CN106682058B

CN106682058B - Application program screening method, device and system

Info

Publication number: CN106682058B
Application number: CN201610643760.3A
Authority: CN
Inventors: 周远远; 吴春成; 邱泰生
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2016-08-08
Filing date: 2016-08-08
Publication date: 2020-11-03
Anticipated expiration: 2036-08-08
Also published as: CN106682058A

Abstract

The invention discloses a method, a device and a system for screening application programs. Wherein, the method comprises the following steps: acquiring a first parameter and a second parameter of the N application programs, wherein the first parameter is a parameter used for representing the loading amount of the application programs, and the second parameter is a parameter used for representing the activity degree of users of the application programs; and screening out the target application program from the N application programs according to the first parameter and the second parameter. The invention solves the technical problem of low accuracy of screening the application program by using a single parameter in the prior art.

Description

Application program screening method, device and system

Technical Field

The invention relates to the field of internet, in particular to a method, a device and a system for screening application programs.

Background

The number of the APP capable of being installed on the terminal is large, and the screening of the growing APP and the declining APP from the massive APP has important value.

In the prior art, growing APP or declining APP are generally obtained by ranking according to the change rate of the loading amount of the APP from high to low. The judgment method has low accuracy. For example, some manufacturers customize APPs, the loading capacity will rise immediately if a new model is introduced, but the APP itself is not necessarily a growth APP.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a screening method, a screening device and a screening system of application programs, which at least solve the technical problem of low accuracy of screening the application programs by using a single parameter in the prior art.

According to an aspect of the embodiments of the present invention, there is provided an application screening method, including: acquiring a first parameter and a second parameter of N application programs, wherein the first parameter is a parameter for representing the loading amount of the application programs, and the second parameter is a parameter for representing the activity degree of users of the application programs; and screening out target application programs from the N application programs according to the first parameters and the second parameters.

According to another aspect of the embodiments of the present invention, there is provided an apparatus for screening an application, including: an acquisition unit configured to acquire a first parameter and a second parameter of N applications, wherein the first parameter is a parameter indicating a mount amount of the application, and the second parameter is a parameter indicating an activity level of a user of the application; and the first screening unit is used for screening the target application program from the N application programs according to the first parameter and the second parameter.

According to another aspect of the embodiments of the present invention, there is provided an application screening system, including: the screening device of the application program.

According to another aspect of the embodiments of the present invention, there is provided an application screening system, including: the terminal is used for reporting the installation condition and the use condition of the N application programs to the server; and the server is in communication connection with the terminal and is used for receiving the installation condition and the use condition of the N application programs reported by the terminal, acquiring first parameters and second parameters of the N application programs according to the installation condition and the use condition, and screening target application programs from the N application programs according to the first parameters and the second parameters, wherein the first parameters are parameters for representing the loading amount of the application programs, and the second parameters are parameters for representing the activity degree of users of the application programs.

The embodiment of the invention uses a plurality of parameters in two aspects of the installation amount (installation amount) and the activity degree (usage amount) as the characteristics, and the plurality of parameters comprehensively reflect the installation and use conditions of the application program, thereby achieving the technical effect of high accuracy of screening the application program and further solving the technical problem of low accuracy of screening the application program by using a single parameter in the prior art.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 is an architecture diagram of a hardware environment constituted by a terminal and a server that execute a screening method of an application according to an embodiment of the present invention;

FIG. 2 is a flow chart of an alternative application screening method according to an embodiment of the present invention;

FIG. 3 is a flow diagram of an alternative application screening method according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of clustering using the KMENS clustering algorithm according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of clustering using a DBSCAN clustering algorithm according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a screening apparatus for an application according to an embodiment of the present invention;

fig. 7 is a schematic diagram of a server for implementing a screening method of an application according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Technical terms appearing in the embodiments of the present invention are explained below:

APP: the abbreviation of application refers to the application program on the mobile phone.

Presents a special APP: mainly refers to some APPs with better or poorer recent development, namely, the APP is different from the APP with general expression form (stable APP).

IMEI: international Mobile Equipment Identity (IMEI), which is commonly called a Mobile phone serial number and a Mobile phone serial number, is used to identify each Mobile communication device such as an independent Mobile phone in a Mobile phone network.

APP loading amount: the total number of users for installing a certain APP is indicated.

Number of APP active users: refers to the total number of users that a certain type of APP is used.

A mobile phone housekeeper: the mobile phone management software mainly comprises functions of mobile phone virus checking and killing, garbage cleaning, harassment interception, flow management, software management and the like.

A large plate: the method refers to the situation that all APPs are reported integrally, for example, the situation that the whole loading amount of all APPs or the total amount of users are collected by a mobile phone manager.

Clustering analysis: clustering refers to the aggregation of samples that do not have a category per se into different groups according to the principle of "clustering of objects", such a set of data objects is called a class or cluster, where within the same class, the differences between individuals are small, and within different classes, the differences between individuals are large.

Training a sample: the present invention refers to sample data used by a clustering algorithm training model (how to learn clustering).

