information by the system. In the embodiment of the invention, for the users in the target cluster, personalized recommendation is carried out on the target users through a collaborative filtering algorithm.
According to the embodiment of the invention, after the recommendation request of the target user is received, the recommendation result is determined by determining the target cluster corresponding to the target user after clustering processing and then performing collaborative filtering on the user in the target cluster and the target user. As the similar users are clustered into the cluster according to the clustering result of the users, and the users in the cluster are subjected to collaborative filtering, all data do not need to be calculated, the calculation performance is improved, and the precision ratio can be ensured.
As an optional implementation manner, for step S103, performing collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm to determine a recommendation result of an application program, where the method includes: calculating the similarity between the target user and other users in the target cluster, wherein the similarity represents the similarity of application programs used between the users; and sequencing the application programs corresponding to the recommendation request based on the similarity to obtain the recommendation result of the application programs.
In the embodiment of the invention, users in the same cluster are classified by a clustering algorithm, and certain similarity exists among the users, but the user data used in clustering contains some characteristic data, and the similarity exists only objectively among the users, and the measure of the similarity among the users cannot be clarified. In this embodiment, the similarity between the target user and the users in other same clusters is calculated, and the similarity mainly represents the similarity of the users in using the application program. The similarity is calculated based on the application program used by the user and parameters such as the time length and the time interval of using the application program through an algorithm.
And after the similarity is obtained through calculation, sequencing all the application programs, and taking the sequencing result as a recommendation result. The corresponding applications may be sorted according to the similarity value of the users, for example, four users A, B, C, D, the corresponding applications are Y1, Y2, Y3, and Y4, and the similarity is from big to small B, C, D, A, so the recommendation results are Y2, Y3, Y4, and Y1. If the same application exists, the merge is performed.
In another alternative embodiment, when one user uses multiple applications, for example, four users A, B, C, D, all of which are Y1, Y2, Y3, Y4, Y5, and Y6 (one user may use multiple applications, where user a corresponds to Y1 and Y2, user B corresponds to Y3 and Y4, user C corresponds to Y5, and user D corresponds to Y6). Calculating the ranking value of each application program, wherein the calculation formula is as follows: similarity of user, weight of application. For example, the weights corresponding to the applications Y1, Y2, Y3, Y4, Y5 and Y6 are Y1, Y2, Y3, Y4, Y5 and Y6 in sequence, the similarity of the four users A, B, C, D is A, B, C, D in sequence, the ranking values of the 6 applications are AY1, AY2, BY3, BY4, CY5 and DY6 in sequence, and then the applications are ranked according to the computed ranking values.
Further optionally, for the foregoing embodiment, calculating the similarity between the target user and the other users in the target cluster includes: determining all the application programs installed by the users in the target cluster, and constructing a matrix of the users and the application programs, wherein the matrix is used for representing the corresponding relation between the users and the installed application programs; and calculating the similarity between the matrix of the target user and the matrixes of other users in the target cluster, and taking the similarity as the similarity between the target user and the other users in the target cluster.
In the embodiment of the invention, the users are classified by judging whether the application program is installed or not, a user-APP matrix is constructed, and then the similarity of the users is determined by calculating the corresponding proof similarity of the users, so that the personalized recommendation is carried out based on the collaborative filtering of the users.
In the embodiment of the invention, in the recommending process, a strong rule intervention mode is further set to optimize and adjust the recommending result so as to improve the recommending accuracy, reduce errors and improve the user experience.
Specifically, after receiving a recommendation request of an application program initiated by a target user, the embodiment of the present invention further includes: determining an application program corresponding to the recommendation request; and increasing weight or reducing weight to part of the determined application programs by using a preset strong rule, wherein the weight is applied to the recommendation sequencing of the application programs.
Wherein the strong rules include: and intervening the recommendation result of the application program based on the time for updating or installing the application program by the user, and/or performing weight reduction processing on the super application program, wherein the super application program refers to the application program with the installation amount reaching a preset threshold value.
In the embodiment of the invention, the interference on the analyzed factors influencing the recommendation result is mainly performed by weighting or weight reduction on part of the application programs, for example, for some super APPs, the super APPs themselves have huge user quantity and installation quantity, which can cause some new excellent APPs not to have any advantages.
