CN107786376B - Content pushing method and device and computer equipment - Google Patents
Content pushing method and device and computer equipment Download PDFInfo
- Publication number
- CN107786376B CN107786376B CN201710986292.4A CN201710986292A CN107786376B CN 107786376 B CN107786376 B CN 107786376B CN 201710986292 A CN201710986292 A CN 201710986292A CN 107786376 B CN107786376 B CN 107786376B
- Authority
- CN
- China
- Prior art keywords
- user
- label
- application program
- click rate
- tag
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000015654 memory Effects 0.000 claims description 24
- 230000006399 behavior Effects 0.000 claims description 11
- 238000013475 authorization Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/34—Network arrangements or protocols for supporting network services or applications involving the movement of software or configuration parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/535—Tracking the activity of the user
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Information Transfer Between Computers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a content pushing method and device and computer equipment. A content push method, comprising the steps of: acquiring a tag set of a user; obtaining the click rate of each label in the label set to an application program; acquiring a Pearson correlation coefficient of each label in the label set and other labels; obtaining a weighted average value of all the labels in the label set according to the click rate of each label in the label set to the application program and the Pearson correlation coefficient of the label and other labels, and taking the weighted average value as the estimated click rate of the user to the application program; and pushing content to the user according to the estimated click rate of the application program. The content pushing method estimates the click rate of the application program by combining the Pearson correlation coefficient between the user tags and the click rate of the application program corresponding to the user tags, improves the estimation accuracy of the click rate of the application program, and can accurately push content to the user according to the estimated click rate of the application program.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a content pushing method, a content pushing device and computer equipment.
Background
In a mobile phone Application (APP) store, a traditional mobile phone application click rate estimation method is as follows: and (4) estimating the click rate of the mobile phone application program by combining artificial feature engineering and a logistic regression algorithm. However, this approach has two insurmountable drawbacks. Firstly, the characteristics in the artificial characteristic engineering are screened artificially, the method has strong subjectivity, and a large amount of useless characteristics are easy to screen to influence the accuracy of a model behind. Secondly, the logistic regression algorithm is a linear model and it is difficult to express a model with non-linear characteristics. Therefore, the traditional mobile phone application click rate estimation method cannot accurately estimate the mobile phone application click rate, so that the content cannot be accurately pushed to the user according to the traditional mobile phone application click rate estimation method. For example, according to the conventional method for estimating the click rate of the mobile phone application program, the application program cannot be accurately pushed to the user.
Disclosure of Invention
The invention aims to provide a content pushing method, a content pushing device and computer equipment, which are used for improving the accuracy of the estimated click rate of an application program, so that the content is accurately pushed to a user according to the estimated click rate of the application program.
In order to achieve the purpose, the invention provides the following technical scheme:
a content push method, comprising the steps of: acquiring a tag set of a user; obtaining the click rate of each label in the label set to an application program; acquiring a Pearson correlation coefficient of each label in the label set and other labels; obtaining a weighted average value of all the labels in the label set according to the click rate of each label in the label set to the application program and the Pearson correlation coefficient of the label and other labels, and taking the weighted average value as the estimated click rate of the user to the application program; and pushing content to the user according to the estimated click rate of the application program.
In one embodiment, the pushing content to the user according to the estimated click rate of the application includes: and pushing the application program to the user according to the estimated click rate of the application program.
In one embodiment, the pushing the application to the user according to the estimated click rate of the application includes: and confirming that the estimated click rate of the application program is greater than a threshold value, and pushing the application program to the user.
In one embodiment, the pushing the application to the user according to the estimated click rate of the application includes: and calculating the estimated click rate of the user to all the application programs in the application market, sequencing the application programs according to the estimated click rate from high to low, and pushing the application programs in the top preset number to the user.
In one embodiment, the obtaining the tab set of the user includes: and acquiring a plurality of labels of the user according to the attributes of the user to form the label set.
In one embodiment, the attribute of the user comprises registration information of the user, authorization information of the user and operation behavior of the user; the acquiring of the plurality of labels of the user comprises: acquiring a label of the user according to the registration information of the user; acquiring a label of the user according to the operation behavior of the user; and acquiring the label of the user according to the authorization information of the user.
In one embodiment, the obtaining the click rate of each tag in the tag set to the application program includes: acquiring each label in the label set; obtaining a number of users having tags in a set of tags and exposing the application; obtaining the number of users who have the label and click the application program; and calculating the ratio of the number of the users who click the application program to the number of the users who expose the application program, and taking the ratio as the click rate of the label to the application program.
In one embodiment, the obtaining the pearson correlation coefficient of each tag in the tag set with other tags includes: acquiring the Pearson correlation coefficient of each label in the label set and other labels according to the following formula:
wherein r isi,jThe Pearson correlation coefficient of a label i and a label j in the label set is represented; x represents an exposure event set of the application program, wherein a user in the exposure event set is a user with a label i or a label j and exposing the application program; f. ofx,iRepresenting an event X in the set X, whether a user has a label i, 0 representing yes, and 1 representing no; f. ofx,jIndicating an event X in the set X, whether the user has a label j, 0 indicating yes, and 1 indicating no.
In one embodiment, obtaining a weighted average of all tags in the tag set according to the click rate of each tag in the tag set to the application program and the pearson correlation coefficient between the tag and other tags, and taking the weighted average as the estimated click rate of the user to the application program includes: calculating the estimated click rate of the application program according to the following formula:
wherein, pctru,ARepresenting the estimated click rate of the application program; a represents a corresponding application program; i represents a label of the user; j represents another label of the user; r isi,jRepresenting label i and label jThe pearson correlation coefficient.
In one embodiment, the obtaining a weighted average of all tags in the tag set includes: determining the homogeneity degree of each label in the label set according to the Pearson correlation coefficient of each label in the label set and other labels; determining the weight of all the tags in the tag set according to the homogeneity degree of each tag in the tag set; and obtaining the weighted average value of all the labels in the label set according to the weights of all the labels in the label set.
A content pushing apparatus comprising: the first acquisition module is used for acquiring a tag set of a user; the second acquisition module is used for acquiring the click rate of each label in the label set to the application program; the third acquisition module is used for acquiring the Pearson correlation coefficient of each label in the label set and other labels; the computing module is used for obtaining a weighted average value of all the labels in the label set according to the click rate of each label in the label set to the application program and the Pearson correlation coefficient of the label and other labels, and taking the weighted average value as the estimated click rate of the user to the application program; and the pushing module is used for pushing the content to the user according to the estimated click rate of the application program.
A computer device, comprising: 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 applications configured to perform the content push method according to any of the embodiments described above.
Compared with the prior art, the scheme of the invention has the following advantages:
according to the content pushing method provided by the invention, the weighted average value of all the tags in the user tag set is calculated according to the click rate of each tag in the user tag set to the application program and the Pearson correlation coefficient of the tag and other tags, the weighted average value is used as the estimated click rate of the user to the application program, and finally, related content is pushed to the user according to the estimated click rate of the application program. For example, the application, or other applications similar to the application, may be pushed to the user based on the application's estimated click rate. The content pushing method estimates the click rate of the application program by combining the Pearson correlation coefficient between the user tags and the click rate of the application program corresponding to the user tags, improves the estimation accuracy of the click rate of the application program, and then accurately pushes the content to the user according to the estimated click rate of the application program. For example, when a user accesses an application program (APP) market, the click rate of the user on the application program can be accurately estimated by using the scheme, so that the application program in the market is effectively recommended to the user.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a method for pushing content according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method in one embodiment of step S20 in FIG. 1;
FIG. 3 is a flow chart of a method for pushing content according to another embodiment of the present invention;
FIG. 4 is a flow chart of a method for pushing content according to another embodiment of the present invention;
FIG. 5 is a block diagram of a content pushing device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
Exposure event definition: one user presents one application as one exposure event.
Those skilled in the art should understand that the content in the content push method of the present invention includes: applications, similar applications, application introductions, advertisements and information related to applications, and the like.
The invention provides a content pushing method. As shown in fig. 1, a content push method of the present invention includes the steps of:
and S10, acquiring the label set of the user.
The server obtains a set of tags for each of all users using the application. For example, the users who use the application include user a, user B, and user C. The server obtains a label set of a user A as { male, student and online game }, a label set of a user B as { female, student and online novel }, and a label set of a user C as { female, family female and online shopping }.
In one embodiment, the server obtains a plurality of tags of the user according to the attributes of the user to form a tag set. Specifically, for each user using the application, the user is tagged with the user's attributes and machine learning methods. The user attribute comprises registration information of the user, authorization information of the user and operation behavior of the user.
In this embodiment, step S10 includes obtaining the user 'S label based on the user' S registration information. Specifically, the user is tagged according to the registration information of the user. For example: if the gender of the user is male and the occupation of the user is student, the user is marked with tags such as male and student according to the registration information of the user.
In this embodiment, step S10 further includes obtaining the label of the user according to the operation behavior of the user. Specifically, the user is tagged according to the operation behavior of the user. For example: the user looks at the mobile phone application related to the network game (i.e. the app applied to the mobile phone), and can be labeled as a "network game user". The user sees the mobile phone application related to the quadratic element, and can be labeled with labels such as 'quadratic element user' and the like. The application program of the scheme is applicable to android, ios or windows and other systems in software, and is applicable to mobile phones, tablet computers or readers and other terminals in hardware.
In this embodiment, step S10 further includes obtaining the label of the user according to the authorization information of the user. Specifically, the user is tagged according to the authorization information of the user. For example: according to the geographic position information of the mobile phone authorized by the user, a region label 'Guangzhou user' can be marked for the user. According to the mobile phone model information authorized by the user, the user can be marked with mobile phone type labels such as 'thousand yuan' and 'high-end phone'.
And S20, obtaining the click rate of each label in the label set to the application program.
And the server respectively acquires the label set of each user, and the click rate of each label to the application program. For example, the users using the application include user a, user b, and user c. The label set of the user a is { male, student, online game }, the label set of the user b is { female, white collar, shopping }, and the label set of the user c is { male, retirement person, travel }. The server respectively obtains the click rate of the 'male' tag to the application program, the click rate of the 'student' tag to the application program and the click rate of the 'online game' tag to the application program in the user a. The server respectively obtains the click rate of the female tag to the application program, the click rate of the white-collar tag to the application program and the click rate of the shopping tag to the application program in the user b. The server respectively obtains the click rate of the 'male' tag to the application program, the click rate of the 'retired person' tag to the application program and the click rate of the 'travel' tag to the application program in the user c.
In one embodiment, as shown in fig. 2, step S20 includes the steps of:
s201, acquiring each label in the label set.
In this embodiment, the server obtains each tag in the set of tags. I.e. the server gets a set of all tags of the full library. For example, the users using the application in the full library include user a, user b, and user c. The label set of the user a is { male, student, online game }, the label set of the user b is { female, white collar, shopping }, and the label set of the user c is { male, retirement person, travel }. The server acquires all the labels in the label set, namely any label in the label set { male, student, online game, female, white collar, shopping, retirement person, travel }. S203, the number of users who have labels in the label set and expose the application program is obtained.
S203, obtaining the number of users having labels in the label set and exposing the application program.
In this embodiment, after the server obtains each tag in the tag set, the number of users who have tags in the tag set and expose the application is obtained. That is, the server obtains the users having the corresponding tags and exposing the application program according to each tag in the tag set, and counts the number of all the users having the tags in the tag set and exposing the application program.
S205, obtaining the number of users having the label and having clicked the application program.
In this embodiment, after acquiring each tag in the tag set, the server acquires the number of users having the tag and having clicked the application. That is, the server obtains the users who have the corresponding tags and have clicked the application program according to each tag in the tag set, and counts the number of the users who have all the tags in the tag set and have clicked the application program.
S207, calculating the ratio of the number of the users who click the application program to the number of the users who expose the application program, and taking the ratio as the click rate of the label to the application program.
In step S20, the click rate of each tab in the tab set to the application is obtained according to the number of users who expose the application and the number of users who click the application.
Specifically, a represents a mobile phone application. T represents the set of all labels in the user's whole library. ctri,AIndicating the click rate of tab i on mobile application a. showi,AAnd the number of the users of the mobile phone application A exposed by the mobile phone client is represented among all the users with the label i. cl isicki,AAnd the number of the users clicking the mobile phone application A in all the users with the label i is shown. The click rate of tag i on mobile application A can be expressed as:
according to the formula, the click rate of all the labels in all the label sets T in the user whole library to the mobile phone application can be obtained.
And S30, acquiring the Pearson correlation coefficient of each label in the label set and other labels.
The server obtains a user tag set, and the Pearson correlation coefficient of each tag and other tags. For example, the user tag set includes tag i and tag j. The pearson correlation coefficients for tag i and tag j may be obtained according to the following formula:
wherein r isi,jRepresenting the pearson correlation coefficients for tag i and tag j in the set. X represents an exposure event set of the application program, and users in the exposure event set X are users which have labels i or j and expose the application program. f. ofx,iIndicating an event X in the set X, whether the user has a tag i, 0 indicating yes, and 1 indicating no. f. ofx,jIndicating an event X in the set X, whether the user has a label j, 0 indicating yes, and 1 indicating no.
Similarly, the correlation coefficient between the label i and the other labels in the label set can be obtained according to the above formula. According to the formula, the server can obtain the Pearson correlation coefficient of each label and other labels in the label set.
In step S30, a pearson correlation coefficient of each tag in the tag set with other tags is obtained from the events of each tag in the tag set exposing the application and the events of other tags in the tag set exposing the application.
Above using fx,iThe event X in the set X is only one of the definition methods of the event, and besides the above formula, the pearson correlation coefficient of each tag and other tags in the tag set can be obtained in other manners.
And S40, obtaining a weighted average value of all the labels in the label set according to the click rate of each label in the label set to the application program and the Pearson correlation coefficient of the label and other labels, and taking the weighted average value as the estimated click rate of the user to the application program.
After the click rate of each label to the application program and the Pearson correlation coefficient of the label and other labels in the user label set are obtained, the weighted average value of all the labels in the label set is calculated according to the click rate of each label to the application program in the label set and the Pearson correlation coefficient of the corresponding label and other labels. The weighted average is used as the estimated click rate of the user to the application program. The weighted average (the estimated click rate of the application) may be obtained according to the following formula:
wherein, pctru,ARepresenting the estimated click rate of the application program; a represents a corresponding application program; i represents a label of the user; j represents another label of the user; r isi,jRepresenting the pearson correlation coefficients for tag i and tag j.
And S50, pushing the content to the user according to the estimated click rate of the application program.
In this embodiment, according to steps S10 to S40, the server may obtain the estimated click rate of the user for each application program in the application marketplace. And pushing corresponding content to the user according to the estimated click rate of the user to each application program. The corresponding content here may be the application itself, other applications similar to the application, advertisements and information related to the application, or introduction information of the application. For example, each application may be pushed to the user based on the user's estimated click-through rate for that application.
According to the content pushing method, the weighted average value of all the tags in the user tag set is calculated according to the click rate of each tag in the user tag set to the application program and the Pearson correlation coefficient of the tag and other tags, the weighted average value is used as the estimated click rate of the user to the application program, and then the content is accurately pushed to the user according to the estimated click rate of the application program. For example, the application may be pushed to the user based on the estimated click rate of the application, or advertisements, information, or other applications associated with the application may be pushed to the user.
The content pushing method estimates the click rate of the application program of the mobile phone by combining the Pearson correlation coefficient among the user tags and the click rate of the application program of the user tags, improves the estimation accuracy of the click rate of the application program of the mobile phone, and then accurately pushes related content to the user according to the estimated click rate of the application program. For example, the related content may include the application itself, other applications related to the application, advertisements and information related to the application, and the like.
In one embodiment, in step S40, the step of obtaining a weighted average of all tags in the tag set includes: determining the homogeneity degree of each label in the label set according to the Pearson correlation coefficient of each label in the label set and other labels; determining the weight of all the tags in the tag set according to the homogeneity degree of each tag in the tag set; and calculating the weighted average value of all the labels in the label set according to the weights of all the labels in the label set.
In one embodiment, user u is tagged according to its operational behavior, attributes, and characteristics. And calculating the click rate of all the tags of the user u to the mobile phone application A, and acquiring the Pearson correlation coefficient among all the tags of the user u. The invention predicts the click rate of a user u to a mobile phone application A according to the click rate information of a label, and the thought is as follows: inspired by the wide expert scoring method, each label is taken as an expert, a weighted average value is calculated for all the expert opinions, and the value is taken as the final criticism. The definition of the weights is determined by the pearson correlation coefficient. For a given tag, if the pearson coefficient of that tag with other tags is higher, it indicates that the tag is more homogeneous and the weight is lower. For example: in actual operation, two labels are obtained from each data channel, one label is a "male", the other label is a "man", and due to the fact that the quantity of the labels is too large and the labels are not checked for one, the two labels are both put into training data, so that the pearson correlation coefficient of the two labels is 1, and the weight of the two labels is 1/(1+1) ═ 0.5. The weight of the attribute of the man is equally distributed into two labels of 'man' and 'man'.
The quantitative expression of the click rate estimation of the application program is as follows:
pctru,Arepresenting the estimated click rate of the application program; a represents a corresponding application program; i represents a label of the user; j represents another label of the user; r isi,jRepresenting the pearson correlation coefficients for tag i and tag j.
It should be noted that, in addition to the above quantization expression, the present solution may also calculate the weighted average of all the tags in the tag set by using other expressions according to the click rate of each tag in the tag set to the application program and the pearson correlation coefficient between the tag and other tags.
In one embodiment, step S50 includes step a: and pushing the application program to the user according to the estimated click rate of the application program. Specifically, as shown in fig. 3, step a includes:
s501, confirming that the estimated click rate of the application program is larger than a threshold value, and pushing the application program to the user.
The server may obtain the estimated click rate of the user for each application program in the application store according to steps S10 to S40. When the estimated click rate of the application program is larger than a threshold value (set in advance according to actual requirements), the server pushes the application program to the user. Thus, the user may be pushed applications that are of interest to the user.
In one embodiment, as shown in fig. 4, step a further includes the steps of:
s503, calculating the estimated click rate of the user to all the application programs in the application store, sequencing the application programs according to the estimated click rate from high to low, and pushing the application programs in the top preset number to the user.
The server respectively obtains estimated click rates of the user for the plurality of application programs in the application store according to the steps S10 to S40. Thus, the server may calculate the user's estimated click-through rate for all applications in the application store. And sequencing the application programs from high to low according to the estimated click rate of each application program, thereby acquiring the application programs in the top preset number and pushing the application programs in the preset number to the user. For example, in an application store, 8 applications need to be pushed to the user. The server acquires the estimated click rate of all the application programs of the application store according to the scheme of the invention. And sequencing all the application programs from high to low according to the estimated click rate of each application program. Further, the 8 application programs ranked at the top are acquired, and the 8 application programs are pushed to the user in the application store.
The application program pushing method provided in this embodiment may filter the application programs of the mobile phone application store according to the estimation of the click rate of the application program, so as to push the application programs that are interested by the user to the user.
The invention also provides a content pushing device, as shown in fig. 5. The content pushing device comprises a first obtaining module 501, a second obtaining module 503, a third obtaining module 505, a calculating module 507 and a pushing module 509.
The first obtaining module 501 is used for obtaining a tag set of a user. The server obtains a set of tags for each of all users using the application. For example, the users who use the application include user a, user B, and user C. The server obtains a label set of a user A as { male, student and online game }, a label set of a user B as { female, student and online novel }, and a label set of a user C as { female, family female and online shopping }.
In one embodiment, the server obtains a plurality of tags of the user according to the attributes of the user to form a tag set. Specifically, for each user using the application, the user is tagged with the user's attributes and machine learning methods. The user attribute comprises registration information of the user, authorization information of the user and operation behavior of the user.
In this embodiment, the first obtaining module 501 obtains the tag of the user according to the registration information of the user. Specifically, the user is tagged according to the registration information of the user. For example: if the gender of the user is male and the occupation of the user is student, the user is marked with tags such as male and student according to the registration information of the user.
In this embodiment, the first obtaining module 501 further includes a tag for obtaining the user according to the operation behavior of the user. Specifically, the user is tagged according to the operation behavior of the user. For example: the user looks at the mobile phone application related to the network game (i.e. the app applied to the mobile phone), and can be labeled as a "network game user". The user sees the mobile phone application related to the quadratic element, and can be labeled with labels such as 'quadratic element user' and the like. The application program of the scheme is applicable to android, ios or windows and other systems in software, and is applicable to mobile phones, tablet computers or readers and other terminals in hardware.
In this embodiment, the first obtaining module 501 further includes a tag for obtaining the user according to the authorization information of the user. Specifically, the user is tagged according to the authorization information of the user. For example: according to the geographic position information of the mobile phone authorized by the user, a region label 'Guangzhou user' can be marked for the user. According to the mobile phone model information authorized by the user, the user can be marked with mobile phone type labels such as 'thousand yuan' and 'high-end phone'.
The second obtaining module 503 is configured to obtain a click rate of each tag in the tag set to the application program. And the server respectively acquires the label set of each user, and the click rate of each label to the application program. For example, the users using the application include user a, user b, and user c. The label set of the user a is { male, student, online game }, the label set of the user b is { female, white collar, shopping }, and the label set of the user c is { male, retirement person, travel }. The server respectively obtains the click rate of the 'male' tag to the application program, the click rate of the 'student' tag to the application program and the click rate of the 'online game' tag to the application program in the user a. The server respectively obtains the click rate of the female tag to the application program, the click rate of the white-collar tag to the application program and the click rate of the shopping tag to the application program in the user b. The server respectively obtains the click rate of the 'male' tag to the application program, the click rate of the 'retired person' tag to the application program and the click rate of the 'travel' tag to the application program in the user c.
In an embodiment, the second obtaining module 503 further includes the operation steps shown in fig. 2 described in the corresponding method.
The third obtaining module 505 is configured to obtain a pearson correlation coefficient of each tag in the tag set with other tags. The server obtains a user tag set, and the Pearson correlation coefficient of each tag and other tags. For example, the user tag set includes tag i and tag j. The pearson correlation coefficients for tag i and tag j may be obtained according to the following formula:
wherein r isi,jRepresenting the pearson correlation coefficients for tag i and tag j in the set. X represents an exposure event set of the application program, and users in the exposure event set X are users which have labels i or j and expose the application program. f. ofx,iRepresenting events in set Xx, whether the user has a label i, 0 means present, 1 means not present. f. ofx,jIndicating an event X in the set X, whether the user has a label j, 0 indicating yes, and 1 indicating no.
Similarly, the correlation coefficient between the label i and the other labels in the label set can be obtained according to the above formula. According to the formula, the server can obtain the Pearson correlation coefficient of each label and other labels in the label set. In the third obtaining module 505, the pearson correlation coefficient of each tag in the tag set and other tags is obtained according to the event of exposing the application program of each tag in the tag set and the event of exposing the application program of other tags in the tag set.
Above using fx,iThe event X in the set X is only one of the definition methods of the event, and besides the above formula, the pearson correlation coefficient of each tag and other tags in the tag set can be obtained in other manners.
The calculation module 507 is configured to obtain a weighted average of all tags in the tag set according to the click rate of each tag in the tag set to the application program and the pearson correlation coefficient between the tag and other tags, and use the weighted average as the estimated click rate of the user to the application program.
After the click rate of each label to the application program and the Pearson correlation coefficient of the label and other labels in the user label set are obtained, the weighted average value of all the labels in the label set is calculated according to the click rate of each label to the application program in the label set and the Pearson correlation coefficient of the corresponding label and other labels. The weighted average is used as the estimated click rate of the user to the application program. The weighted average (the estimated click rate of the application) may be obtained according to the following formula:
wherein, pctru,ARepresenting the estimated click rate of the application program; a represents a corresponding application program; i represents a userA label of (a); j represents another label of the user; r isi,jRepresenting the pearson correlation coefficients for tag i and tag j.
The pushing module 509 is configured to push the content to the user according to the estimated click rate of the application. In this embodiment, according to steps S10 to S40, the server may obtain the estimated click rate of the user for each application program in the application marketplace. And pushing the corresponding application program to the user according to the estimated click rate of the user to each application program.
The invention also provides computer equipment. The computer device includes: 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 applications configured to perform the content push method of any of the embodiments described above.
Fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention. Such as servers, personal computers, and network appliances. As shown in fig. 6, the apparatus includes devices such as a processor 603, a memory 605, an input unit 607, and a display unit 609. Those skilled in the art will appreciate that the device configuration means shown in fig. 6 do not constitute a limitation of all devices and may include more or less components than those shown, or some components in combination. The memory 605 may be used to store the application program 601 and various functional modules, and the processor 603 executes the application program 601 stored in the memory 605, thereby performing various functional applications of the device and data processing. The memory may be internal or external memory, or include both internal and external memory. The memory may comprise Read Only Memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or random access memory. The external memory may include a hard disk, a floppy disk, a ZIP disk, a usb-disk, a magnetic tape, etc. The disclosed memory includes, but is not limited to, these types of memory. The disclosed memory is by way of example only and not by way of limitation.
The input unit 607 is used for receiving input of signals and receiving keywords input by a user. The input unit 607 may include a touch panel and other input devices. The touch panel can collect touch operations of a user on or near the touch panel (for example, operations of the user on or near the touch panel by using any suitable object or accessory such as a finger, a stylus and the like) and drive the corresponding connecting device according to a preset program; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., play control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like. The display unit 609 may be used to display information input by the user or information provided to the user and various menus of the computer device. The display unit 609 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 603 is a control center of the computer device, connects various parts of the entire computer using various interfaces and lines, and performs various functions and processes data by operating or executing software programs and/or modules stored in the memory 605 and calling data stored in the memory.
In one embodiment, the device includes one or more processors 603, as well as one or more memories 605, one or more applications 601. Wherein the one or more applications 601 are stored in the memory 605 and configured to be executed by the one or more processors 603, the one or more applications 601 configured to perform the content push method of the above embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the storage medium may include a memory, a magnetic disk, an optical disk, or the like.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (12)
1. A content push method, comprising the steps of:
acquiring a tag set of a user using an application program;
obtaining the click rate of each label in the label set to an application program;
acquiring a Pearson correlation coefficient of each label in the label set and other labels;
obtaining a weighted average value of all the labels in the label set according to the click rate of each label in the label set to the application program and the Pearson correlation coefficient of the label and other labels, and taking the weighted average value as the estimated click rate of the user to the application program;
and pushing content to the user according to the estimated click rate of the application program.
2. The content pushing method according to claim 1, wherein the pushing content to the user according to the estimated click-through rate of the application comprises:
and pushing the application program to the user according to the estimated click rate of the application program.
3. The content pushing method according to claim 2, wherein the pushing the application to the user according to the estimated click-through rate of the application comprises:
and confirming that the estimated click rate of the application program is greater than a threshold value, and pushing the application program to the user.
4. The content pushing method according to claim 2, wherein the pushing the application to the user according to the estimated click-through rate of the application comprises:
and calculating the estimated click rate of the user to all the application programs in the application market, sequencing the application programs according to the estimated click rate from high to low, and pushing the application programs in the top preset number to the user.
5. The content pushing method according to claim 1, wherein the obtaining of the tab set of the user comprises:
and acquiring a plurality of labels of the user according to the attributes of the user to form the label set.
6. The content pushing method according to claim 5, wherein the attributes of the user include registration information of the user, authorization information of the user, and operation behavior of the user;
the acquiring of the plurality of labels of the user comprises:
acquiring a label of the user according to the registration information of the user;
acquiring a label of the user according to the operation behavior of the user;
and acquiring the label of the user according to the authorization information of the user.
7. The content pushing method according to claim 1, wherein the obtaining a click-through rate of each tag in the tag set to the application comprises:
acquiring each label in the label set;
obtaining a number of users having tags in a set of tags and exposing the application;
obtaining the number of users who have the label and click the application program;
and calculating the ratio of the number of the users who click the application program to the number of the users who expose the application program, and taking the ratio as the click rate of the label to the application program.
8. The content push method according to claim 1, wherein the obtaining of the pearson correlation coefficient of each tag with other tags in the tag set comprises:
acquiring the Pearson correlation coefficient of each label in the label set and other labels according to the following formula:
wherein r isi,jThe Pearson correlation coefficient of a label i and a label j in the label set is represented; x represents an exposure event set of the application program, wherein a user in the exposure event set is a user with a label i or a label j and exposing the application program; f. ofx,iRepresenting an event X in the set X, whether a user has a label i, 0 representing yes, and 1 representing no; f. ofx,jIndicating an event X in the set X, whether the user has a label j, 0 indicating yes, and 1 indicating no.
9. The content push method according to claim 1, wherein obtaining a weighted average of all the tags in the tag set according to the click rate of each tag in the tag set to the application and the pearson correlation coefficient between the tag and other tags, and taking the weighted average as the estimated click rate of the user to the application comprises:
calculating the estimated click rate of the application program according to the following formula:
wherein, pctru,ARepresenting the estimated click rate of the application program; a represents a corresponding application program; i.e. iA tag representing a user; j represents another label of the user; r isi,jPearson correlation coefficient, ctr, representing label i and label ji,AIndicating the click rate of tab i on application a.
10. The method according to claim 1, wherein the obtaining a weighted average of all tags in the tag set comprises:
determining the homogeneity degree of each label in the label set according to the Pearson correlation coefficient of each label in the label set and other labels;
determining the weight of all the tags in the tag set according to the homogeneity degree of each tag in the tag set;
and obtaining the weighted average value of all the labels in the label set according to the weights of all the labels in the label set.
11. A content pushing apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a tag set of a user using an application program;
the second acquisition module is used for acquiring the click rate of each label in the label set to the application program;
the third acquisition module is used for acquiring the Pearson correlation coefficient of each label in the label set and other labels;
the computing module is used for obtaining a weighted average value of all the labels in the label set according to the click rate of each label in the label set to the application program and the Pearson correlation coefficient of the label and other labels, and taking the weighted average value as the estimated click rate of the user to the application program;
and the pushing module is used for pushing the content to the user according to the estimated click rate of the application program.
12. A computer device, comprising:
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 applications configured to perform the content push method of any of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710986292.4A CN107786376B (en) | 2017-10-20 | 2017-10-20 | Content pushing method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710986292.4A CN107786376B (en) | 2017-10-20 | 2017-10-20 | Content pushing method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107786376A CN107786376A (en) | 2018-03-09 |
| CN107786376B true CN107786376B (en) | 2021-06-04 |
Family
ID=61435131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710986292.4A Active CN107786376B (en) | 2017-10-20 | 2017-10-20 | Content pushing method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107786376B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612548B (en) * | 2020-05-27 | 2023-08-29 | 恩亿科(北京)数据科技有限公司 | Information acquisition method, information acquisition device, computer equipment and readable storage medium |
| CN116055551A (en) * | 2022-11-18 | 2023-05-02 | 北京奇艺世纪科技有限公司 | Information pushing method, device and system, electronic equipment and storage medium |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100539503C (en) * | 2005-12-31 | 2009-09-09 | 华为技术有限公司 | Information issuing system, public media information publication system and dissemination method |
| CN103488788B (en) * | 2011-12-27 | 2019-03-08 | 北京奇虎科技有限公司 | Method and device for automatic application recommendation |
| CN104052714B (en) * | 2013-03-12 | 2019-02-26 | 腾讯科技（深圳）有限公司 | The method for pushing and server of multimedia messages |
| CN104574124B (en) * | 2013-10-10 | 2018-07-17 | 深圳市腾讯计算机系统有限公司 | Determine the method and device of the bandwagon effect of ad data |
| US11113345B2 (en) * | 2014-07-17 | 2021-09-07 | Bigtincan Holdings Limited | Method and system for providing contextual electronic content |
| CN104268644A (en) * | 2014-09-23 | 2015-01-07 | 新浪网技术(中国)有限公司 | Method and device for predicting click frequency of advertisement at advertising position |
| CN104915861A (en) * | 2015-06-15 | 2015-09-16 | 浙江经贸职业技术学院 | An electronic commerce recommendation method for a user group model constructed based on scores and labels |
| CN105893406A (en) * | 2015-11-12 | 2016-08-24 | 乐视云计算有限公司 | Group user profiling method and system |
| CN106503269A (en) * | 2016-12-08 | 2017-03-15 | 广州优视网络科技有限公司 | Method, device and server that application is recommended |
| CN106803190A (en) * | 2017-01-03 | 2017-06-06 | 北京掌阔移动传媒科技有限公司 | A kind of ad personalization supplying system and method |
| CN106777396A (en) * | 2017-03-01 | 2017-05-31 | 合网络技术（北京）有限公司 | The put-on method and device of a kind of promotion message |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
-
2017
- 2017-10-20 CN CN201710986292.4A patent/CN107786376B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107786376A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6615362B2 (en) | Method and apparatus for obtaining user caricature | |
| JP6267344B2 (en) | Content selection using quality control | |
| WO2020192013A1 (en) | Directional advertisement delivery method and apparatus, and device and storage medium | |
| US20200356572A1 (en) | Search ranking method and apparatus, electronic device and storage medium | |
| WO2019085327A1 (en) | Electronic device, product recommendation method and system, and computer readable storage medium | |
| US9715486B2 (en) | Annotation probability distribution based on a factor graph | |
| US20200286154A1 (en) | Utilizing item-level importance sampling models for digital content selection policies | |
| US10559004B2 (en) | Systems and methods for establishing and utilizing a hierarchical Bayesian framework for ad click through rate prediction | |
| CN108022007B (en) | Method and device for predicting daily active user number of target application and terminal equipment | |
| CN110889725B (en) | Online advertisement CTR estimation method, device, equipment and storage medium | |
| CN107729473B (en) | Article recommendation method and device | |
| US9483806B2 (en) | Aggregating content related to a notable individual | |
| WO2019061664A1 (en) | Electronic device, user's internet surfing data-based product recommendation method, and storage medium | |
| CN112035320B (en) | Service monitoring method and device, electronic equipment and readable storage medium | |
| US20220114607A1 (en) | Method, apparatus and computer readable storage medium for data processing | |
| CN113420227B (en) | Training method of click rate estimation model, click rate estimation method and device | |
| CN114117221A (en) | Information recommendation method, device, and computer-readable storage medium | |
| US20210034635A1 (en) | Intent based second pass ranker for ranking aggregates | |
| CN107786376B (en) | Content pushing method and device and computer equipment | |
| US10296924B2 (en) | Document performance indicators based on referral context | |
| US20130218960A1 (en) | Method and system for providing a structured topic drift for a displayed set of user comments on an article | |
| CN110472166A (en) | Method and apparatus for showing the page | |
| CN112133420A (en) | Data processing method, device and computer readable storage medium | |
| CN114697711B (en) | Method and device for recommending anchor, electronic equipment and storage medium | |
| WO2018205642A1 (en) | Video revenue calculation modeling device and method, video recommendation device and method, server, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200422 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510640 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |