WO2018171288A1

WO2018171288A1 - Method and apparatus for tagging information stream, terminal device, and storage medium

Info

Publication number: WO2018171288A1
Application number: PCT/CN2017/120182
Authority: WO
Inventors: 潘岸腾
Original assignee: 广州优视网络科技有限公司
Priority date: 2017-03-22
Filing date: 2017-12-29
Publication date: 2018-09-27
Also published as: CN106960033B; CN106960033A

Abstract

A method for tagging an information stream, comprising: determining degrees of interest of a user to different tags on the basis a third party application installed by the user on a terminal (S1); determining degrees of matching between an information stream and the tags on the basis of the degrees of interest and information about tapping the information stream by the user (S2); and selecting a particular number of tags on the basis of the degrees of matching in a preset manner, and tagging the information stream (S3).

Description

Method, device, terminal device and storage medium for labeling information flow

Technical field

The present invention relates to the field of information processing technologies, and in particular, to a method, an apparatus, a terminal device, and a storage medium for labeling information streams.

Background technique

With the rapid development of Internet technologies and smart mobile terminal technologies, many functions implemented on computer terminals (such as shopping, reading) can also be implemented on smart mobile terminals, such as using a smart phone or a tablet. In addition, the implementation of these functions requires the installation of the corresponding application on the smart mobile terminal. For example, online shopping requires installing a Taobao client, for example, to listen to music, and to install a music player client. As a result, many software companies offer application stores or application markets, such as pea pods or PP assistants. Users can open the app store or the app market, so they can quickly search and download the various applications they need, including video playback, system tools, communication and social, online shopping, reading, etc. Of course, you can download games, etc. Entertainment app (APP).

In order to continuously improve the user's good experience in using the app store or the application market, the current app store or application market can display the app directly to the user, as shown in FIG. 1A, and also provides a new app release method: Add information to the app store, introduce and promote apps through interesting articles, short videos, or headlines, open the stream to see article content, videos or news, and have the stream at the bottom of the page. The application for downloading, as shown in FIG. 1A and FIG. 1B, when clicking on the news "Do you have the most dangerous function of WeChat?" in the information flow display page shown in FIG. 1A, the page shown in FIG. 1B is entered. In addition to the details of this news, the news provider is also provided at the bottom of the page - the third-party application "UC headline" and the download button. However, there are many sources of information sources for “information flow”. The information flow provided by many channels lacks description of information. In addition, the specifications of information description are not uniform, and the use of information flow-application store or application market does not currently have one. A good way to unify the information with irregular descriptions from various channels, so that the labeling of the information flow can not be done automatically by means of tools, and relying on manual implementation of labeling is time-consuming and laborious, not easy to do.

In the case where the information flow is not labeled, the business that carries out the personalized recommendation information flow related to the information itself may encounter many difficulties.

Summary of the invention

It is an object of embodiments of the present invention to provide a method and apparatus for labeling information streams to improve the above problems.

According to a first aspect, an embodiment of the present invention provides a method for labeling an information flow, including: determining, according to a third-party application installed by the user on the terminal, the user's interest in different tags; based on the interest degree and the user information. The click condition of the stream determines the matching degree of the information flow to the label; according to the matching degree, a corresponding number of labels are selected according to the preset manner to label the information flow.

According to a second aspect, an embodiment of the present invention provides an apparatus for labeling an information flow, including: an interest degree determining unit, configured to determine, according to a third-party application installed by the user on the terminal, the user's interest level for different labels; The matching degree determining unit is configured to determine the matching degree of the information stream to the label based on the interest degree and the user's click condition of the information flow; the labeling unit is configured to select a corresponding quantity label according to the matching degree to the information flow labeling according to the preset manner.

According to a third aspect, an embodiment of the present invention provides a terminal device, including: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory And configured to be executed by the one or more processors, the one or more programs configured to:

Determining the user's interest in different tags based on the third-party application installed by the user on the terminal;

Determining the matching degree of the information flow to the tag based on the degree of interest and the user's click on the information flow;

According to the matching degree, a corresponding number of labels are selected according to a preset manner to label the information flow.

According to a fourth aspect, an embodiment of the present invention provides a computer readable storage medium carrying one or more computer instruction programs executed by one or more processors when the computer instruction program is executed by one or more processors Methods for labeling information flows, including:

The embodiment of the invention provides a method, a device, a terminal device and a storage medium for labeling information flow, and can analyze the user by counting the third-party application installed by the user on the terminal used by the user and clicking the information flow by the user. The degree of interest in the tag, and then the degree of matching between the information stream that the user clicked and the tag is analyzed, so that a certain number of tags with the highest matching degree can be selected as the tag of the information stream, and the tag is marked, thereby realizing the application store Or the information flow provided in the application market automatically labels the label, which solves the problem that the manual labeling is time-consuming and laborious, and is not easy to complete, and the automatic labeling of the information flow is beneficial to the subsequent personalized recommendation related to the information flow itself. Information flow business.

DRAWINGS

FIG. 1A is a screenshot of an example of an existing application store adopting an information flow recommendation application;

Figure 1B is an example screenshot of a detail page of an information of an information stream;

2 is a flowchart of a method for labeling an information flow according to an embodiment of the present invention;

3 is a schematic block diagram of an apparatus for labeling an information flow according to an embodiment of the present disclosure;

FIG. 4 is a block diagram of an internal structure of a terminal device according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the embodiments of the present invention and the accompanying drawings. 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 the embodiments of the invention, which are generally described and illustrated in the figures herein, may be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention in the claims All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

The main idea of the solution is to determine the user's interest in different tags by the third-party application installed by the user on the terminal; determine the information flow tag based on the user's interest in different tags and the user clicks on the information flow. Matching degree; after obtaining the matching degree of the information stream to the label, selecting a certain number of labels as the label of the information stream according to the matching degree according to the matching degree, and marking the information flow.

First embodiment

2 is a flow chart of a method for labeling an information flow according to an embodiment of the present invention. As shown in FIG. 2, the method for labeling an information flow according to an embodiment of the present invention includes the following steps:

S1: Determine the user's interest in different tags based on the third-party application installed by the user on the terminal.

Based on the above ideas, it is necessary to count which third-party applications a user has installed so far on the terminal they use. By counting the weight of all the tags of the third-party application in the preset application library installed by the user within a certain number of days, the weight of all the tags of the application is decayed with time, and the user is attached to the third-party application. The degree of interest of different tags in the collection, the user is accumulated for the same tag's interest value due to all third-party applications installed on the terminal, thereby obtaining the user's interest in different tags. In this way, the user's interest in different tags is determined based on these installed third party applications.

First, calculate the degree of interest of each third-party application installed by the user on the terminal for different tags in the tag set, and the calculation method is as follows:

Where: cint _{p, i, j} represents the degree of interest of the third party application i in the preset application library installed by the user p on the terminal for the tag j in the tag set;

Ct1 _p,i indicates that the user p installed the third-party application i in the preset application library in the N days and maintained the number of days until today, where the user p does not install the third-party application i within N days, ct1 _p,i is N;

Tag _i,j indicates whether the third-party application i has the tag j in the preset tag set, wherein the tag _{i, j} is 1 when there is a tag j, otherwise 0;

Represents the sum of the number of labels in the preset label set that the third party application i has;

n represents the number of third-party applications in the preset application library;

m represents the number of labels in the preset label set;

N is an integer greater than zero.

N can set the number of days according to the actual needs, such as 60 days, 90 days, 180 days, and so on.

Those skilled in the art are aware of the purpose and function of developing an application store or application market, and an application library is preset in the application store or the application market, and a large number of various applications developed by different third-party application developers are placed in the application library. . In addition, third-party applications provided by the app store or the app market have one or more tags, all of which come from a collection of tags that are preset when developing the app store or app market. There is no introduction to these conventional technologies. It is.

Through the above operation, it can be counted that the third-party application in the preset application library installed by the user within a certain number of days has a weight of all the labels of the application, and the weight of the label has decayed with time, and the user is installed because the third party has installed the third party. Application and interest in different tags in the tag collection.

In addition, a third-party application that a user usually installs on a terminal that is used by the user, so that all third-party applications installed on the terminal need to accumulate interest values of the same tag, thereby obtaining that the user has different tags. The degree of interest is as follows:

Where: int _p,j represents the degree of interest of a user p for the tag j in the preset tag set;

D represents the number of third-party applications in the preset application library installed by the user p on the terminal used by the user p;

Cint _p,i,j represents the degree of interest of the third party application i in the preset application library installed by the user p on the terminal for the tag j in the tag set.

In this way, the user is accumulated for the same tag's interest value due to all the third-party applications installed on the terminal, thereby obtaining the user's interest in different tags.

S2: determining, according to the interest degree and the click condition of the user on the information flow, the matching degree of the information flow that the user clicked on the label;

After determining a user's interest in different tags, the user needs to count the user's click on the information stream, and then determine the user click based on the user's interest in different tags and the user's click on the information stream. The degree to which the information flow matches the label.

That is, the degree of interest of different users for different tags is attenuated according to the time when the user clicks on the information flow, and the matching degree of the information flow to the tags is obtained.

Specifically, the user clicks the data of the information flow, and combines the interest degree of the user with different tags, and calculates the matching degree of the information flow clicked by the user on different tags in the tag set, and the calculation method is as follows:

Where: S _l,j represents the degree of matching of the information stream 1 clicked by the user for the tag j in the preset tag set;

Ct2 _p,l represents the number of days that the user p last clicked on the information stream l today, where user p did not click on the information stream l within N days, ct2 _{p, l} is N;

Int _p,j represents the degree of interest of the user p for the tag j in the preset tag set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than 0;

Those skilled in the art know that when counting data of a user clicking on a stream of information, it is necessary to define a period of time to have a statistical result. Here, it is preferable to set a number of days for which the data of the user clicks on the information stream is compared with the terminal used by the statistical user described above. The number of days to install a third-party application is the same, for example, 60 days, 90 days, 180 days, and the like. In addition, the application store or the application market can also preset a stream library, and the information streams that need to be displayed are placed in the preset stream library.

S3: Select a corresponding quantity label according to the matching degree to label the information flow according to a preset manner.

Specifically, the step of selecting a corresponding quantity of labels according to a matching manner to label the information flow according to the matching manner includes: sorting the labels in descending order according to the matching degree of the information streams to the labels; and selecting a certain number from the arrangement according to the largest to the small Label and label the information flow.

Preferably, the corresponding number of labels are selected according to the matching degree from the largest to the smallest, and the information flow is marked. For example, 3-5 labels may be selected as labels of the information flow, that is, from large to small. Sort the 3-5 labels corresponding to the matching scores of the first 3-5. Alternatively, a certain number of labels may be randomly selected from the plurality of labels corresponding to the matching degree that is greater than or equal to the preset threshold to label the information flow, and may also be selected according to the matching degree from large to small, for example, may be selected. 3-5 labels are labeled as labels for the information stream.

The information flow involved in the embodiment of the present invention preferably refers to an information flow without a label. Of course, even if a part of the information flow is manually labeled, the information flow can be re-labeled using the method of the embodiment of the present invention.

In addition, in the above calculation of the matching degree of the information flow clicked by the user, when the tag encountered is a popular tag, for example: "social", the matching degree calculated based on the tag is relatively large; when encountered A label is an unpopular label, such as "Chinese Chess", and the matching calculated based on the label is relatively small. In order to get a more objective match, avoid the social emotions that the label itself is hot today, such as when the Chinese chess becomes a worldwide competition and the public is widely concerned, the label "Chinese Chess" will become a hot label. It is necessary to standardize the matching degree to obtain the final matching degree of the information stream to the label.

In a preferred embodiment, first, similar to the description in step S2 above, the user clicks on the data of the information stream, and in combination with the user's interest in different tags, calculates the information stream clicked by the user for the tag set. The first matching degree of the different labels is calculated as follows:

Where: S _l,j represents the first matching degree of the information stream 1 clicked by the user for the label j in the preset label set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than 0;

Then, the first matching degree is standardized, and the final matching degree of the information stream clicked by the user on the label is obtained, as follows:

Where: ptag _{l, j} represents the degree of matching between the information stream 1 clicked by the user and the tag j in the preset tag set;

S _l,j represents the first matching degree of the information stream 1 clicked by the user for the tag j in the preset tag set;

U represents the number of streams in the preset stream library;

m represents the number of labels in the preset label set.

The practical significance of performing the standardization process is to convert the matching degree of the information stream 1 clicked by the user to the label j to a multiple of the average matching degree of all the information streams for the label j, and use this multiple to measure the information flow 1 and the label j. The degree of matching between the two indicates that the higher the degree of matching of the information stream 1 to the label j, the lower the multiple indicates that the matching degree of the information stream 1 to the label j is lower. For example, the matching degree of the information stream a clicked by the user on the label b is 0.3, and the average matching degree of all the information streams to the label b is 0.1, and the final matching degree of the information stream a to the label b is 3.

According to the method for labeling information flow according to an embodiment of the present invention, by counting the third-party application installed by the user on the terminal used by the user and the user clicking the information flow, the user's interest in the label can be determined, and then the user is obtained. The degree of matching between the clicked stream and the tag, so that a certain number of tags with the highest matching degree can be selected as the tag of the stream, and the tag is marked, thereby realizing the automatic flow of information preset in the application store or the application market. Labeling labels solves the problem of time-consuming and laborious manual labeling, and it is not easy to complete. Moreover, by automatically labeling the information stream, it is beneficial to the subsequent personalized recommendation information flow related to the information flow itself.

Second embodiment

FIG. 3 is a schematic block diagram of an apparatus for labeling an information flow according to another embodiment of the present invention. As shown in FIG. 3, the apparatus for labeling an information flow according to an embodiment of the present invention includes:

a degree of interest determining unit, configured to determine, according to a third party application installed by the user on the terminal, the degree of interest of the user for different tags;

a matching degree determining unit, configured to determine a matching degree of the information stream to the tag based on the interest degree and the click condition of the user on the information flow;

And a labeling unit, configured to select, according to the matching degree, a corresponding quantity of labels to label the information flow according to a preset manner.

Preferably, the interest degree determining unit is specifically configured to determine, by counting, that each tag of the third-party application in the preset application library installed by the user in a period of time accounts for attenuating the weight of all tags of the application with time, and determining The user's interest in different tags in the tag set due to the installation of the third-party application; the interest degree determining unit is specifically used to interest the same tag for all third-party applications installed on the terminal. The degrees are accumulated to determine the user's interest in different tags.

The interest degree determining unit is further configured to calculate, by using the following formula, the interest degree of each third-party application installed by the user on the terminal for different labels in the label set:

Ct1 _p,i means that the user p installs the third-party application i in the preset application library in the N days on the terminal and keeps the number of days until today, wherein the user p does not install ct1 _p, N is N in N days;

m represents the number of labels in the preset label set;

N is an integer greater than 0;

The interest degree determining unit is further configured to determine the user's interest in different tags by using the following formula:

D represents the number of third-party applications in the preset application library installed by the user p on the terminal.

Preferably, the matching degree determining unit is specifically configured to obtain a matching degree of the information stream to the label by performing statistics on the degree of interest of different users for different tags as the user clicks on the information flow.

The matching degree determining unit is specifically configured to determine the matching degree of the information flow to the label by using the following formula:

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than zero.

As described above in the preferred embodiment of the method, it is necessary to normalize the degree of matching, so that the same degree of processing can be done here.

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than 0;

U represents the number of streams in the preset stream library;

m represents the number of labels in the preset label set.

Specifically, the labeling unit is specifically configured to arrange the labels in descending order of the matching degree of the labels according to the information flow.

The labeling unit is specifically used to select a certain number of labels from the largest to the smallest in the arrangement, and mark the information flow.

Preferably, the labeling unit selects a corresponding number of labels to mark the information flow based on the matching degree from the largest to the smallest, for example, 3-5 labels may be selected as labels of the information stream, that is, Sort the 3-5 labels corresponding to the matching degrees of the first 3-5 names from large to small. Alternatively, a certain number of labels may be randomly selected from the plurality of labels corresponding to the matching degree that are greater than or equal to the preset threshold to label the information flow, and of course, the matching degree may be selected from the largest to the smallest, for example, 3-5 labels are selected as labels for the information stream for labeling.

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the device described above in connection with FIG. 3 can refer to the corresponding process in the foregoing method embodiments, and the description is not repeated here.

According to the embodiment of the present invention, the device for labeling the information flow can determine the user's interest in the label by counting the third-party application installed by the user on the terminal used by the user and the user clicking the information flow, thereby obtaining the user. The degree of matching between the clicked stream and the tag, so that a certain number of tags with the highest matching degree can be selected as the tag of the stream, and the tag is marked, thereby realizing the automatic flow of information preset in the application store or the application market. Labeling labels solves the problem of time-consuming and laborious manual labeling, and it is not easy to complete. Moreover, by automatically labeling the information stream, it is beneficial to the subsequent personalized recommendation information flow related to the information flow itself.

A computer program product for providing a method for labeling an information stream according to an embodiment of the present invention includes a computer readable storage medium storing program code, the program code comprising instructions for executing the method described in the foregoing method embodiment For specific implementation, refer to the method embodiment, and details are not described herein again.

Fourth embodiment

To further illustrate the foregoing method for labeling information flows, the embodiment of the present invention provides a terminal device, which is specifically as follows:

As shown in FIG. 4, the terminal device includes a processor 410, a memory 420, an internal memory 430, a network interface 440, and a display screen 450 connected through a system bus. The processor 410 is configured to implement a computing function and a function of controlling the operation of the terminal device, and the processor 410 is configured to perform the method for labeling the information flow provided by the above embodiment. The processor 410 is configured to determine, according to the third party application installed by the user on the terminal, the degree of interest of the user for different tags; determining the matching degree of the information flow to the tag based on the degree of interest and the click condition of the user on the information flow; Set the mode to select a corresponding number of labels to label the information flow. The memory 420 is a non-volatile storage medium storing an operating system 421, a database 422, and a computer program for implementing the information stream labeling-based method provided by the above embodiments, and candidate intermediate data generated by executing the computer program, and Result data. Network interface 440 is used to communicate with the server, and network interface 440 includes a radio frequency transceiver.

Further, an embodiment of the present invention further provides a computer readable storage medium carrying one or more computer instruction programs, and when the computer instruction program is executed by one or more processors, one or more processors execute the implementation The method for labeling information flow includes: determining, according to a third-party application installed by the user on the terminal, the user's interest in different tags; determining the matching degree of the information flow to the tag based on the interest degree and the user's click on the information flow According to the matching degree, a corresponding number of labels are selected according to a preset manner to mark the information flow.

A person skilled in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by using hardware related to the program instructions. The foregoing program may be stored in a computer readable storage medium, and the program is executed when executed. The foregoing storage medium includes: a mobile storage device, a random access memory (RAM), a read-only memory (ROM), a magnetic disk, or an optical disk. A medium that can store program code.

Alternatively, the functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product. Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including The instructions are used to cause a computer device (which may be a personal computer, tablet, smartphone, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a removable hard disk, a read only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

The above is only a specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of changes or substitutions within the technical scope of the present invention. It should be covered by the scope of the present invention. Therefore, the scope of the invention should be determined by the scope of the appended claims.

Claims

A method of labeling information flows, including:

Determining the user's interest in different tags based on the third-party application installed by the user on the terminal;

Determining a degree of matching of the information stream to the tag based on the degree of interest and the user's click on the information stream;

And selecting a corresponding quantity label according to the matching degree to label the information flow.
The method according to claim 1, wherein the step of determining the degree of interest of the user for different tags based on a third-party application installed by the user on the terminal comprises:

By counting the weight of all the tags of the third-party application in the preset application library installed by the user in a period of days, the weight of all the tags of the application is attenuated over time, and determining that the user has installed the third-party application for the tag set. Interest in different labels;

The user is accumulated for the same tag's interest value due to all third-party applications installed on the terminal, and the user's interest in different tags is determined.
The method according to claim 1 or 2, wherein the step of determining the degree of interest of the user for different tags based on the third-party application installed by the user on the terminal comprises:

Calculate the interest of each third-party application installed by the user on the terminal for different tags in the tag set by using the following formula:

Where: cint p, i, j represents the degree of interest of the third party application i in the preset application library installed by the user p on the terminal for the tag j in the tag set;

Ct1 p,i means that the user p installs the third-party application i in the preset application library in the N days on the terminal and keeps the number of days until today, wherein the user p does not install ct1 p, N is N in N days;

Tag i,j indicates whether the third-party application i has the tag j in the preset tag set, wherein the tag i, j is 1 when there is a tag j, otherwise 0;

Represents the sum of the number of labels in the preset label set that the third party application i has;

n represents the number of third-party applications in the preset application library;

m represents the number of labels in the preset label set;

N is an integer greater than 0;

The third party application installed on the terminal accumulates the interest value of the same tag to determine the user's interest in different tags, including:

Determine the user's interest in different tags by the following formula:

Where: int p,j represents the degree of interest of a user p for the tag j in the preset tag set;

D represents the number of third-party applications in the preset application library installed by the user p on the terminal.
The method according to claim 1, wherein the step of determining the matching degree of the information stream to the tag based on the degree of interest and the user's click on the information flow comprises:

The degree of interest of different users for different tags is attenuated as the user clicks on the information flow, and the matching degree of the information flow to the tags is obtained.
The method according to claim 1 or 4, wherein the step of determining the matching degree of the information stream to the label comprises:

Determine the matching of the information flow to the label by the following formula:

Where: S l,j represents the degree of matching of the information stream 1 clicked by the user for the tag j in the preset tag set;

Ct2 p,l represents the number of days that the user p last clicked on the information stream l today, where user p did not click on the information stream l within N days, ct2 p, l is N;

Int p,j represents the degree of interest of the user p for the tag j in the preset tag set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than zero.
The method according to claim 1 or 4, wherein the step of determining the matching degree of the information stream to the label comprises:

Calculating a first matching degree of the information flow clicked by the user for different tags in the tag set by counting a user's click on the information flow and the user's interest in different tags;

The first matching degree is normalized to obtain a final matching degree of the information stream to different tags.
The method according to claim 6, wherein the information flow clicked by the user is calculated for different tags in the tag set by counting the user's click on the information stream and the user's interest in different tags. The first match, including:

The first matching degree of the information stream clicked by the user for different labels in the label set is calculated by the following formula:

Where: S l,j represents the first matching degree of the information stream 1 clicked by the user for the label j in the preset label set;

Ct2 p,l represents the number of days that the user p last clicked on the information stream l today, where user p did not click on the information stream l within N days, ct2 p, l is N;

Int p,j represents the degree of interest of the user p for the tag j in the preset tag set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than 0;

The first matching degree is normalized to obtain a final matching degree of the information stream to different labels, including:

The first matching degree is normalized by the following formula to obtain the final matching degree of the information stream to different labels:

Where: ptag l, j represents the degree of matching between the information stream 1 clicked by the user and the tag j in the preset tag set;

S l,j represents the first matching degree of the information stream 1 clicked by the user for the tag j in the preset tag set;

U represents the number of streams in the preset stream library;

m represents the number of labels in the preset label set.
The method according to any one of claims 5-7, wherein the step of selecting a corresponding number of labels to mark the information flow according to the matching degree in a preset manner comprises:

Arranging the labels in descending order according to the matching degree of the information flow to the labels;

A certain number of tags are selected from the arrangement in order from large to small, and the information flow is labeled.
A device for labeling information flows, including:

a degree of interest determining unit, configured to determine, according to a third party application installed by the user on the terminal, the degree of interest of the user for different tags;

a matching degree determining unit, configured to determine a matching degree of the information stream to the tag based on the interest degree and the click condition of the user on the information flow;

And a labeling unit, configured to select, according to the matching degree, a corresponding quantity of labels to label the information flow according to a preset manner.
The apparatus according to claim 9, wherein the interest degree determining unit is configured to collect, by counting, a third-party application in a preset application library installed by a user within a period of days, each label of the application has all the labels of the application. The weight is attenuated over time, determining the user's interest in different tags in the tag set due to the installation of the third party application;

The interest degree determining unit is further configured to accumulate the interest value of the same tag by the user for all third-party applications installed on the terminal, and determine the interest degree of the user for different tags.
The apparatus according to claim 9 or 10, wherein the interest degree determining unit is further configured to calculate, by using the following formula, the degree of interest of each third-party application installed by the user on the terminal for different labels in the label set. :

Where: cint p, i, j represents the degree of interest of the third party application i in the preset application library installed by the user p on the terminal for the tag j in the tag set;

Ct1 p,i means that the user p installs the third-party application i in the preset application library in the N days on the terminal and keeps the number of days until today, wherein the user p does not install ct1 p, N is N in N days;

Tag i,j indicates whether the third-party application i has the tag j in the preset tag set, wherein the tag i, j is 1 when there is a tag j, otherwise 0;

Represents the sum of the number of labels in the preset label set that the third party application i has;

n represents the number of third-party applications in the preset application library;

m represents the number of labels in the preset label set;

N is an integer greater than 0;

The interest degree determining unit is further configured to determine the user's interest in different tags by using the following formula:

Where: int p,j represents the degree of interest of a user p for the tag j in the preset tag set;

D represents the number of third-party applications in the preset application library installed by the user p on the terminal.
The apparatus according to claim 9, wherein the matching degree determining unit is configured to obtain a matching degree of the information stream to the label by performing statistics on the degree of interest of different users for different tags as the user clicks on the information flow.
The apparatus according to claim 9 or 12, wherein the matching degree determining unit is specifically configured to determine the matching degree of the information stream to the label by using the following formula:

Where: S l,j represents the degree of matching of the information stream 1 clicked by the user for the tag j in the preset tag set;

Ct2 p,l represents the number of days that the user p last clicked on the information stream l today, where user p did not click on the information stream l within N days, ct2 p, l is N;

Int p,j represents the degree of interest of the user p for the tag j in the preset tag set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than zero.
The apparatus according to claim 9 or 12, wherein the matching degree determining unit is specifically configured to calculate, by counting a user's click on the information stream and the user's interest in different tags, calculating the information flow clicked by the user. The first match of the different tags in the tag set;

The matching degree determining unit is further configured to perform normalization processing on the first matching degree to obtain a final matching degree of the information stream to different labels.
The device of claim 14

The matching degree determining unit is further configured to calculate, by using the following formula, a first matching degree of the information stream clicked by the user for different labels in the label set:

Where: S l,j represents the first matching degree of the information stream 1 clicked by the user for the label j in the preset label set;

Ct2 p,l represents the number of days that the user p last clicked on the information stream l today, where user p did not click on the information stream l within N days, ct2 p, l is N;

Int p,j represents the degree of interest of the user p for the tag j in the preset tag set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than 0;

The matching degree determining unit is further configured to perform normalization processing on the first matching degree by using the following formula to obtain a final matching degree of the information stream to different labels:

Where: ptag l, j represents the degree of matching between the information stream 1 clicked by the user and the tag j in the preset tag set;

S l,j represents the first matching degree of the information stream 1 clicked by the user for the tag j in the preset tag set;

U represents the number of streams in the preset stream library;

m represents the number of labels in the preset label set.
The device according to any one of claims 13-15, wherein the labeling unit is specifically configured to arrange the labels in descending order according to the matching degree of the information flow to the labels;

The labeling unit is further configured to select a certain number of labels from the largest to the smallest in the arrangement, and mark the information flow.
A terminal device comprising:

One or more processors;

Memory

One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to:

Determining the user's interest in different tags based on the third-party application installed by the user on the terminal;

Determining a degree of matching of the information stream to the tag based on the degree of interest and the user's click on the information stream;

And selecting a corresponding quantity label according to the matching degree to label the information flow.
The terminal device according to claim 17, wherein the one or more program configurations are specifically configured to:

By counting the weight of all the tags of the third-party application in the preset application library installed by the user in a period of days, the weight of all the tags of the application is attenuated over time, and determining that the user has installed the third-party application for the tag set. Interest in different labels;

The user is accumulated for the same tag's interest value due to all third-party applications installed on the terminal, and the user's interest in different tags is determined.
The terminal device according to claim 18, wherein the one or more program configurations are specifically configured to:

Calculate the interest of each third-party application installed by the user on the terminal for different tags in the tag set by using the following formula:

Where: cint p, i, j represents the degree of interest of the third party application i in the preset application library installed by the user p on the terminal for the tag j in the tag set;

Ct1 p,i means that the user p installs the third-party application i in the preset application library in the N days on the terminal and keeps the number of days until today, wherein the user p does not install ct1 p, N is N in N days;

Tag i,j indicates whether the third-party application i has the tag j in the preset tag set, wherein the tag i, j is 1 when there is a tag j, otherwise 0;

Represents the sum of the number of labels in the preset label set that the third party application i has;

n represents the number of third-party applications in the preset application library;

m represents the number of labels in the preset label set;

N is an integer greater than 0;

Wherein the one or more program configurations are specifically used to:

Determine the user's interest in different tags by the following formula:

Where: int p,j represents the degree of interest of a user p for the tag j in the preset tag set;

D represents the number of third-party applications in the preset application library installed by the user p on the terminal.
The terminal device according to claim 17, wherein the one or more program configurations are specifically configured to:

The degree of interest of different users for different tags is attenuated as the user clicks on the information flow, and the matching degree of the information flow to the tags is obtained.
The terminal device according to claim 17 or 20, wherein the one or more program configurations are specifically used to:

Determine the matching of the information flow to the label by the following formula:

Where: S l,j represents the degree of matching of the information stream 1 clicked by the user for the tag j in the preset tag set;

Ct2 p,l represents the number of days that the user p last clicked on the information stream l today, where user p did not click on the information stream l within N days, ct2 p, l is N;

Int p,j represents the degree of interest of the user p for the tag j in the preset tag set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than zero.
The terminal device according to claim 17 or 20, wherein the one or more program configurations are specifically used to:

Calculating a first matching degree of the information flow clicked by the user for different tags in the tag set by counting a user's click on the information flow and the user's interest in different tags;

The first matching degree is normalized to obtain a final matching degree of the information stream to different tags.
The terminal device according to claim 22, wherein the one or more program configurations are specifically configured to:

The first matching degree of the information stream clicked by the user for different labels in the label set is calculated by the following formula:

Where: S l,j represents the first matching degree of the information stream 1 clicked by the user for the label j in the preset label set;

Ct2 p,l represents the number of days that the user p last clicked on the information stream l today, where user p did not click on the information stream l within N days, ct2 p, l is N;

Int p,j represents the degree of interest of the user p for the tag j in the preset tag set;

m represents the number of labels in the preset label set;

U represents the number of streams in the preset stream library;

F indicates the number of users who have clicked on the information stream l;

N is an integer greater than 0;

Wherein the one or more program configurations are specifically used to:

The first matching degree is normalized by the following formula to obtain the final matching degree of the information stream to different labels:

Where: ptag l, j represents the degree of matching between the information stream 1 clicked by the user and the tag j in the preset tag set;

S l,j represents the first matching degree of the information stream 1 clicked by the user for the tag j in the preset tag set;

U represents the number of streams in the preset stream library;

m represents the number of labels in the preset label set.
The terminal device according to any one of claims 21 to 23, wherein the one or more program configurations are specifically used to:

Arranging the labels in descending order according to the matching degree of the information flow to the labels;

A certain number of tags are selected from the arrangement in order from large to small, and the information flow is labeled.
A computer readable storage medium having one or more computer program programs thereon, the one or more processors executing any one of claims 1 to 8 when the computer program program is executed by one or more processors The method described in the item.