CN106844724B - Method and device for recommending applications based on applications installed by user - Google Patents
Method and device for recommending applications based on applications installed by user Download PDFInfo
- Publication number
- CN106844724B CN106844724B CN201710072980.XA CN201710072980A CN106844724B CN 106844724 B CN106844724 B CN 106844724B CN 201710072980 A CN201710072980 A CN 201710072980A CN 106844724 B CN106844724 B CN 106844724B
- Authority
- CN
- China
- Prior art keywords
- application
- applications
- user
- preset
- library
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The invention provides a method and a device for recommending an application based on an installed application of a user. The method comprises the following steps: determining a similarity list between every two applications in a preset application library; determining the preference degree of the user to each application in a preset application library based on 1 or more applications installed by the user and the similarity list; and selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a method and a device for recommending applications based on applications installed by a user.
Background
With the rapid development of internet technology and intelligent mobile terminal technology, many functions (e.g., shopping and reading) implemented on a computer terminal can also be implemented on an intelligent mobile terminal, for example, using a smart phone or a tablet computer. In addition, the implementation of these functions requires the installation of corresponding applications on the smart mobile terminal. For example, online shopping, installation of e.g. a panning client, listening to music, installation of a music player client, etc. Thus, many software companies offer application stores or markets, such as pea pods or PP assistants, for example. The user can open an application store or an application market, so that various required application programs including video and audio playing, system tools, communication social contact, online shopping, reading and the like can be quickly searched and downloaded, and leisure and entertainment application programs (APP) such as games and the like can be downloaded.
In an application store or an application market, in order to continuously improve the good experience of a user using the application store or the application market, developers currently develop a plurality of functions convenient for the user to use, one of which is a recommendation function that recommends some applications to the user to help the user find more interesting applications, for example: guessing you like, downloading by everyone, etc. The current methods for recommending applications are generally recommended according to the popularity of the application, such as recommending applications with download amount ranked in the front or recommending applications on a popular ranking list. However, different users have different interests, and applications recommended according to the prior art are not necessarily interesting to the users, and cannot meet the requirements of different users, so that the user experience is poor.
Disclosure of Invention
The invention aims to provide a method and a device for recommending an application based on an installed application of a user, so as to improve the problem.
The embodiment of the invention provides a method for recommending applications based on applications installed by a user, which comprises the following steps:
determining a similarity list between every two applications in a preset application library;
determining the preference degree of the user to each application in a preset application library based on 1 or more applications installed by the user and the similarity list;
and selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small.
In the steps of determining the preference degree of the user to each application in a preset application library and selecting a certain number of corresponding applications from the preset application library as recommended applications based on the sequence of the preference degrees from large to small, selecting a plurality of applications from the preset application library as the pre-recommended applications, establishing a candidate set containing the plurality of pre-recommended applications, determining the preference degree of the user to each pre-recommended application in the candidate set, and selecting a certain number of corresponding applications from the candidate set as the recommended applications based on the sequence of the preference degrees from large to small.
Preferably, the pre-recommended application is an application having the same tag as that of 1 or more applications that the user has installed.
The embodiment of the invention also provides a device for recommending the application based on the application installed by the user, which comprises the following steps:
the application similarity list determining unit is used for determining a similarity list between every two applications in a preset application library;
the user preference determining unit is used for determining the preference of the user to each application in the preset application library based on 1 or more applications installed by the user and the similarity list;
and the recommending unit is used for selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small.
Preferably, the similarity between two applications in the preset application library is calculated, and the similarity between the two applications is tabulated, wherein the similarity between the two applications is calculated as follows:
wherein: k is 1,2, …, n j is 1,2 …, n
Sk,lRepresenting the similarity between application k and application l;
n represents the number of applications in the preset application library;
m represents the number of labels in the preset label set;
tk,jwhether the application k has a label j is represented as 1, and the application k is not represented as 0;
tl,jwhether the application l has a label j is represented as 1, and the application l has no label j;
rjrepresents the resolution of label j, where:
n represents the number of applications in the preset application library;
ti,jand the label j is represented by whether the application i has a label j with 1 or no 0.