In summary, the embodiment of the invention can achieve the following technical effects:
interest tracking is timely: and considering factors such as the time for installing or updating the APP by the user, the super APP and the like, and using the factors as strong rules to intervene the recommendation result, so that the user experience is better.
The performance is high: the users are clustered firstly, and then the similarity of the users is calculated based on the clustered results, so that the calculation amount can be greatly reduced, and the user experience is improved.
The precision ratio is high: when the user similarity is calculated, similar users are solved according to the clustering result, the precision ratio is improved, and the user experience is good.
An embodiment of the present invention further provides an apparatus for recommending an application, where the apparatus may be configured to execute the recommendation method according to the foregoing embodiment of the present invention, as shown in fig. 2, and the apparatus includes: a receiving module 100, a determining module 200 and a recommending module 300.
The receiving module 100 is configured to receive a recommendation request of an application initiated by a target user.
A determining module 200, configured to determine a target cluster corresponding to the target user, where the target cluster is obtained by clustering conditions of all users using an application program.
And the recommending module 300 is configured to perform collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm, and determine a recommending result of the application program.
According to the embodiment of the invention, after the recommendation request of the target user is received, the recommendation result is determined by determining the target cluster corresponding to the target user after clustering processing and then performing collaborative filtering on the user in the target cluster and the target user. As the similar users are clustered into the cluster according to the clustering result of the users, and the users in the cluster are subjected to collaborative filtering, all data do not need to be calculated, the calculation performance is improved, and the precision ratio can be ensured.
Optionally, the recommendation module 300 comprises: the calculating unit is used for calculating the similarity between the target user and other users in the target cluster, and the similarity represents the similarity of application programs used between the users; and the sequencing unit is used for sequencing the application programs corresponding to the recommendation requests based on the similarity to obtain the recommendation results of the application programs.
Optionally, the computing unit comprises: the determining subunit is used for determining the application programs installed by all the users in the target cluster and constructing a matrix of the users and the application programs, wherein the matrix is used for representing the corresponding relation between the users and the installed application programs; and the calculating subunit is used for calculating the similarity between the matrix of the target user and the matrices of other users in the target cluster, and taking the similarity as the similarity between the target user and other users in the target cluster.
Optionally, the recommendation device further comprises: the program determining module is used for determining an application program corresponding to a recommendation request after receiving the recommendation request of the application program initiated by a target user; and the intervention module is used for increasing weight or reducing weight to part of the determined application programs by using a preset strong rule, wherein the weight is acted on the recommendation sequencing of the application programs.
Optionally, the strong rules include: and intervening the recommendation result of the application program based on the time for updating or installing the application program by the user, and/or performing weight reduction processing on the super application program, wherein the super application program refers to the application program with the installation amount reaching a preset threshold value.
Optionally, the determining module 200 is specifically configured to match the target user with a user cluster obtained by clustering in advance, so as to obtain a target cluster where the target user is located.
Optionally, the determining module 200 includes:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring user data of all users using application programs;
the clustering unit is used for clustering all users based on the user data by utilizing a preset clustering algorithm to obtain a plurality of clusters;
and the cluster determining unit is used for determining the cluster where the target user is located as the target cluster.
For specific description, reference is made to the above method embodiments, which are not described herein again.
The present embodiment also provides a computer device, such as a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server or a server cluster composed of multiple servers) capable of executing programs. The computer device 20 of the present embodiment includes at least, but is not limited to: a memory 21, a processor 22, which may be communicatively coupled to each other via a system bus, as shown in FIG. 3. It is noted that fig. 3 only shows the computer device 20 with components 21-22, but it is to be understood that not all shown components are required to be implemented, and that more or fewer components may be implemented instead.
In the present embodiment, the memory 21 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 20, such as a hard disk or a memory of the computer device 20. In other embodiments, the memory 21 may also be an external storage device of the computer device 20, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device 20. Of course, the memory 21 may also include both internal and external storage devices of the computer device 20. In this embodiment, the memory 21 is generally used for storing an operating system installed in the computer device 20 and various types of application software, such as program codes of the recommendation device of the application program described in the embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 20. In this embodiment, the processor 22 is configured to execute the program code stored in the memory 21 or process data, for example, execute a recommendation device of an application program, so as to implement the recommendation method of the application program of the embodiment.
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an APP application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of the embodiment is used for storing a recommendation device of an application program, and when being executed by a processor, the recommendation device of the embodiment realizes the recommendation method of the application program of the embodiment.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications of this invention are intended to be covered by the present application.
Claims (10)
1. A recommendation method for an application program, comprising:
receiving a recommendation request of an application program initiated by a target user;
determining a target cluster corresponding to the target user, wherein the target cluster is obtained by clustering the conditions of all users using application programs;
and performing collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm to determine a recommendation result of the application program.
2. The method for recommending an application program according to claim 1, wherein the determining the recommendation result of the application program by cooperatively filtering the target user and other users in the target cluster based on a preset cooperative filtering algorithm comprises:
calculating the similarity between the target user and other users in the target cluster, wherein the similarity represents the similarity of application programs used between the users;
and sequencing the application programs corresponding to the recommendation request based on the similarity to obtain the recommendation result of the application programs.
3. The method for recommending an application program according to claim 2, wherein calculating the similarity between the target user and other users in the target cluster comprises:
determining all the application programs installed by the users in the target cluster, and constructing a matrix of the users and the application programs, wherein the matrix is used for representing the corresponding relation between the users and the installed application programs;
and calculating the similarity between the matrix of the target user and the matrixes of other users in the target cluster, and taking the similarity as the similarity between the target user and the other users in the target cluster.
4. The method for recommending application programs according to claim 1, further comprising, after receiving a recommendation request for an application program initiated by a target user:
determining an application program corresponding to the recommendation request;
and increasing weight or reducing weight to part of the determined application programs by using a preset strong rule, wherein the weight is applied to the recommendation sequencing of the application programs.
5. The method according to claim 4, wherein the strong rule comprises: and intervening the recommendation result of the application program based on the time for updating or installing the application program by the user, and/or performing weight reduction processing on the super application program, wherein the super application program refers to the application program with the installation amount reaching a preset threshold value.
6. The method for recommending an application program according to claim 1, wherein determining the target cluster corresponding to the target user comprises:
and matching the target user with a user cluster obtained by pre-clustering to obtain a target cluster where the target user is located.
7. The method for recommending an application program according to claim 1, wherein determining the target cluster corresponding to the target user comprises:
acquiring user data of all users using the application program;
clustering all users based on the user data by using a preset clustering algorithm to obtain a plurality of clusters;
and determining the cluster where the target user is located as the target cluster.
8. An apparatus for recommending an application program, comprising:
the receiving module is used for receiving a recommendation request of an application program initiated by a target user;
the determining module is used for determining a target cluster corresponding to the target user, wherein the target cluster is obtained by clustering the conditions of all users using the application programs;
and the recommendation module is used for performing collaborative filtering on the target user and other users in the target cluster based on a preset collaborative filtering algorithm to determine a recommendation result of the application program.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program when executed by a processor implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910960392.9A CN112650940A (en) | 2019-10-10 | 2019-10-10 | Recommendation method and device of application program, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910960392.9A CN112650940A (en) | 2019-10-10 | 2019-10-10 | Recommendation method and device of application program, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112650940A true CN112650940A (en) | 2021-04-13 |
Family
ID=75342841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910960392.9A Pending CN112650940A (en) | 2019-10-10 | 2019-10-10 | Recommendation method and device of application program, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112650940A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113806637A (en) * | 2021-09-23 | 2021-12-17 | 湖北天天数链技术有限公司 | User classification method and device and item recommendation method and device |
| CN114268836A (en) * | 2021-11-16 | 2022-04-01 | 上海视九信息科技有限公司 | Cold start recommendation method and system for television applet |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104750807A (en) * | 2015-03-25 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Application recommending method and device |
| CN104991914A (en) * | 2015-06-23 | 2015-10-21 | 腾讯科技（深圳）有限公司 | Application recommendation method and server |
| CN105653655A (en) * | 2015-12-25 | 2016-06-08 | Tcl集团股份有限公司 | Application pushing method and device |
| CN105912550A (en) * | 2015-12-15 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Method and device for information recommendation of mobile terminal |
| CN105975537A (en) * | 2016-04-29 | 2016-09-28 | 乐视控股（北京）有限公司 | Sorting method and device of application program |
| CN106548255A (en) * | 2016-11-24 | 2017-03-29 | 山东浪潮云服务信息科技有限公司 | A kind of Method of Commodity Recommendation based on mass users behavior |
| CN106776859A (en) * | 2016-11-28 | 2017-05-31 | 南京华苏科技有限公司 | Mobile solution App commending systems based on user preference |
| CN107977445A (en) * | 2017-12-11 | 2018-05-01 | 北京麒麟合盛网络技术有限公司 | Application program recommends method and device |
| CN109190023A (en) * | 2018-08-15 | 2019-01-11 | 深圳信息职业技术学院 | The method, apparatus and terminal device of Collaborative Recommendation |
-
2019
- 2019-10-10 CN CN201910960392.9A patent/CN112650940A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104750807A (en) * | 2015-03-25 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Application recommending method and device |
| CN104991914A (en) * | 2015-06-23 | 2015-10-21 | 腾讯科技（深圳）有限公司 | Application recommendation method and server |
| CN105912550A (en) * | 2015-12-15 | 2016-08-31 | 乐视网信息技术（北京）股份有限公司 | Method and device for information recommendation of mobile terminal |
| CN105653655A (en) * | 2015-12-25 | 2016-06-08 | Tcl集团股份有限公司 | Application pushing method and device |
| CN105975537A (en) * | 2016-04-29 | 2016-09-28 | 乐视控股（北京）有限公司 | Sorting method and device of application program |
| CN106548255A (en) * | 2016-11-24 | 2017-03-29 | 山东浪潮云服务信息科技有限公司 | A kind of Method of Commodity Recommendation based on mass users behavior |
| CN106776859A (en) * | 2016-11-28 | 2017-05-31 | 南京华苏科技有限公司 | Mobile solution App commending systems based on user preference |
| CN107977445A (en) * | 2017-12-11 | 2018-05-01 | 北京麒麟合盛网络技术有限公司 | Application program recommends method and device |
| CN109190023A (en) * | 2018-08-15 | 2019-01-11 | 深圳信息职业技术学院 | The method, apparatus and terminal device of Collaborative Recommendation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113806637A (en) * | 2021-09-23 | 2021-12-17 | 湖北天天数链技术有限公司 | User classification method and device and item recommendation method and device |
| CN114268836A (en) * | 2021-11-16 | 2022-04-01 | 上海视九信息科技有限公司 | Cold start recommendation method and system for television applet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110427368B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110866181B (en) | Resource recommendation method, device and storage medium | |
| CN108270842B (en) | Method, system and server for pushing rights and interests task | |
| WO2018192496A1 (en) | Trend information generation method and device, storage medium and electronic device | |
| TWI677828B (en) | Business customization device, method, and computer readable storage media based on data source | |
| CN111144937A (en) | Advertisement material determination method, device, equipment and storage medium | |
| US20120124030A1 (en) | Methods and Systems For Pathing Analysis | |
| CN110781372B (en) | Method and device for optimizing website, computer equipment and storage medium | |
| CN111371858A (en) | Group control equipment identification method, device, medium and electronic equipment | |
| WO2019061664A1 (en) | Electronic device, user's internet surfing data-based product recommendation method, and storage medium | |
| WO2022105496A1 (en) | Intelligent follow-up contact method and apparatus, and electronic device and readable storage medium | |
| CN112650940A (en) | Recommendation method and device of application program, computer equipment and storage medium | |
| CN113127482B (en) | Data quality analysis method, device, computer equipment and storage medium | |
| CN113220657A (en) | Data processing method and device and computer equipment | |
| CN112328592A (en) | Data storage method, electronic device and computer readable storage medium | |
| CN112104505A (en) | Application recommendation method and device, server and computer-readable storage medium | |
| CN110389817B (en) | Scheduling method, device and computer readable medium of multi-cloud system | |
| CN113157198A (en) | Method, apparatus and computer program product for managing a cache | |
| CN112650946B (en) | Product information recommendation method, device, system and storage medium | |
| CN112148880A (en) | Customer service dialogue corpus clustering method, system, equipment and storage medium | |
| CN110781404A (en) | Friend relationship chain matching method, system, computer equipment and readable storage medium | |
| KR102372996B1 (en) | Method, apparatus and program for user identification through browser fingerprinting | |
| JP6957761B2 (en) | Context adaptive scan | |
| CN112491939A (en) | Multimedia resource scheduling method and system | |
| CN112016017A (en) | Method and device for determining characteristic data |
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 |