In accordance with an embodiment of the present invention, there is provided an embodiment of a method that may be performed by an embodiment of the apparatus of the present application, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.

According to an embodiment of the invention, a method for screening an application program is provided.

Alternatively, in this embodiment, the screening method of the application program may be applied to a hardware environment formed by the first terminal 102, the second terminal 106 and the server 104 shown in fig. 1. As shown in fig. 1, the first terminal 102 and the second terminal 106 may be connected to the server 104 through a network, or the first terminal 102 may not be connected to the server 104. The first terminal 102 and the second terminal 106 may communicate with each other without the first terminal 102 being connected to the server 104. Such networks include, but are not limited to: the terminal 102 may be a mobile phone terminal, or may also be a PC terminal, a notebook terminal, or a tablet terminal.

The main operating principles of the hardware environment system shown in fig. 1 are:

the mobile phone housekeeping clients of the first terminal 102 and the second terminal 106 report the user software installation list and the user use list to the server 104. The server 104 obtains a parameter representing the loading amount of the application program and a parameter representing the user activity according to the user software installation list and the user usage list, clusters the application programs according to the parameter representing the loading amount of the application program and the parameter representing the user activity, wherein the clustered application programs are ordinary APPs, and the application programs which are not clustered are special APPs, namely target application programs. It should be noted that the first terminal 102 and the second terminal 106 in fig. 1 are only schematic, and in the embodiment of the present invention, a mobile phone housekeeping client that needs a large number of terminals reports the user software installation list and the user usage list to the server 104.

Fig. 2 is a flowchart of an alternative screening method for applications according to an embodiment of the present invention. As shown in fig. 2, the method comprises the steps of:

step S202, acquiring a first parameter and a second parameter of the N application programs, wherein the first parameter is a parameter used for representing the loading amount of the application programs, and the second parameter is a parameter used for representing the activity degree of users of the application programs.

And step S204, screening out target application programs from the N application programs according to the first parameters and the second parameters.

The method for screening the APP in the prior art is to rank according to the change rate of the loading amount of the APP from high to low to obtain the growing type APP or the declining type APP, and has the defect that great differences exist in the change rates of the loading amounts of the APPs with different loading levels.

The embodiment of the invention uses a plurality of parameters in two aspects of the installation amount (installation amount) and the activity degree (usage amount) as the characteristics, and the plurality of parameters comprehensively reflect the installation and use conditions of the application program, so the technical problem of low accuracy of screening the application program by using a single parameter in the prior art is solved, and the technical effect of high accuracy of screening the application program is achieved.

Fig. 3 is a flow chart of another alternative screening method for applications in accordance with an embodiment of the present invention. As shown in fig. 3, the method comprises the steps of:

step S302, data source collection.

And step S304, extracting the characteristic indexes.

Step S306, generating a training sample.

Step S308, clustering analysis is carried out by a clustering algorithm.

In step S310, an APP with a special appearance is obtained. The APP with special appearance is the target application program.

The following details the data source collection (step S302):

the method represents the APP performance in two aspects of the loading amount (installation amount) and the activity (usage amount), the loading amount data of the APP is obtained through a user software installation list reported by a client, and the APP activity is obtained through a user usage list reported by the client.

1) The reported user software installation list log format is as follows (an IMEI represents a mobile phone terminal).

IMEI1，APP1、APP2、APP3……

IMEI2，APP31、APP3、APP5……

……

2) The reported user software usage list log format is as follows:

IMEI1, APP1, begin _ time, end _ time, use _ cnt (number of uses), use _ time (duration of use)

IMEI1, APP2, begin _ time, end _ time, use _ cnt (number of uses), use _ time (duration of use)

IMEI2, APP1, begin _ time, end _ time, use _ cnt (number of uses), use _ time (duration of use)

……

The user uses the list of the APP to record the use times and the use duration information of a certain user to a certain APP within a certain period of time, wherein the use refers to the situation (non-back-end operation state) when the user opens the certain APP and operates on the screen of the mobile phone terminal. If the user opens a certain APP and runs on the screen of the mobile phone terminal, the user is an active user and is also a first user.

The feature index extraction (step S304) is explained in detail below:

after software installation lists and software use lists of all users (about 9 million active users) at a client are collected, APP is taken as a dimension, and multiple characteristic indexes of two aspects of APP installation quantity change and activity change are counted to represent recent APP performance trends. The characteristic indexes are the first parameter and the second parameter.

The first parameter is a parameter in terms of the loading amount. The first parameter may include at least one of the following two parameters: the current (the week relative to the last week) and last (the last week relative to the last week) loading rates.

At present (the week is relative to the last week) the change rate of the loading capacity of the cycle (APP 1 loading capacity/total loading capacity of the big plate in the week-last week APP1 loading capacity/total loading capacity of the big plate in the last week)/(last week APP1 loading capacity/total loading capacity of the big plate in the last week)

The rate of change of the loading capacity in the previous cycle (relative last cycle to last cycle) is (last cycle APP1 loading capacity/total loading capacity of last cycle big plate-last cycle APP1 loading capacity/total loading capacity of last cycle big plate)/(last cycle APP1 loading capacity/total loading capacity of last cycle big plate)

Taking APP1 as an example, the load of APP1 in a certain period refers to the number of users who install APP1 in the software installation list of all users collected in the period, the total number of times of using APP1 in the certain period refers to the total number of times of using APP1 by all active users of APP1 in the period, and the total duration of using APP1 in the certain period refers to the total duration of using APP1 by all active users of APP1 in the period.

The second parameter is a parameter in terms of the liveness of the user. The second parameter may include any one or more of the following sub-parameters: the change rate of the first user number of the current period application program, the change rate of the first user number of the last period application program, the change rate of the total using times of the current period application program, the change rate of the total using times of the last period application program, the change rate of the total using time of the current period application program and the change rate of the total using time of the last period application program.

The current period active user number change rate (the number of active users in APP 1/the total number of active users in the current period-the number of active users in APP 1/the total number of active users in the last period)/(the number of active users in APP 1/the total number of active users in the last period)

The number of users active in the last cycle (number of users active in APP1 last week/total number of users active in big last week-number of users active in APP1 last week/total number of users active in big last week)/(number of users active in APP1 last week/total number of users active in big last week)

The total APP usage number change rate in the current period (total APP1 usage number in the current period/total APP usage number in the week-total APP1 usage number in the previous period/total APP usage number in the previous period)/(total APP1 usage number in the previous period/total APP usage number in the previous period)

The rate of change of total APP usage in the previous period (total number of APP 1/total number of upper week disks used in the previous period-total number of APP 1/total number of upper week disks used in the previous period)/(total number of APP 1/total number of upper week disks used in the previous period)

The total usage duration change rate of APP in the current period (total usage duration of APP1 in the current period/total usage duration of the day-the last week APP 1/total usage duration of the day)/(total usage duration of APP1 in the last week)

The rate of change of the total usage duration of the last APP (last week APP 1/last week day total usage duration-last week APP 1/last week day total usage duration)/(last week APP 1/last week day total usage duration)

The large disk loading quantity refers to the total number of users reporting a user software list through a mobile phone housekeeper client, the large disk active total user number refers to the total number of users reporting the APP list used by the users, the large disk total use number refers to the total number of times that all users reporting the use of the software use each APP, and the large disk total use duration refers to the total use duration of all users reporting the use of the software use each APP.

The time period in the above embodiment may be a week, or a month, a quarter, etc., and different time periods may be used to count the characteristic indicators (the first parameter and the second parameter) of the APP.

The following details the training sample generation (step S306):

optionally, before the similarity between each of the N applications and other applications in the N applications is obtained according to the first parameter and the second parameter, the applications with the number of users smaller than a third preset value in the N applications may be filtered out.

Optionally, before the similarity between each of the N applications and other applications in the N applications is obtained according to the first parameter and the second parameter, applications with a machine installation amount smaller than a certain value in the N applications may be filtered out.

The number of the APPs reaches millions, and if the similarity of each APP and other APPs in all the APPs needs to be calculated, the workload is huge. In the embodiment of the invention, the sense of paying attention to the APPs with the extremely small machine loading amount or the extremely small user number is not great, the APPs with the extremely small machine loading amount or the extremely small user number do not need to be paid attention to, and the APPs with the extremely small machine loading amount or the extremely small user number can be directly filtered out. In the embodiment of the invention, certain APP built in the android are not concerned, so that some APP built in the android can be filtered out.

After the first parameter and the second parameter are calculated according to the above formula, a target application (showing a special APP) is screened out from the N applications according to the first parameter and the second parameter.

The APP with special manifestations can be divided into two categories, one is the growth type APP with good development tendency, and the other is the decline type APP with poor development tendency. The growth type APP is characterized in that: the loading volume is more and the loading volume change rate is big, and the increase that the active user is more and active user is very fast, and APP total use number is more and total use number rises fast, and APP total use is long and long more and long and total use time's change is fast. The decline type APP is characterized by: the loading is less and less, and active user is less and less, and APP total use number of times is less and less, and APP total use duration is more and more short.

As the APP with special performance has larger difference with the APP with common performance in the aspects of the loading amount and the user activity, the APP with special performance can be screened out from the N applications according to the first parameter and the second parameter.

The embodiment of the invention also provides a process of clustering the APP by using a clustering algorithm to screen out the APP with special performance.

The following detailed description is made for the clustering algorithm to perform clustering analysis (step S308) and obtain APP with special performance (step S310):

the general APP can be represented approximately, the clustering algorithm is used, the general APPs can be well clustered together, the APPs which are not clustered together are the special APPs, and therefore the influence on the APP magnitude can be eliminated. The clustering algorithm can consider the comparison between the horizontal direction and the vertical direction, so that the accuracy of the target application program obtained by using the screening method of the embodiment of the invention is high. The APP with special expression may be growth type APP with better development trend and also may be decline type APP with worse development trend. After selecting the APP with special performance, dividing the APP into a growing type APP or a declining type APP according to the first parameter and the second parameter.

And (3) performing cluster analysis on the training sample by using the characteristic indexes (the first parameter and the second parameter) obtained in the step (S304) as characteristics through a cluster algorithm, wherein the commonly-represented APPs generally have APPs with similar expression forms, and the purpose of the cluster analysis is to cluster the more commonly-represented APPs into various classes.

It should be noted that, in the process of performing cluster analysis on the training samples by using the feature indexes (the first parameter and the second parameter) obtained in step S304 as features through the clustering algorithm, the number of the used feature indexes is not particularly limited, and any plurality (2 to 8) of the following feature indexes may be used as the feature indexes: the change rate of the current (the week is relative to the last week) period loading amount, the change rate of the last period (the last week is relative to the last week) loading amount, the change rate of the first user number of the current period application program, the change rate of the first user number of the last period application program, the change rate of the total use times of the current period application program, the change rate of the total use times of the last period application program, the change rate of the total use time of the current period application program and the change rate of the total use time of the last period application program.

In general, when the number of the used feature indexes is larger, the installation and use conditions of the application program can be more comprehensively expressed, so that the clustering effect is better and the accuracy is higher.

The embodiment of the invention provides the following three clustering methods.

The first clustering method comprises the following steps:

and clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, and screening out the first application program, wherein the degree of the first application program deviating from the center of the category where the first application program is located is greater than a first preset value. The clustering method is a distance-based clustering algorithm, and points with close distances are clustered into a class, such as the KMENS clustering algorithm.

Taking the KMENS clustering algorithm as an example for explanation, the basic idea of the KMENS clustering algorithm is as follows:

1. creating k points as initial centroid points (random selection)

2. The following process is repeated until convergence

{

For each data point in the data set

Calculating the distances of the k centroids and the data points

Assigning data points to nearest class

For each class, calculating the mean of all points in the class, and taking the mean as the centroid

}

The value of k is arbitrary, for example, a plurality of values of k may be tried, and then the value of k with the best clustering effect is found. For example, when k is 4, the clustering result is as shown in fig. 4. In FIG. 4, there are a total of 4 boxes, box L4-1, box L4-2, box L4-3, and box L4-4, respectively. Each frame includes a plurality of points, the five-pointed star is a central point of each frame, the five-pointed star is used as a circle center, R1 (a first preset value) is used as a radius to draw a circle, and 4 circles are obtained, namely a circle Y1, a circle Y2, a circle Y3 and a circle Y4. The degree of deviation of the points outside the 4 circles from the center of the category in which the points are located is greater than the first preset value, and the points outside the 4 circles are all characteristic. That is, the application program represented by the arrow labeled points is performance specific.

And a second clustering method:

and clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, wherein the density degree of the application programs around the application programs in each category is within a preset range, and then screening the application programs out of the at least two categories. The second clustering method is a clustering algorithm based on density, such as a DBSCAN clustering algorithm. DBSCAN is a density-based clustering algorithm, and the point sets are clustered into two classes, as shown in FIG. 5, with a total of 2 irregular boxes, box L5-1 and box L5-2. Each box comprises a plurality of points, all the points in each box are gathered into the same class, the points in different boxes are in different classes, and the points which do not belong to any box are discrete points (points marked by arrows). The discrete points represent applications that are presentation specific.

And (3) clustering method III:

and acquiring a distance parameter between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter, wherein the distance parameter is used for representing the similarity degree between each application program and other application programs, and then screening the application programs of which the distance parameters are greater than a preset distance. The third clustering method is a density-based clustering algorithm, such as the OPTICS algorithm. The OPTICS algorithm is similar in principle to the DBSCAN algorithm, but gives a notion of distance-of-arrival (distance parameter), similar to the degree of dispersion, with greater distances-of-arrival indicating greater dispersion.

A threshold (preset distance) may be set for distance parameters and applications with distance parameters greater than the preset distance are considered performance specific.

When the arrival distance of the APP is calculated by adopting the OPTIC clustering algorithm, the calculated arrival distance of most of the APPs is very small, for example, the arrival distance is less than 0.05, the preset distance can be set to be 0.05, and the APP with the arrival distance greater than 0.05 is the APP with special performance. Table 1 shows that 12 APPs (the loading capacity is more than 10 ten thousand) with special performances are screened by using the OPTICS clustering algorithm in a certain period, and the arrival distances of the 12 APPs are all larger than 0.05. The first user in table 1 is the active user.

TABLE 1

It should be noted that the clustering algorithm used in the embodiment of the present invention is not limited to the three clustering algorithms KMEANS, DBSCAN and OPTICS.

When the magnitude of N is hundreds of thousands, millions or more, after the APPs are clustered, the APPs which are shown to be common are often clustered together, and the number of the APPs contained in the formed cluster is large and can reach hundreds, thousands or even tens of thousands; while APPs that behave specifically tend not to converge together, the number of APPs contained in a formed class is small, even if they do. Therefore, the category containing a very small number of APPs contains APPs with particularity. In order to find out the APPs, after clustering the APPs, screening out a target category from the obtained multiple categories, wherein the number of the application programs contained in the target category is less than or equal to a second preset value, and all the application programs in the target category are used as target application programs.

For example, assuming that the second preset value is 10, N is 100 ten thousand, and 100 ten thousand APPs are clustered to obtain 10 classes, as shown in table 2, the number of APPs included in the class C6 is only 5. That is, although the similarity between the 5 APPs is high, since the number of APPs included in the category C6 is too small, the 5 APPs may all be specifically represented, the category C6 is the target category, and the 5 APPs included in the category C6 are all target applications.

TABLE 2

The screening method of the application program provided by the embodiment of the invention can quickly and accurately mine the APP with special recent expression from a large amount of APPs.

The embodiment of the invention uses the parameters of two aspects of the installation amount (installation amount) and the activity amount (usage amount) as the characteristics, uses a plurality of parameters to calculate the similarity between the application program and other application programs, can screen the application program with more special performance from a mass of application programs according to the similarity because the similarity between the common application program and other application programs is high and the similarity between the special application program and other application programs is low, and solves the technical problem of low accuracy of screening the application program by using a single parameter in the prior art because the plurality of parameters comprehensively reflect the installation and use conditions of the application programs, thereby achieving the technical effect of high accuracy of screening the application programs. Furthermore, in the process of calculating the similarity, the longitudinal comparison of the application program per se in different periods and the transverse comparison of the application program and other application programs exist, so that the accuracy of screening the application programs is high.

The APP with special performance is the target application program. The APP with special manifestations can be divided into two categories, one is the growth type APP with good development tendency, and the other is the decline type APP with poor development tendency. The growth type APP is characterized in that: the loading volume is more and the loading volume change rate is big, and the increase that the active user is more and active user is very fast, and APP total use number is more and total use number rises fast, and APP total use is long and long more and long and total use time's change is fast. The decline type APP is characterized by: the loading is less and less, and active user is less and less, and APP total use number of times is less and less, and APP total use duration is more and more short. After selecting the APP with special performance according to the screening method of the application program provided by the embodiment of the invention, the APP with special performance is classified into a growth type APP or a decline type APP according to the first parameter and the second parameter. For growing APP, the popularization strength can be increased. For the declining APP, the promotion strength can be weakened.

A specific example is given below to illustrate the screening method of the application program provided by the embodiment of the present invention.

The embodiment of the invention represents the APP expression form by two aspects of the machine loading amount (installation amount) and the activity (usage amount), the APP machine loading amount data is obtained through a user software installation list reported by a client, and the APP activity is obtained through a user usage list reported by the client.

The following 8 characteristic indicators were calculated:

the change rate of the current (the week is relative to the last week) period loading amount, the change rate of the last period (the last week is relative to the last week) loading amount, the change rate of the first user number of the current period application program, the change rate of the first user number of the last period application program, the change rate of the total use times of the current period application program, the change rate of the total use times of the last period application program, the change rate of the total use time of the current period application program and the change rate of the total use time of the last period application program.

Some application programs built in android are filtered out from massive application programs, application programs with small installing amount or small number of active users are filtered out, and the rest application programs are used as training samples.

The training samples are subjected to cluster analysis by using 8 calculated characteristic indexes through an OPTIC algorithm, the OPTIC algorithm can give a concept of a distance to reach (distance parameter), a threshold value (preset distance) can be set for the distance parameter, and application programs with the distance parameter larger than the preset distance are considered to be specially represented. When the arrival distance of the APP is calculated by adopting the OPTIC clustering algorithm, the calculated arrival distance of most of the APPs is very small, for example, the arrival distance is less than 0.05, the preset distance can be set to be 0.05, and the APP with the arrival distance greater than 0.05 is the APP with special performance. Table 1 shows that 12 APPs (the loading capacity is more than 10 ten thousand) with special performances are screened by using the OPTICS clustering algorithm in a certain period, and the arrival distances of the 12 APPs are all larger than 0.05. The first user in table 1 is the active user.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

According to an embodiment of the present invention, there is further provided an application screening apparatus for implementing the application screening method, where the application screening apparatus is mainly used to execute the application screening method provided in the foregoing description of the embodiment of the present invention, and the application screening apparatus provided in the embodiment of the present invention is specifically described as follows:

fig. 6 is a schematic diagram of a screening apparatus for an application according to an embodiment of the present invention, and as shown in fig. 6, the screening apparatus for an application mainly includes an obtaining unit 10 and a first screening unit 20.

The acquiring unit 10 is configured to acquire a first parameter and a second parameter of the N applications, where the first parameter is a parameter indicating a loading amount of the application, and the second parameter is a parameter indicating an activity level of a user of the application.

The first screening unit 20 is configured to screen a target application program from the N application programs according to the first parameter and the second parameter.

Optionally, the first parameter includes a load change rate of the current period application program and/or a load change rate of the last period application program. The first screening unit 20 comprises a first screening subunit. And the first screening subunit is used for screening the target application program from the N application programs according to the second parameter and the loading amount change rate of the current period application program and/or the loading amount change rate of the last period application program.

Optionally, the second parameter comprises at least one sub-parameter and the first screening unit 20 comprises a second screening sub-unit. A second screening subunit, configured to screen a target application program from the N application programs according to at least one sub-parameter and the first parameter, where the sub-parameter includes any one of: the method comprises the steps of obtaining the change rate of the first user number of the current period application program, the change rate of the first user number of the last period application program, the change rate of the total using times of the current period application program, the change rate of the total using times of the last period application program, the change rate of the total using time of the current period application program and the change rate of the total using time of the last period application program, wherein the first user is a user who uses the application program.

Optionally, the first screening unit 20 comprises an acquisition subunit, a third screening subunit and a determination subunit. And the acquiring subunit is used for acquiring the similarity between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter. And the third screening subunit is used for screening out the application programs with the similarity meeting the preset condition. And the determining subunit is used for taking the screened application program as the target application program.

Optionally, the obtaining subunit comprises an obtaining module. And the acquisition module is used for acquiring the distance parameter between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter, wherein the distance parameter is used for expressing the similarity between each application program and other application programs. The third screening subunit includes a first screening module. The first screening module is used for screening out the application programs with the distance parameters larger than the preset distance.

Optionally, the obtaining subunit includes a first clustering module. And the first clustering module is used for clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories. The third screening subunit includes a second screening module. And the second screening module is used for screening out the first application program, wherein the degree of the first application program deviating from the center of the category of the first application program is greater than a first preset value.

Optionally, the obtaining subunit comprises a second clustering module. And the second clustering module is used for clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, wherein the density degree of the application programs around the application programs in each category is within a preset range. The third screening subunit includes a third screening module. And the third screening module is used for screening out the application programs outside the at least two categories.

Optionally, the apparatus further comprises a second screening unit and a determining unit. And the second screening unit is used for screening out a target category from the at least two categories after the screened application programs are determined to be the target application programs by the determining subunit, wherein the number of the application programs contained in the target category is less than or equal to a second preset value. And the determining unit is used for taking all the application programs in the target category as target application programs.

Optionally, the device further comprises a filtration unit. And the filtering unit is used for filtering the application programs of which the number of users is less than a third preset value in the N application programs before the acquiring subunit acquires the similarity between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter.

According to an embodiment of the present invention, there is also provided an application screening system, including: the screening device of the application program.

According to an embodiment of the present invention, there is also provided an application screening system, including: a terminal and a server. And the terminal is used for reporting the installation condition and the use condition of the N application programs to the server. The server is in communication connection with the terminal and is used for receiving the installation condition and the use condition of the N application programs reported by the terminal, acquiring first parameters and second parameters of the N application programs according to the installation condition and the use condition, and screening out target application programs from the N application programs according to the first parameters and the second parameters, wherein the first parameters are parameters for representing the loading amount of the application programs, and the second parameters are parameters for representing the activity degree of users of the application programs.

According to an embodiment of the present invention, there is also provided a server for implementing the screening method of the application program, as shown in fig. 7, the server mainly includes a processor 701, a display 703, a data interface 704, a memory 705, and a network interface 706, where:

the data interface 704 transmits the data to the processor 701 mainly by means of data transmission.

The memory 705 is mainly used for storing a first parameter, a second parameter, a similarity, an identifier of an application program, and the like.

The network interface 706 is primarily used for network communications with the server.

The display 703 is mainly used for displaying the first parameter, the second parameter, the similarity and the target application program.

The processor 701 is mainly configured to perform the following operations:

acquiring a first parameter and a second parameter of N application programs, wherein the first parameter is a parameter for representing the loading amount of the application programs, and the second parameter is a parameter for representing the activity degree of users of the application programs; and screening out target application programs from the N application programs according to the first parameters and the second parameters.

The processor 701 is further configured to perform: and screening out target application programs from the N application programs according to the second parameters and the change rate of the loading amount of the application programs in the current period and/or the change rate of the loading amount of the application programs in the last period.

The processor 701 is further configured to perform: screening out target application programs from the N application programs according to the at least one sub-parameter and the first parameter, wherein the sub-parameter comprises any one of the following: the method comprises the steps of obtaining the change rate of the number of first users of the application program in the current period, the change rate of the number of first users of the application program in the last period, the change rate of the total using times of the application program in the current period, the change rate of the total using times of the application program in the last period, the change rate of the total using time of the application program in the current period and the change rate of the total using time of the application program in the last period, wherein the first users are users who have used the application program.

The processor 701 is further configured to perform: acquiring the similarity between each application program in the N application programs and other application programs in the N application programs according to the first parameters and the second parameters; screening out the application programs with the similarity meeting preset conditions; and taking the screened application program as a target application program.

The processor 701 is further configured to perform: and acquiring a distance parameter between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter, wherein the distance parameter is used for representing the similarity degree between each application program and other application programs, and screening the application programs of which the distance parameter is greater than a preset distance.

The processor 701 is further configured to perform: and clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, and screening out a first application program, wherein the degree of the first application program deviating from the center of the category where the first application program is located is greater than a first preset value.

The processor 701 is further configured to perform: clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, wherein the density degree of the application programs around the application programs in each category is within a preset range; screening out applications that are outside of the at least two categories.

The processor 701 is further configured to perform: screening out a target category from the at least two categories, wherein the number of the application programs contained in the target category is less than or equal to a second preset value; and taking all the application programs in the target category as the target application programs.

The processor 701 is further configured to perform: and filtering out the application programs of which the number of users in the N application programs is less than a third preset numerical value.

Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment is not described herein again.

The embodiment of the invention also provides a storage medium. Optionally, in this embodiment, the storage medium may be configured to store a program code of the screening method for the application program according to the embodiment of the present invention.

Optionally, in this embodiment, the storage medium may be located in at least one of a plurality of network devices in a network of a mobile communication network, a wide area network, a metropolitan area network, or a local area network.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:

s1, acquiring a first parameter and a second parameter of N application programs, wherein the first parameter is a parameter for representing the loading amount of the application programs, and the second parameter is a parameter for representing the activity degree of users of the application programs;

s2, screening out target application programs from the N application programs according to the first parameters and the second parameters.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: and screening out target application programs from the N application programs according to the second parameters and the change rate of the loading amount of the application programs in the current period and/or the change rate of the loading amount of the application programs in the last period.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: screening out target application programs from the N application programs according to the at least one sub-parameter and the first parameter, wherein the sub-parameter comprises any one of the following: the method comprises the steps of obtaining the change rate of the number of first users of the application program in the current period, the change rate of the number of first users of the application program in the last period, the change rate of the total using times of the application program in the current period, the change rate of the total using times of the application program in the last period, the change rate of the total using time of the application program in the current period and the change rate of the total using time of the application program in the last period, wherein the first users are users who have used the application program.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: acquiring the similarity between each application program in the N application programs and other application programs in the N application programs according to the first parameters and the second parameters; screening out the application programs with the similarity meeting preset conditions; and taking the screened application program as a target application program.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: and acquiring a distance parameter between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter, wherein the distance parameter is used for representing the similarity degree between each application program and other application programs, and screening the application programs of which the distance parameter is greater than a preset distance.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: and clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, and screening out a first application program, wherein the degree of the first application program deviating from the center of the category where the first application program is located is greater than a first preset value.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, wherein the density degree of the application programs around the application programs in each category is within a preset range; screening out applications that are outside of the at least two categories.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: screening out a target category from the at least two categories, wherein the number of the application programs contained in the target category is less than or equal to a second preset value; and taking all the application programs in the target category as the target application programs.

Optionally, in this embodiment, the processor executes, according to the program code stored in the storage medium: and filtering out the application programs of which the number of users in the N application programs is less than a third preset numerical value.

Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, network devices, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The foregoing is only a preferred 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

1. A method for screening an application program, comprising:

acquiring first parameters and second parameters of N application programs according to a user software installation list and a user use list reported by a terminal, wherein the first parameters are parameters for representing the loading amount of the application programs, and the second parameters are parameters for representing the activity degree of users of the application programs;

screening out target application programs from the N application programs according to the first parameters and the second parameters, wherein the screening comprises the following steps: acquiring the similarity between each application program in the N application programs and other application programs in the N application programs according to the first parameters and the second parameters; screening out the application programs with the similarity meeting preset conditions;

wherein obtaining the similarity between each of the N applications and other applications of the N applications according to the first parameter and the second parameter comprises: obtaining a distance parameter between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter, wherein the distance parameter is used for representing a similarity degree between each application program and other application programs, and screening the application programs of which the similarity degree meets a preset condition includes: screening out the application programs with the distance parameters larger than the preset distance;

and taking the screened application program as a target application program.

2. The method of claim 1, wherein the first parameter comprises a rate of change of a loading amount of the application program in a current cycle and/or a rate of change of a loading amount of the application program in a previous cycle, and wherein the screening out the target application program from the N application programs according to the first parameter and the second parameter comprises:

and screening out target application programs from the N application programs according to the second parameters and the change rate of the loading amount of the application programs in the current period and/or the change rate of the loading amount of the application programs in the last period.

3. The method of claim 1, wherein the second parameter comprises at least one sub-parameter, and wherein the screening of the target application from the N applications according to the first parameter and the second parameter comprises:

screening out target application programs from the N application programs according to the at least one sub-parameter and the first parameter, wherein the sub-parameter comprises any one of the following:

the method comprises the steps of obtaining the change rate of the number of first users of the application program in the current period, the change rate of the number of first users of the application program in the last period, the change rate of the total using times of the application program in the current period, the change rate of the total using times of the application program in the last period, the change rate of the total using time of the application program in the current period and the change rate of the total using time of the application program in the last period, wherein the first users are users who have used the application program.

4. The method of claim 1,

obtaining the similarity between each application program of the N application programs and other application programs of the N application programs according to the first parameter and the second parameter includes: clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories,

screening out the application programs with the similarity meeting the preset condition comprises the following steps: screening a first application program, wherein the degree of the first application program deviating from the center of the category of the first application program is greater than a first preset value.

5. The method of claim 1,

obtaining the similarity between each application program of the N application programs and other application programs of the N application programs according to the first parameter and the second parameter includes: clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, wherein the density degree of the application programs around the application programs in each category is within a preset range;

screening out the application programs with the similarity meeting the preset condition comprises the following steps: screening out applications that are outside of the at least two categories.

6. The method of claim 4 or 5, wherein after the screened applications are targeted applications, the method further comprises:

screening out a target category from the at least two categories, wherein the number of the application programs contained in the target category is less than or equal to a second preset value;

and taking all the application programs in the target category as the target application programs.

7. The method according to claim 1, wherein before obtaining the similarity between each of the N applications and the other of the N applications according to the first parameter and the second parameter, the method further comprises:

and filtering out the application programs of which the number of users in the N application programs is less than a third preset numerical value.

8. An apparatus for screening an application, comprising:

an obtaining unit, configured to obtain first parameters and second parameters of N application programs according to a user software installation list and a user usage list reported by a terminal, where the first parameters are parameters used to represent loading amounts of the application programs, and the second parameters are parameters used to represent activity degrees of users of the application programs;

the first screening unit is used for screening target application programs from the N application programs according to the first parameters and the second parameters;

wherein the first screening unit includes: an obtaining subunit, configured to obtain, according to the first parameter and the second parameter, a similarity between each of the N application programs and another application program in the N application programs; wherein the obtaining subunit includes: an obtaining module, configured to obtain, according to the first parameter and the second parameter, a distance parameter between each of the N application programs and another application program of the N application programs, where the distance parameter is used to indicate a degree of similarity between each application program and another application program, and a third screening subunit, configured to screen out an application program whose degree of similarity satisfies a preset condition; a determining subunit, configured to use the screened application program as a target application program, where the third screening subunit includes: and the first screening module is used for screening out the application programs of which the distance parameters are greater than the preset distance.

9. The apparatus according to claim 8, wherein the first parameter includes a loading change rate of the application program in a current cycle and/or a loading change rate of the application program in a previous cycle, and the first filtering unit includes:

and the first screening subunit is used for screening out a target application program from the N application programs according to the second parameter and the loading quantity change rate of the application program in the current period and/or the loading quantity change rate of the application program in the last period.

10. The apparatus of claim 8, wherein the second parameter comprises at least one sub-parameter, and wherein the first filtering unit comprises:

a second filtering subunit, configured to filter out a target application from the N applications according to the at least one sub-parameter and the first parameter, where the sub-parameter includes any one of:

11. The apparatus of claim 8,

the acquisition subunit includes:

a first clustering module for clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories,

the third screening subunit comprises:

and the second screening module is used for screening out the first application program, wherein the degree of the first application program deviating from the center of the category of the first application program is greater than a first preset value.

12. The apparatus of claim 8,

the acquisition subunit includes:

the second clustering module is used for clustering the N application programs according to the first parameter and the second parameter to obtain at least two categories, wherein the density degree of the application programs around the application programs in each category is within a preset range;

the third screening subunit comprises:

and the third screening module is used for screening out the application programs outside the at least two categories.

13. The apparatus of claim 11 or 12, further comprising:

a second screening unit, configured to screen a target category from the at least two categories after the determining subunit takes the screened application as a target application, where a number of applications included in the target category is less than or equal to a second preset value;

a determining unit, configured to use all the applications in the target category as the target applications.

14. The apparatus of claim 8, further comprising:

and the filtering unit is configured to filter out the application programs, of which the number of users is smaller than a third preset value, in the N application programs before the obtaining subunit obtains the similarity between each of the N application programs and other application programs in the N application programs according to the first parameter and the second parameter.

15. A screening system for applications, comprising: a screening apparatus for an application program according to any one of claim 8 to claim 14.

16. A screening system for applications, comprising:

the terminal is used for reporting the installation condition and the use condition of the N application programs to the server;

the server is in communication connection with the terminal and is used for receiving the installation condition and the use condition of the N application programs reported by the terminal, acquiring first parameters and second parameters of the N application programs according to the installation condition and the use condition, and screening target application programs from the N application programs according to the first parameters and the second parameters, wherein the first parameters are parameters for representing the loading amount of the application programs, and the second parameters are parameters for representing the activity degree of users of the application programs; wherein the screening of the target application program from the N application programs according to the first parameter and the second parameter comprises: obtaining a distance parameter between each application program in the N application programs and other application programs in the N application programs according to the first parameter and the second parameter, wherein the distance parameter is used for representing the similarity degree between each application program and other application programs, and screening out the application programs of which the distance parameter is greater than a preset distance; and taking the screened application program as the target application program.