The preference degree of the user to a certain application is the accumulated sum of the similarity degrees between a plurality of applications installed by the user and the certain application, and the calculation formula is as follows:
wherein: plRepresenting the preference of a user to an application l in a preset application library;
t represents the number of applications installed by the user;
Sk,lrepresenting the similarity between the user installed application k and the application l in the preset application library.
The embodiment of the invention also provides a device for recommending the application based on the application installed by the user, which comprises the following steps:
the application similarity list determining unit is used for determining a similarity list between every two applications in a preset application library;
the device comprises a candidate set establishing unit of pre-recommended applications, a candidate set determining unit and a pre-recommending application setting unit, wherein the candidate set establishing unit is used for selecting a plurality of applications from a preset application library as the pre-recommended applications and establishing the candidate set containing the pre-recommended applications;
the user preference determining unit is used for determining the preference of the user to each pre-recommended application in the candidate set based on 1 or more applications installed by the user and the similarity list;
and the recommending unit is used for selecting a certain number of corresponding applications from the candidate set as recommended applications according to the sequence of the preference values from large to small.
Preferably, the pre-recommended application is an application having the same tag as that of 1 or more applications that the user has installed.
According to the method and the device for recommending the application based on the application installed by the user, firstly, a similarity list between every two applications in a preset application library is established; then determining the preference degree of the user to each application in a preset application library according to 1 or more applications installed by the user and the similarity list; and selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small, thereby realizing the purpose of carrying out personalized recommended applications according to the interests and hobbies of the user and greatly improving the user experience.
Drawings
FIG. 1 is a flowchart of a method of recommending applications based on a user installed application according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a method of recommending applications based on a user installed application according to a second embodiment of the present invention;
FIG. 3 is a schematic block diagram of an apparatus for recommending an application based on a user-installed application according to a third embodiment of the present invention;
fig. 4 is a schematic block diagram of an apparatus for recommending an application based on a user-installed application according to a fourth embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention and the accompanying drawings, 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. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
One of the reasons for the above-mentioned poor user experience is that different users have different interests, and the recommendation scheme of the prior art is only to recommend applications with the highest download amount, but the applications with the highest download amount are not always preferred by people. Taking a game as an example, assuming that the 'fisherman APP' is the highest downloading amount, but the user A does not like playing the 'fisherman' game but like playing a fighting game, so that the user A is recommended that the 'fisherman' cannot arouse the interest of the user A to click to download; as another example, user B downloads "catch fellow" under the recommendation of a friend, but does not like to play, and unloads it. However, according to the recommendation method in the prior art, when the user B clicks to enter the application store or the application market, the "fish catcher" is still recommended to the user B, which brings a bad user experience.
The inventor of the technical scheme fully considers the interests and hobbies of the users, provides a novel personalized recommendation method, and can recommend different applications according to different interests and hobbies of different users, so that personalized recommendation is realized, and the experience of the users is greatly improved.
Generally, it can be considered that various applications installed on a smart terminal such as a smart phone or a tablet computer or a computer used by a user, such as games, leisure, offices, and the like, are applications in which the user is interested, and if a method can be found to recommend the applications based on the applications installed by the user, the purpose of personalized recommendation can be achieved.
Fig. 1 is a flowchart of a method of recommending an application based on a user-installed application according to a first embodiment of the present invention. As shown in fig. 1, the method for recommending applications based on applications installed by a user of the present invention includes the following steps:
s1: and determining a similarity list between every two applications in the preset application library.
An application library is generally preset when an application market or an application store is developed, and application information downloaded from the application market or the application store is stored in the preset application library. The method of the invention firstly calculates the similarity value between every two applications in a preset application library, and makes the similarity value between every two applications into a list. The similarity list may include: ID numbers of two applications, similarity values between the two applications. For example as shown in the following table:
first application ID | Second application ID | Degree of similarity |
00001 | 00002 | 0.21 |
00001 | 00003 | 0.35 |
00001 | 00004 | 0.26 |
… | … | … |
00002 | 00003 | 0.13 |
00002 | 00004 | 0.29 |
00002 | 00005 | 0.38 |
… | … | … |
There are many methods for determining the similarity between two applications, and a very simple method such as classification sets the similarity between two applications of the same class to 1 and the similarity between two applications of different classes to 0. In addition, various third-party applications (abbreviated as applications) provided in an application store or an application market usually have tags, and the tags are used for identifying the categories or contents of the various applications, so that the user can conveniently search the categories or contents. Currently, each application in an application marketplace or application store contains at least 1 application tag, so that the similarity between two applications can be determined based on whether they have the same tag. Further, the value of the similarity may be determined according to the number of the same tags, and for example, the similarity between two applications having 1 same tag may be set to 1, and the similarity between two applications having 2 same tags may be set to 2. Of course, the similarity values exemplified here are 1 or 2, etc., for illustrative purposes only, and other numbers may be used in practice, such as a percentage value between (0, 1).
Third party applications provided by an application store or application marketplace all have 1 or more tags from a set of tags that were preset at the time of development of the application store or application marketplace, which is common knowledge to those skilled in the art, and such conventional techniques are not described here in too much detail.
Of course, the above-described exemplary method is the simplest method, and other methods may be used. However, in the present invention, it is preferable to provide a better determination method, and the similarity value obtained thereby can show the similarity between two applications in the preset application library.
The method for calculating the similarity between every two applications is as follows:
wherein: k is 1,2, …, n j is 1,2 …, n
Sk,lRepresenting the similarity between application k and application l;
n represents the number of applications in the preset application library;
m represents the number of labels in the preset label set;
tk,jwhether the application k has a label j is represented as 1, and the application k is not represented as 0;
tl,jwhether the application l has a label j is represented as 1, and the application l has no label j;
rjrepresents the resolution of label j, where:
n represents the number of applications in the preset application library;
ti,jand the label j is represented by whether the application i has a label j with 1 or no 0.
Here the resolution r of the label j is usedjTo reflect the degree of fineness of the content divided by the tag j, a larger resolution value indicates a finer content division.
For example: there are two labels "flashlight", "gadget" in the preset set of labels. There are 10 types of applications with "flashlights" that all function as cell phone lighting. There are 100 versions of the "gadget" label that contain some applications on the gadget category of weather queries, alarm clocks, calculators, etc., in addition to all "flashlight" applications contained. The label "flashlight" in this example is more refined in its partitioning than the label "gadget", and the label passing through the "flashlight" can be more accurately matched to the relevant application and therefore can be considered to be of higher resolution. The quantization resolution can be measured by counting the inverse of the number of applications covered by a label. In this example, the resolution of the "flashlight" is 0.1, the resolution of the "gadget" is 0.01, and the resolution of the "flashlight" is 10 times that of the "gadget", and the division content is finer.
Here, the similarity value is compressed to be between (0, 1) by superimposing two applications, wherein the application k and the application l have the same label resolution, and then performing normalization processing.
S2: and determining the preference degree of the user to each application in the preset application library based on the 1 or more applications installed by the user and the similarity list.
The user-installed application described herein refers to a third-party application that is installed on a terminal used by the user when recommending the application to the user.
To find out a plurality of applications suitable for recommendation to a user from a preset application library, a method capable of determining the preference of the user for each application in the preset application library is required, and a recommended application is selected according to the preference.
The method adopted here is: and taking the accumulated sum of the similarity between each of the plurality of applications installed by the user and a certain application as the value of the preference degree of the user for the certain application. That is, the similarity values between one application in the preset application library and 1 or more applications installed by the user are found from the similarity list established in the previous step, and the similarity values are accumulated and summed, so that the obtained value is the preference value of the user for the application. Similarly, the preference degree of the user to each application in the preset application library can be obtained. The calculation formula for determining the preference is as follows:
wherein: plRepresenting the preference of a user to an application l in a preset application library;
t represents the number of applications installed by the user;
Sk,lrepresenting the similarity between the user installed application k and the application l in the preset application library.
Since it is referred to herein as using the similarity between the user-installed application and the applications in the preset application library, the user-installed application herein includes applications that the user downloads through an application store or an application market and applications that can be found in the application store or the application market.
S3: and selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small.
And according to the obtained preference degree of the user to each application in the preset application library, selecting a certain number of corresponding applications from the preset application library according to the sequence of the preference degree from large to small, and if the corresponding applications are selected from the maximum value of the preference degree downwards, displaying the corresponding applications as recommended applications to the user. The number can be chosen freely in practice, for example 5, 10, 20, 50 or values thereof, etc.
In the above embodiment, a method of determining the preference of the user for each application in the preset application library is adopted, but the number of applications in the preset application library is large, which results in a large amount of calculation. In the following, a preferred embodiment is described, a part of applications is selected from a preset application library in advance as pre-recommended applications, and a candidate set including the plurality of pre-recommended applications is established, so as to determine the preference of the user for each pre-recommended application in the candidate set, thereby reducing the amount of computation and increasing the speed of finding recommended applications.
Fig. 2 is a flowchart of a method of recommending an application based on a user-installed application according to a second embodiment of the present invention. As shown in fig. 2, the method for recommending applications based on applications installed by a user of the present invention includes the following steps:
s1: and determining a similarity list between every two applications in the preset application library.
The same as the corresponding step S1 of the first embodiment, and the description will not be repeated.
S2: and selecting a plurality of applications from a preset application library as pre-recommended applications, and establishing a candidate set containing the pre-recommended applications.
The selection method for selecting a plurality of applications from the preset application library as the pre-recommended applications can adopt a plurality of modes or a plurality of modes to coexist. For example, one of the selection methods: counting the downloading amount of applications provided by an application store or an application market, and selecting a plurality of applications with the top downloading amount as pre-recommended applications, or selecting a plurality of applications with the top downloading amount in each classification as pre-recommended applications from a plurality of classified applications with the same classification as the applications installed by a user; the second selection method comprises: counting quality scores of applications provided by an application store or an application market, and selecting a plurality of applications with high scores as pre-recommended applications, or selecting a plurality of applications with high scores in each category as pre-recommended applications from a plurality of classified applications with the same categories as the applications installed by the user; the third selection method comprises the following steps: counting the conversion rate of the applications provided by an application store or an application market, namely, the ratio of the number of users clicking one application and downloading the application to the number of users clicking the application is the conversion rate, and selecting a plurality of applications with the top conversion rate ranking as pre-recommended applications, or selecting a plurality of applications with the top conversion rate ranking in each classification as pre-recommended applications from a plurality of classified applications with the same classification as the applications installed by the user; the fourth selection method comprises the following steps: an application having the same tag as the tags of 1 or more applications already installed by the user is selected as the pre-recommended application, that is, if 1 application already installed by the user has 3 tags, an application having 1 or 2 or 3 tags of the 3 tags is selected as the pre-recommended application. In addition, other methods can be used for selection, and any combination of the above 4 methods can be used for selecting multiple applications from the preset application library as the pre-recommended applications.
A candidate set containing the plurality of pre-recommended applications is established. For a plurality of selected applications, the selected applications can be recorded in a list, and if the number of the selected pre-recommended applications is large, thousands or tens of thousands, a candidate application library can be separately established and the selected pre-recommended applications are recorded in the candidate application library.
S3: and determining the preference degree of the user to each pre-recommended application in the candidate set based on the 1 or more applications installed by the user and the similarity list.
The same as the corresponding step S2 of the first embodiment. That is, the similarity values between one application in the candidate set and 1 or more applications installed by the user are found from the established similarity list, and the similarity values are accumulated and summed, so that the obtained value is the preference value of the user for the application. Similarly, the user preference for each application in the candidate set may be obtained. The calculation formula for determining the preference is as follows:
wherein: plRepresenting the preference of the user to the application l in the candidate set;
t represents the number of applications installed by the user;
Sk,lrepresenting the similarity between the user installed application k and the application l in the candidate set.
Since it is referred to herein as using the similarity between the user-installed application and the applications in the preset application library, the user-installed application herein includes applications that the user downloads through an application store or an application market and applications that can be found in the application store or the application market.
S4: and selecting a certain number of corresponding applications from the candidate set as recommended applications according to the sequence of the preference values from large to small.
The same as the corresponding step S3 of the first embodiment, and the description will not be repeated.
Compared with the first embodiment, the second embodiment has the difference that a plurality of applications are selected from the preset application library in advance as the pre-recommended applications based on certain conditions, so that the applications with poor quality and without attention can be abandoned, the preference degree of a subsequent user for the applications with poor quality is avoided, the calculation amount is reduced, and the speed of searching the recommended applications is improved.
According to the method for recommending the application based on the application installed by the user, the preference degree of the user to each application in the preset application library can be determined; and selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small, so that the purpose of carrying out personalized recommended applications according to the interests and hobbies of the user is realized, and the user experience is greatly improved.
Fig. 3 is a schematic block diagram of an apparatus for recommending an application based on a user-installed application according to a third embodiment of the present invention. As shown in fig. 3, the apparatus for recommending an application based on an installed application of a user according to the present invention includes:
the application similarity list determining unit is used for determining a similarity list between every two applications in a preset application library;
the user preference determining unit is used for determining the preference of the user to each application in the preset application library based on 1 or more applications installed by the user and the similarity list;
and the recommending unit is used for selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small.
Preferably, the similarity list determining unit of the applications is configured to calculate similarity values between two applications in a preset application library, and make the similarity values between the two applications into a list, where the similarity between the two applications is calculated by the following method:
wherein: k is 1,2, …, n j is 1,2 …, n
Sk,lRepresenting the similarity between application k and application l;
n represents the number of applications in the preset application library;
m represents the number of labels in the preset label set;
tk,jwhether the application k has a label j is represented as 1, and the application k is not represented as 0;
tl,jwhether the application l has a label j is represented as 1, and the application l has no label j;
rjrepresents the resolution of label j, where:
n represents the number of applications in the preset application library;
ti,jand the label j is represented by whether the application i has a label j with 1 or no 0.
Preferably, the preference determining unit of the user for the application is configured to use an accumulated sum of similarities between each of the plurality of applications installed by the user and the application as the preference of the user for the application, and the calculation formula is as follows:
wherein: plRepresenting the preference of a user to an application l in a preset application library;
t represents the number of applications installed by the user;
Sk,lrepresenting the similarity between the user installed application k and the application l in the preset application library.
It will be clear to those skilled in the art that for convenience and brevity of description, the specific working process of the apparatus described in conjunction with the third embodiment may refer to the corresponding process in the foregoing first embodiment, and will not be described repeatedly herein.
Fig. 4 is a schematic block diagram of an apparatus for recommending an application based on a user-installed application according to a fourth embodiment of the present invention. As shown in fig. 4, the apparatus for recommending an application based on an installed application of a user according to the present invention includes:
the application similarity list determining unit is used for determining a similarity list between every two applications in a preset application library;
the device comprises a candidate set establishing unit of pre-recommended applications, a candidate set determining unit and a pre-recommending application setting unit, wherein the candidate set establishing unit is used for selecting a plurality of applications from a preset application library as the pre-recommended applications and establishing the candidate set containing the pre-recommended applications;
the user preference determining unit is used for determining the preference of the user to each pre-recommended application in the candidate set based on 1 or more applications installed by the user and the similarity list;
and the recommending unit is used for selecting a certain number of corresponding applications from the candidate set as recommended applications according to the sequence of the preference values from large to small.
Preferably, the operation of the applied similarity degree list determining unit is the same as that described in the third embodiment.
Preferably, the working process of the candidate set establishing unit of the pre-recommended application, which is preferably an application having the same tag as that of 1 or more applications already installed by the user, may refer to the corresponding process in the foregoing second embodiment, and will not be described again here.
Preferably, the working process of the preference degree determination unit of the user for the application may refer to the corresponding process in the foregoing second embodiment. That is, the similarity values between one application in the candidate set and 1 or more applications installed by the user are found from the established similarity list, and the similarity values are accumulated and summed, so that the obtained value is the preference value of the user for the application. Similarly, the user preference for each application in the candidate set may be obtained. The calculation formula for determining the preference is as follows:
wherein: plRepresenting the preference of the user to the application l in the candidate set;
t represents the number of applications installed by the user;
Sk,lrepresenting the similarity between the user installed application k and the application l in the candidate set.
Since it is referred to herein as using the similarity between the user-installed application and the applications in the preset application library, the user-installed application herein includes applications that the user downloads through an application store or an application market and applications that can be found in the application store or the application market.
It is clear to those skilled in the art that for convenience and brevity of description, the specific working process of the apparatus described in conjunction with the fourth embodiment may refer to the corresponding process in the foregoing second embodiment, and the description is not repeated here.
According to the device for recommending the application based on the application installed by the user, the preference degree of the user to each application in the preset application library can be determined; and selecting a certain number of corresponding applications from a preset application library as recommended applications according to the sequence of the preference values from large to small, so that the purpose of carrying out personalized recommended applications according to the interests and hobbies of the user is realized, and the user experience is greatly improved.
The computer program product of the method for recommending an application based on an application installed by a user according to the embodiment of the present invention includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the method embodiment, and will not be described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a 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 instructions for causing a computer device (which may be a personal computer, a tablet computer, a smart phone, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (8)
1. A method of recommending applications based on a user installed applications, comprising:
determining a similarity list of one application relative to another application between every two applications in a preset application library;
determining the similarity of the 1 or more applications installed by the user relative to each application in a preset application library based on the 1 or more applications installed by the user and the similarity list, and further determining the preference of the user to each application in the preset application library;
selecting a certain number of corresponding applications from a preset application library as recommended applications based on the preference values in descending order,
in the step of determining a similarity list of one application relative to another application between two applications in the preset application library, calculating a similarity value of one application relative to another application between two applications in the preset application library, and tabulating the similarity value of one application relative to another application between the two applications, the similarity of one application relative to another application between the two applications is calculated by the following method:
wherein: k 1,2, …, nj 1,2 …, n
Sk,lRepresenting the similarity of application k relative to application l;
n represents the number of applications in the preset application library;
m represents the number of labels in the preset label set;
tk,jwhether the application k has a label j is represented as 1, and the application k is not represented as 0;
tl,jwhether the application l has a label j is represented as 1, and the application l has no label j;
rjrepresents the resolution of label j, where:
n represents the number of applications in the preset application library;
ti,jand the label j is represented by whether the application i has a label j with 1 or no 0.
2. The method according to claim 1, wherein in the steps of determining the preference of the user for each application in a preset application library and selecting a number of corresponding applications from the preset application library as recommended applications based on the preference values in descending order, selecting a plurality of applications from the preset application library as the recommended applications, creating a candidate set comprising the plurality of pre-recommended applications, thereby determining the preference of the user for each pre-recommended application in the candidate set, and selecting a number of corresponding applications from the candidate set as recommended applications based on the preference values in descending order.
3. The method according to claim 1, wherein in the step of determining the preference of the user for each application in the preset application library based on the 1 or more applications installed by the user and the similarity list, the preference of the user for a certain application is a cumulative sum of similarities between the applications installed by the user and the certain application, and the calculation formula is as follows:
wherein: plRepresenting the preference of a user to an application l in a preset application library;
t represents the number of applications installed by the user;
Sk,lindicating the similarity of the user-installed application k with respect to the application l in the preset application library.
4. The method of claim 2, wherein the pre-recommended application is an application having the same tag as 1 or more applications that the user has installed.
5. An apparatus that recommends an application based on a user installed application, comprising:
the application similarity list determining unit is used for determining a similarity list of one application relative to another application between every two applications in a preset application library;
the user preference degree determining unit is used for determining the similarity of the 1 or more applications installed by the user relative to each application in the preset application library based on the 1 or more applications installed by the user and the similarity list, and further determining the preference degree of the user to each application in the preset application library;
a recommending unit for selecting a certain number of corresponding applications from a preset application library as recommended applications based on the preference values in descending order,
the similarity list determining unit of the applications is used for calculating the similarity value of one application relative to the other application between every two applications in a preset application library, and the similarity value of one application relative to the other application between every two applications is made into a list, and the similarity of one application relative to the other application between every two applications is calculated by the following method:
wherein: k 1,2, …, nj 1,2 …, n
Sk,lRepresenting the similarity of application k relative to application l;
n represents the number of applications in the preset application library;
m represents the number of labels in the preset label set;
tk,jwhether the application k has a label j is represented as 1, and the application k is not represented as 0;
tl,jwhether the application l has a label j is represented as 1, and the application l has no label j;
rjrepresents the resolution of label j, where:
n represents the number of applications in the preset application library;
ti,jand the label j is represented by whether the application i has a label j with 1 or no 0.
6. The apparatus according to claim 5, wherein the preference determining unit of the user for the application is configured to take an accumulated sum of similarities between each of the plurality of applications installed by the user and the application as the preference of the user for the application, and the calculation formula is as follows:
wherein: plRepresenting the preference of a user to an application l in a preset application library;
t represents the number of applications installed by the user;
Sk,lindicating the similarity of the user-installed application k with respect to the application l in the preset application library.
7. An apparatus that recommends an application based on a user installed application, comprising:
the device comprises a candidate set establishing unit of pre-recommended applications, a candidate set determining unit and a pre-recommending application setting unit, wherein the candidate set establishing unit is used for selecting a plurality of applications from a preset application library as the pre-recommended applications and establishing the candidate set containing the pre-recommended applications;
the user preference determining unit is used for determining the similarity of the 1 or more applications installed by the user relative to each application in the candidate set based on the similarity list of one application relative to the other application between the 1 or more applications installed by the user and every two applications in the preset application library, and further determining the preference of the user to each pre-recommended application in the candidate set;
a recommending unit, configured to select a certain number of corresponding applications from the candidate set as recommended applications in descending order based on the preference values,
the method for determining the similarity list of one application relative to another application between every two applications in the preset application library comprises the following steps: calculating the similarity value of one application relative to another application between two applications in a preset application library, and listing the similarity values of the two applications, wherein the similarity value of the one application relative to the another application between the two applications is calculated by the following method:
wherein: k 1,2, …, nj 1,2 …, n
Sk,lRepresenting the similarity of application k relative to application l;
n represents the number of applications in the preset application library;
m represents the number of labels in the preset label set;
tk,jwhether the application k has a label j is represented as 1, and the application k is not represented as 0;
tl,jwhether the application l has a label j is represented as 1, and the application l has no label j;
rjrepresents the resolution of label j, where:
n represents the number of applications in the preset application library;
ti,jand the label j is represented by whether the application i has a label j with 1 or no 0.
8. The apparatus of claim 7, wherein the pre-recommended application is an application having the same tag as 1 or more applications that the user has installed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710072980.XA CN106844724B (en) | 2017-02-10 | 2017-02-10 | Method and device for recommending applications based on applications installed by user |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710072980.XA CN106844724B (en) | 2017-02-10 | 2017-02-10 | Method and device for recommending applications based on applications installed by user |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106844724A CN106844724A (en) | 2017-06-13 |
CN106844724B true CN106844724B (en) | 2020-10-16 |
Family
ID=59121804
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710072980.XA Active CN106844724B (en) | 2017-02-10 | 2017-02-10 | Method and device for recommending applications based on applications installed by user |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106844724B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446311A (en) * | 2018-02-06 | 2018-08-24 | 微梦创科网络科技(中国)有限公司 | A kind of APP recommendation method and devices based on social networks |
CN108734556A (en) * | 2018-05-18 | 2018-11-02 | 广州优视网络科技有限公司 | Recommend the method and device of application |
CN109040164B (en) * | 2018-05-21 | 2021-11-26 | 阿里巴巴(中国)有限公司 | Application recommendation method and device, storage medium and computer equipment |
CN109299993B (en) * | 2018-07-20 | 2023-04-18 | 平安科技(深圳)有限公司 | Product function recommendation method, terminal device and computer readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455522A (en) * | 2012-06-04 | 2013-12-18 | 北京搜狗科技发展有限公司 | Recommendation method and system of application extension tools |
CN103677866A (en) * | 2012-09-05 | 2014-03-26 | 北京搜狗科技发展有限公司 | Application program extension tool pushing method and system |
CN104808983A (en) * | 2015-03-19 | 2015-07-29 | 深圳市梦域科技有限公司 | Application program push method and server |
CN106202328A (en) * | 2016-07-01 | 2016-12-07 | 中国传媒大学 | A kind of recommendation method for new projects' cold start-up |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8977577B2 (en) * | 2011-11-30 | 2015-03-10 | At&T Intellectual Property I, L.P. | Methods, systems, and computer program products for recommending applications based on user interaction patterns |
-
2017
- 2017-02-10 CN CN201710072980.XA patent/CN106844724B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455522A (en) * | 2012-06-04 | 2013-12-18 | 北京搜狗科技发展有限公司 | Recommendation method and system of application extension tools |
CN103677866A (en) * | 2012-09-05 | 2014-03-26 | 北京搜狗科技发展有限公司 | Application program extension tool pushing method and system |
CN104808983A (en) * | 2015-03-19 | 2015-07-29 | 深圳市梦域科技有限公司 | Application program push method and server |
CN106202328A (en) * | 2016-07-01 | 2016-12-07 | 中国传媒大学 | A kind of recommendation method for new projects' cold start-up |
Also Published As
Publication number | Publication date |
---|---|
CN106844724A (en) | 2017-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107424043B (en) | Product recommendation method and device and electronic equipment | |
WO2017181612A1 (en) | Personalized video recommendation method and device | |
CN103823908B (en) | Content recommendation method and server based on user preference | |
CN106326391B (en) | Multimedia resource recommendation method and device | |
CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
CN106302085B (en) | Recommendation method and system for instant messaging group | |
CN106844724B (en) | Method and device for recommending applications based on applications installed by user | |
CN109033149B (en) | Information recommendation method and device, server and storage medium | |
CN111259173B (en) | Search information recommendation method and device | |
CN106951571B (en) | Method and device for labeling application with label | |
US20120096088A1 (en) | System and method for determining social compatibility | |
CN104462573A (en) | Method and device for displaying video retrieval results | |
US20120284283A1 (en) | Information Processing Method, Apparatus, and Computer Program | |
US20090144226A1 (en) | Information processing device and method, and program | |
CN106961636A (en) | Commodity information recommendation method and device and electronic equipment | |
CN106909688A (en) | A kind of method and apparatus that search word is recommended based on input search word | |
CN109446415A (en) | A kind of application recommendation, acquisition methods and equipment | |
CN106919692B (en) | Method and device for pushing message | |
US20130211951A1 (en) | Self learning gift recommendation engine | |
CN106919693B (en) | Method and device for improving hot word exposure coverage rate | |
CN111400609A (en) | User recommendation method and device, storage medium and server | |
CN111753204B (en) | Information pushing method and device, electronic equipment and storage medium | |
CN110110206A (en) | Relation excavation and recommended method, device, calculating equipment, storage medium between article | |
CN111274492A (en) | Information recommendation method, information recommendation device and computer readable storage medium | |
CN107562846B (en) | Method and device for recommending applications |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200902 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |