CN108804462B - Advertisement recommendation method and device and server - Google Patents
Advertisement recommendation method and device and server Download PDFInfo
- Publication number
- CN108804462B CN108804462B CN201710304206.7A CN201710304206A CN108804462B CN 108804462 B CN108804462 B CN 108804462B CN 201710304206 A CN201710304206 A CN 201710304206A CN 108804462 B CN108804462 B CN 108804462B
- Authority
- CN
- China
- Prior art keywords
- user
- characteristic
- feature
- attribute
- attributes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Abstract
The embodiment of the invention discloses an advertisement recommendation method, an advertisement recommendation device and a server, wherein behavior data of a first object are obtained, and the behavior data comprise data information of at least one characteristic attribute related to payment capacity; processing the data information of each characteristic attribute of the first object respectively to obtain a characteristic value of each characteristic attribute of the first object; determining a weight for each of the feature attributes; determining a scoring result of the first object according to the characteristic value and the corresponding weight of each characteristic attribute of the first object; and determining the user grade to which the first object belongs based on the scoring result, and recommending the advertisement corresponding to the determined user grade to the first object, so that the payment capacity of the object is evaluated based on the behavior data of the object which is more prone to reflect the payment capacity of the object, and the effective popularization of the advertisement in computer application is further ensured.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an advertisement recommendation method, an advertisement recommendation device and a server.
Background
With the rapid development of network technology, computer applications have become an important tool for people to recommend advertisements. When the computer is applied to the process of recommending advertisements, in order to reduce the occurrence of the situation that the advertisement receiver generates a negative emotion to the received advertisements and further influences the promotion effect of the advertisements, the computer usually avoids recommending advertisements which are not matched with the payment capability of the advertisement receiver to the advertisement receiver as much as possible. For example, when the payment capacity of the advertisement receiver is 5000 yuan, if the payment capacity required for the advertisement recommended to the advertisement receiver is 5 ten thousand yuan, the advertisement may be considered as harassment information by the advertisement receiver to a great extent, which may cause the advertisement receiver to generate an emotional aversion and affect the popularization of the advertisement.
In the prior art, the payment capability of a user is determined by directly utilizing data such as payroll details, bank flow and the like of the user, and then information matched with the payment capability is spread to the user. However, it has been found that the payment ability of the user determined in this way tends to reflect the income ability of the user more, and has no great correlation with the real payment ability of the user.
In view of the above, it is an urgent need to provide an advertisement recommendation method, apparatus, and server to evaluate the payment capability of a user and further ensure effective popularization of advertisements in computer applications.
Disclosure of Invention
In view of this, embodiments of the present invention provide an advertisement recommendation method, an advertisement recommendation device, and a server, so as to implement evaluation on payment capability of a user, thereby ensuring effective popularization of an advertisement in computer applications.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
an advertisement recommendation method comprising:
acquiring behavior data of a first user, wherein the behavior data comprises data information of at least one characteristic attribute related to the payment capacity;
respectively processing the data information of each characteristic attribute of the first user based on the behavior data of at least one second user to obtain a characteristic value of each characteristic attribute of the first user;
determining a weight of each of the feature attributes using the feature value of each of the feature attributes of the first user and the feature value of each of the feature attributes of each of the second users;
obtaining scores of all the characteristic attributes of the first user according to the characteristic values and the corresponding weights of all the characteristic attributes of the first user, and determining the score result of the first user according to the scores of all the characteristic attributes of the first user;
and determining a user grade to which the first user belongs based on the scoring result, and recommending advertisements corresponding to the determined user grade to the first user.
An advertisement recommendation device comprising:
a behavior data acquisition unit for acquiring behavior data of a first user, the behavior data including data information of at least one characteristic attribute related to payment capability;
a feature value determining unit, configured to separately process data information of each feature attribute of the first user based on behavior data of at least one second user, to obtain a feature value of each feature attribute of the first user;
a weight determination unit configured to determine a weight of each of the feature attributes using a feature value of each of the feature attributes of the first user and a feature value of each of the feature attributes of each of the second users;
the first scoring result calculating unit is used for obtaining the scores of the characteristic attributes of the first user according to the characteristic values and the corresponding weights of the characteristic attributes of the first user and determining the scoring result of the first user according to the scores of the characteristic attributes of the first user;
and the first advertisement recommending unit is used for determining the user grade of the first user based on the scoring result and recommending the advertisement corresponding to the determined user grade to the first user.
An advertisement recommendation server comprising a memory for storing a program and a processor for invoking the program, the program for:
acquiring behavior data of a first user, wherein the behavior data comprises data information of at least one characteristic attribute related to the payment capacity;
respectively processing the data information of each characteristic attribute of the first user based on the behavior data of at least one second user to obtain a characteristic value of each characteristic attribute of the first user;
determining a weight of each of the feature attributes using the feature value of each of the feature attributes of the first user and the feature value of each of the feature attributes of each of the second users;
obtaining scores of all the characteristic attributes of the first user according to the characteristic values and the corresponding weights of all the characteristic attributes of the first user, and determining the score result of the first user according to the scores of all the characteristic attributes of the first user;
and determining a user grade to which the first user belongs based on the scoring result, and recommending advertisements corresponding to the determined user grade to the first user.
The embodiment of the invention discloses an advertisement recommendation method, an advertisement recommendation device and a server, wherein behavior data of a first user are obtained, and the behavior data comprise data information of at least one characteristic attribute related to payment capacity; processing the data information of each characteristic attribute of the first user respectively to obtain a characteristic value of each characteristic attribute of the first user; determining a weight for each of the feature attributes; determining a scoring result of the first user according to the characteristic value and the corresponding weight of each characteristic attribute of the first user; and determining the user grade to which the first user belongs based on the scoring result, and recommending the advertisement corresponding to the determined user grade to the first user, so that the payment capacity of the user is evaluated based on the behavior data of the user which is more prone to reflecting the payment capacity of the user, and further the effective popularization of the advertisement in computer application is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an advertisement recommendation method according to an embodiment of the present application;
fig. 2 is a flowchart of a method for unifying, for each feature attribute, data information of the feature attribute of the first user and data information of the feature attribute of behavior data of at least one second user to determine a feature value of the feature attribute of the first user and a feature value of the feature attribute of each second user according to an embodiment of the present application;
fig. 3 is a flowchart of a method for determining a value represented by data information of the characteristic attribute of the first user according to an embodiment of the present application;
fig. 4 is a flowchart of a method for determining a weight of each feature attribute of the first user by using a feature value of each feature attribute of the first user and a feature value of each feature attribute of each second user according to an embodiment of the present application;
fig. 5 is a flowchart of a method for determining a weight of each of the feature attributes according to the obtained variation values respectively corresponding to the feature attributes according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an advertisement recommendation device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a feature value determination unit provided in an embodiment of the present application in detail;
fig. 8 is a schematic structural diagram of a weight determining unit provided in an embodiment of the present application in detail;
fig. 9 is a schematic structural diagram of an advertisement recommendation server according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example (b):
the embodiment of the application provides an advertisement recommendation method which is applied to a first computer application, wherein the first computer application is a third-party application. The above is merely a preferred mode of application of the advertisement recommendation method provided in the embodiment of the present application, and is not limited herein.
Fig. 1 is a flowchart of an advertisement recommendation method according to an embodiment of the present application.
As shown in fig. 1, the method includes:
s101, obtaining a user data set, wherein the user data set comprises behavior data of a first user and at least one second user, and the behavior data comprises data information of at least one characteristic attribute related to payment capacity.
Optionally, the behavior data of each user (first user/second user) includes data information of at least one characteristic attribute related to the payment capability of the user. The characteristic attribute corresponding to the behavior data of each user is completely the same as the characteristic attribute corresponding to the behavior data of each other user. If it is determined that data information of a feature attribute corresponding to behavior data of a user does not need to be acquired, the data information of the feature attribute can be represented in a mode of setting the data information of the feature attribute to be a null/preset value, and accordingly, in the execution process of a subsequent advertisement recommendation method, the data information of the feature attribute can be determined to represent a numerical value, and the numerical value is 0.
S102, respectively processing data information of each characteristic attribute of the first user based on behavior data of at least one second user to obtain a characteristic value of each characteristic attribute of the first user;
optionally, the processing, based on behavior data of at least one second user, data information of each feature attribute of the first user is respectively processed to obtain a feature value of each feature attribute of the first user, and the processing includes: and for each characteristic attribute, unifying the data information of the characteristic attribute of the first user and the data information of the characteristic attribute included in the behavior data of at least one second user to obtain the characteristic value of the characteristic attribute of the first user.
Optionally, for each feature attribute, unifying the data information of the feature attribute of the first user and the data information of the feature attribute included in the behavior data of the at least one second user to obtain a feature value of the feature attribute of the first user, where the method includes: and for each characteristic attribute, performing unification processing on the data information of the characteristic attribute of the first user and the data information of the characteristic attribute of the behavior data of at least one second user, and determining a characteristic value of the characteristic attribute of the first user and a characteristic value of the characteristic attribute of each second user.
Optionally, please refer to fig. 2, for a method for unifying, for each feature attribute, data information of the feature attribute of the first user and data information of the feature attribute of behavior data of at least one second user, and determining a feature value of the feature attribute of the first user and a feature value of the feature attribute of each second user.
As shown in fig. 2, the method includes:
s201, determining a numerical value represented by data information of each characteristic attribute of the first user;
optionally, the at least one characteristic attribute associated with the payment capability includes: a first characteristic attribute, a second characteristic attribute, a third characteristic attribute, a fourth characteristic attribute, a fifth characteristic attribute, a sixth characteristic attribute, a seventh characteristic attribute, an eighth characteristic attribute, a ninth characteristic attribute, a tenth characteristic attribute, and/or an eleventh characteristic attribute.
Wherein the first characteristic attribute indicates a hardware device that logged into the second computer application the most number of times within the first historical time period; a second characteristic attribute indicates hardware devices logged into the second computer application within the first historical time period; a third characteristic attribute indicating a total amount of each transaction message generated by the user based on the second computer application over the first historical period of time; the fourth characteristic attribute indicates an importance degree value of the user in the second computer application in the first historical time period (the importance degree value can be called a pagerank value) which is obtained by utilizing a pagerank algorithm and based on the number of red packets which are sent and received by the user in the first historical time period by the second computer application; a fifth characteristic attribute indicating a total amount of red packs issued by the user over the first historical period of time based on the second computer application; a sixth characteristic attribute indicates a number of users that are touched by a user based on a red envelope issued by the second computer application over the first historical period of time; the seventh characteristic attribute indicating a difference between a total amount of red packs issued and a total amount of red packs received by the user over the first historical period of time based on the second computer application; an eighth feature attribute indicating a number of transnational trips that a user has achieved within the first historical time period based on the second computer application; a ninth feature attribute indicating a number of domestic cross-market trips that the user has achieved within the first historical time period based on the second computer application; a tenth characteristic attribute indicating an average travel distance of the user for each trip (the trips including a cross-country trip and a domestic cross-market trip) within the first historical time period based on the second computer application; an eleventh feature attribute indicates a cell in which the user resides within the first historical time period, determined from information reported by the second computing application.
The above is only the preferred information of at least one characteristic attribute related to the payment capability included in the behavior data provided in the embodiment of the present application, and the inventor can arbitrarily set the specific content of at least one characteristic attribute related to the payment capability according to his own needs, which is not limited herein.
Optionally, in this embodiment of the application, the data information of the at least one characteristic attribute related to the payment capability is obtained according to the information reported by the second computer application. The second computer application is a third party application, and the first computer application is the same as the second computer application, or the first computer application is different from the second computer application. When the first computer application is the same as the second computer application, the first computer application is a functional component in the second computer application.
Preferably, the eleventh characteristic attribute indicates a cell where the user lives in within the first historical time period, which is determined according to the information reported by the second computing application, and a manner of acquiring the data information of the eleventh characteristic attribute of the behavior data of the first user is now described:
receiving information (the information comprises target information) of a first user reported by a second computer application, wherein the target information comprises all check-in information of the first user reported by the second computer application based on check-in of the second computer application in the first historical time period, and the check-in information comprises a check-in position and a check-in time. Removing the check-in information of which the check-in time meets a preset first time range from the target information to obtain at least one piece of first check-in information; determining at least one second check-in information with the lowest personnel flowing probability of the check-in position from the at least one first check-in information; determining third check-in information from the second check-in information, wherein the number of days the first user checked-in at the check-in position of the third check-in information in the first historical time period is the largest.
Optionally, the calculation method of the person flow probability of the check-in position includes: and acquiring all third check-in information reported by a second computer application, wherein the third check-in information is based on check-in of all users (the first user and the at least one second user) in a second historical time period and all fourth check-in information is based on check-in of the second computer application in a third historical time period.
Determining all check-in positions of all third check-in information and all fourth check-in information, determining all users corresponding to the check-in positions from all third check-in information as a first user set and determining all users corresponding to the check-in positions from all fourth check-in information as a second user set aiming at each check-in position; calculating the intersection of the first user set and the second user set (the number of the same users existing between the first user set and the second user set), calculating the union of the first user set and the second user set (the total number of the users of the first user set and the second user set), dividing the union by the intersection to obtain a first result, and taking a second result obtained by subtracting the first result from 1 as the personnel flow probability of the check-in position.
Optionally, the second history time period and the third history time period are two adjacent time periods, for example, the second history time period is 2016, 6 months, and the third history time period is 2016, 7 months.
Preferably, the first historical period includes the second historical period and the third historical period, for example, if the second historical period is 2016, 6 months, the third historical period is 2016, 7 months, and the first historical period is 2016, 1-7 months.
Optionally, the acquiring the behavior data of the first user includes: determining original behavior data of a first user; and eliminating abnormal data in the original behavior data to obtain the behavior data of the first user.
It should be noted that: the determined original behavior data of the first user is the received information of the first user reported by the second computer application.
For ease of understanding, the description will now be made with respect to the characteristic attributes:
and for the first characteristic attribute and the second characteristic attribute, determining first information in the original behavior data of the first user, wherein the first information comprises equipment information, reported by the second computer application, of hardware equipment used by the first user for logging in the second computer application each time within the first historical time period. And taking the device information indicating the non-mobile phone device in the first information as abnormal data, and removing the abnormal data from the original behavior data. And then acquiring the data information of the first characteristic attribute and the data information of the second characteristic attribute according to the first information after the abnormal data is removed.
For the third feature attributes, determining second information in the raw behavior data of the first user, the second information comprising respective transaction information generated by the first user based on the second computer application over the first historical time period. And taking each transaction information of which the transaction amount does not meet the preset transaction amount threshold value in the second information as abnormal data, and removing the abnormal data from the original behavior data. And then acquiring data information of a third characteristic attribute according to the second information after the abnormal data is removed.
For the fourth, fifth, sixth, and seventh feature attributes, determining third information in the raw behavior data of the first user, the third information including red packet information for each red packet transceived by the first user based on the second computer application over the first historical time period. And taking each piece of red packet information of which the sent red packet amount does not meet a preset red packet amount threshold value as abnormal data, and removing the abnormal data from the original behavior data.
It should be noted that: and if the total amount of the red packets sent by the first user based on the second computer application in the first historical time period does not reach the preset amount of the red packets sent, determining that the data information of the fourth characteristic attribute, the fifth characteristic attribute, the sixth characteristic attribute and the seventh characteristic attribute of the first user does not need to be acquired. And further acquiring data information of a fourth characteristic attribute, data information of a fifth characteristic attribute, data information of a sixth characteristic attribute and data information of a seventh characteristic attribute according to the third information from which the abnormal data are removed.
And for the eighth characteristic attribute, the ninth characteristic attribute and the tenth characteristic attribute, determining fourth information in the original behavior data of the first user, wherein the fourth information comprises cross-country trip data and domestic cross-market trip data reported by the first user based on the second computer application in the first historical time period. And taking each piece of cross-country trip data/domestic cross-market trip data with positioning errors caused by abnormal reasons as abnormal data, and removing the abnormal data from the original behavior data. And further acquiring data information of an eighth characteristic attribute, data information of a ninth characteristic attribute and data information of a tenth characteristic attribute according to the fourth information from which the abnormal data are removed.
For an eleventh feature attribute, determining fifth information (i.e. the above target information) in the original behavior data of the first user, where the fifth information includes all check-in information reported by the second computer application, of the first user checked in based on the second computer application in the first historical time period, and the check-in information includes a check-in location and a check-in time. The step of "removing the check-in information whose check-in time satisfies a preset first time range from the target information to obtain at least one first check-in information" may be regarded as a process of removing abnormal data from fifth information of the original behavior data. And further acquiring data information of the eleventh characteristic attribute according to the fifth information from which the abnormal data are removed.
S202, determining the ranking of the first user in all users according to the numerical value represented by the data information of the characteristic attribute of the first user, wherein all users comprise the first user and the at least one second user;
optionally, after determining the value represented by the data information of the characteristic attribute of the first user, determining the value represented by the data information of the characteristic attribute of each second user of the at least one second user; and sorting the determined values of all the users (the first user and all the second users) in a descending order, and determining the sorting of the first users among all the users and the sorting of each second user among all the users.
S203, obtaining the characteristic value of the characteristic attribute of the first user and the characteristic value of the characteristic attribute of each second user based on the number of all the users and the sorting ordinal of the first user in all the users.
Optionally, the feature value of the feature attribute of the first user is determined according to the number of the users and the ranking ranks of the first user among the users.
Optionally, for each second user, the manner of determining the feature value of the feature attribute of the second user is as follows: and determining the characteristic value of the characteristic attribute of the second user according to the number of the users and the sorting ordinal of the second user in all the users.
S103, determining the weight of each characteristic attribute by using the characteristic value of each characteristic attribute of the first user and the characteristic value of each characteristic attribute of each second user;
s104, obtaining scores of the characteristic attributes of the first user according to the characteristic values and the corresponding weights of the characteristic attributes of the first user, and determining a score result of the first user according to the scores of the characteristic attributes of the first user;
s105, determining the user grade of the first user based on the grading result, and recommending the advertisement corresponding to the determined user grade to the first user.
Optionally, a plurality of user grades with different levels are preset, and each user grade corresponds to a corresponding scoring range; after the scoring result of the first user is determined, determining the user grade corresponding to the scoring range to which the scoring result of the first user belongs as the user grade to which the first user belongs.
Optionally, advertisements corresponding to each user rank are preset, and after the user rank to which the first user belongs is determined, the advertisements corresponding to the user rank to which the first user belongs are recommended to the first user.
Further, in an advertisement recommendation method provided in an embodiment of the present application, the method further includes: obtaining scores of the characteristic attributes of the second user by using the characteristic values and the corresponding weights of the characteristic attributes of the second user, and determining the score result of the second user according to the scores of the characteristic attributes of the second user; and determining the user grade of the second user based on the grading result, and recommending advertisements corresponding to the determined user grade to the second user.
Optionally, each of the at least one second user in the advertisement recommendation method provided in this embodiment of the application may perform role exchange with the first user, so that the second user performing role exchange is used as the first user in the execution process of the advertisement recommendation method, and the first user performing role exchange is used as the second user in the execution process of the advertisement recommendation method.
The embodiment of the invention discloses an advertisement recommendation method, which comprises the steps of obtaining behavior data of a first user, wherein the behavior data comprises data information of at least one characteristic attribute related to payment capacity; processing the data information of each characteristic attribute of the first user respectively to obtain a characteristic value of each characteristic attribute of the first user; determining a weight for each of the feature attributes; determining a scoring result of the first user according to the characteristic value and the corresponding weight of each characteristic attribute of the first user; and determining the user grade to which the first user belongs based on the scoring result, and recommending the advertisement corresponding to the determined user grade to the first user, so that the payment capacity of the user is evaluated based on the behavior data of the user which is more prone to reflecting the payment capacity of the user, and further the effective popularization of the advertisement in computer application is ensured.
Optionally, please refer to fig. 3 for a method for determining a value represented by the data information of the characteristic attribute of the first user according to an embodiment of the present application. As shown in fig. 3, the method includes:
s301, determining whether the data information of the characteristic attribute of the first user is non-numerical value information or not aiming at each characteristic attribute, and if not, executing the step S302; if yes, go to step S303;
optionally, the above is an example of the first characteristic attribute, the second characteristic attribute, the third characteristic attribute, the fourth characteristic attribute, the fifth characteristic attribute, the sixth characteristic attribute, the seventh characteristic attribute, the eighth characteristic attribute, the ninth characteristic attribute, the tenth characteristic attribute and/or the eleventh characteristic attribute provided in the embodiment. The data information of the first characteristic attribute, the second characteristic attribute and the eleventh characteristic attribute is non-numerical value information; and the numerical information of the third characteristic attribute, the fourth characteristic attribute, the fifth characteristic attribute, the sixth characteristic attribute, the seventh characteristic attribute, the eighth characteristic attribute, the ninth characteristic attribute and the tenth characteristic attribute is numerical information.
S302, converting the data information of the characteristic attribute of the first user into numerical value information, and calling a corresponding numerical value from the converted data information of the characteristic attribute of the first user;
optionally, the method for converting the data information of the first characteristic attribute into data information includes: and determining the price of the hardware device indicated by the first characteristic attribute and having the most times of logging in the second computer application in the first historical time period as the data information of the first characteristic attribute.
The method for converting the data information of the second characteristic attribute into the data information includes: and determining the average price of the hardware devices which are indicated by the second characteristic attribute and logged into the second computer application in the first historical time period as the data information of the second characteristic attribute.
Optionally, the price of the hardware device may be captured by means of a web crawler. The above is only the preferred way for capturing the price of the hardware device provided in the embodiment of the present application, and the inventor may set the way for capturing the price of the hardware device according to the personal requirement, which is not limited herein.
Optionally, the method for converting the data information of the eleventh characteristic attribute into data information includes: and determining the price of the cell occupied by the user in the first historical time period indicated by the eleventh characteristic attribute as the data information of the eleventh characteristic attribute.
Optionally, the price of the cell occupied by the user in the first historical time period is determined by searching a preset price of the cell occupied by the user in the first historical time period. The above is only a preferred way to determine the price of the cell where the user lives in the first history time period provided by the embodiment of the present application, and the inventor can arbitrarily set a specific way to determine the price of the cell where the user lives in the first history time period according to his own needs, and is not limited here.
S303, calling a corresponding numerical value from the data information of the characteristic attribute of the first user.
Optionally, a corresponding numerical value is retrieved from the data information of the characteristic attribute of the first user (i.e., the value of the data information of the characteristic attribute of the first user is retrieved), and is used as the determined numerical value represented by the data information of the characteristic attribute of the first user.
Through the further introduction of the method for determining the numerical value represented by the data information of the characteristic attribute of the first user, the advertisement recommendation method provided by the embodiment of the present application is clearer and more complete, and is convenient for a person skilled in the art to understand.
For convenience of understanding, a specific implementation method for obtaining the feature value of the feature attribute of the first user and the feature value of the feature attribute of each second user based on the number of the all users and the ranking order of the first user among the all users, which is provided in the embodiment of the present application, is described in detail.
Optional, preset eigenvalue calculation formula
Wherein, the ftotalRepresenting the number of all users, said fm(rank)The rank ordering of the numerical value represented by the data information representing the characteristic attribute of the user among all the users, pmA feature value representing the feature attribute of the user (which may also be referred to as a percentile of the feature attribute of the user).
It should be noted that: f in the eigenvalue calculation formulam(rank)The rank ordering of the represented users among all users is: the data information is obtained by arranging the numerical values represented by the data information of the characteristic attributes from large to small.
Optionally, the method for determining the feature value of the feature attribute of the first user according to the number of the all users and the ranking ranks of the first user among the all users includes: and calling the characteristic value calculation formula, and calculating to obtain the characteristic value of the characteristic attribute of the first user according to the number of the users and the sequencing ordinal of the first user in all the users.
Optionally, for each second user, the manner of determining the feature value of the feature attribute of the second user is as follows: and determining the characteristic value of the characteristic attribute of the second user according to the number of the all users and the sorting ordinal of the second user in all the users.
In this embodiment of the application, preferably, the determining the feature value of the feature attribute of the second user according to the number of the all users and the ranking order of the second user among all users includes: and calling the characteristic value calculation formula, and calculating to obtain the characteristic value of the characteristic attribute of the second user according to the number of the users and the sequencing ordinal of the second user in all the users.
Through the further introduction of the method for determining the characteristic value of the characteristic attribute of the first user and the characteristic value of the characteristic attribute of each second user according to the number of the all users and the ranking ranks of the first user among the all users, provided by the embodiment of the present application, the advertisement recommendation method provided by the embodiment of the present application is clearer and more complete, and is convenient for a person skilled in the art to understand.
Optionally, a flowchart of a method for determining a weight of each feature attribute by using a feature value of each feature attribute of the first user and a feature value of each feature attribute of each second user is provided in an embodiment of the present application, please refer to fig. 4.
As shown in fig. 4, the method includes:
s401, performing exponential transformation on the feature values of the first users and the feature values of each second user with the same feature attribute to obtain variation values with the same spatial discrimination;
optionally, determining a weight of each feature attribute based on the determined feature value of each feature attribute of the first user and the determined feature value of each feature attribute of each second user includes: and for each feature attribute, performing exponential transformation on the feature value of the feature attribute of the first user and the feature value of the feature attribute of each second user to obtain a variation value corresponding to the feature attribute and having the same spatial discrimination. It should be noted that the obtained variation values with the same spatial differentiation degree corresponding to the feature attribute include a plurality of numerical values, and the numerical values are in one-to-one correspondence with the feature values corresponding to the feature attribute (here, the feature values of the feature attribute of the first user and the feature values of the feature attribute of each second user).
Optionally, the method for performing exponential transformation on the feature value of the feature attribute of the first user and the feature value of the feature attribute of each second user to obtain the variation value corresponding to the feature attribute and having the same spatial discrimination includes: invoking an exponential transformation formula fnew＝efxWherein f is a characteristic value, x is a characteristic coefficient, fnewIs a variation value; determining a characteristic coefficient corresponding to the characteristic attribute; based on the called exponential transformation formula, calculating to obtain a variation value f with the same spatial discrimination corresponding to the characteristic attribute by using the determined characteristic coefficient, the characteristic value of the characteristic attribute of the first user and the characteristic value of the characteristic attribute of each second usernew。
In the embodiment of the present application, preferably, the feature coefficients corresponding to the feature attributes are preset according to actual situations, and for each two feature attributes, the feature coefficients corresponding to the two feature attributes may be the same or different, and are not limited herein.
S402, determining the weight of each characteristic attribute according to the obtained change value respectively corresponding to each characteristic attribute.
Optionally, a flowchart of a method for determining a weight of each feature attribute according to the obtained variation value respectively corresponding to each feature attribute provided in the embodiment of the present application is shown in fig. 5.
As shown in fig. 5, the method includes:
s501, determining a correlation coefficient between every two characteristic attributes according to the obtained change values respectively corresponding to the characteristic attributes;
in this embodiment of the present application, preferably, the determining a correlation coefficient between each two of the feature attributes includes: calling a preset correlation coefficient calculation formula
Wherein X is the variation value corresponding to the characteristic attribute X, Y is the variation value corresponding to the characteristic attribute Y, co ν (X, Y) represents the covariance of the characteristic attribute X and the characteristic attribute Y, σXIs the standard deviation, σ, of the characteristic attribute XYIs the standard deviation of the characteristic attribute Y, and p is the correlation coefficient between the characteristic attribute X and the characteristic attribute Y; and respectively calculating the correlation coefficient between every two characteristic attributes based on the correlation coefficient calculation formula.
S502, determining the weight of each characteristic attribute based on the determined correlation coefficient between every two characteristic attributes.
Optionally, based on the determined correlation coefficient between each two feature attributes, the correlation coefficient between each feature attribute and each other feature attribute may be determined, and then, for each feature attribute, the correlation coefficient sum corresponding to the feature attribute is calculated.
For each characteristic attribute, the way of calculating the correlation coefficient sum corresponding to the characteristic attribute is as follows: and determining the correlation coefficient between the characteristic attribute and each of the other characteristic attributes, and taking the sum of the determined correlation coefficients as the correlation coefficient sum corresponding to the characteristic attribute.
Correspondingly, after calculating the correlation coefficient sum corresponding to each characteristic attribute, summing all the calculated correlation coefficient sums to obtain a final correlation coefficient; and for each characteristic attribute, determining a correlation coefficient corresponding to the characteristic attribute and a proportion of the correlation coefficient to the final correlation coefficient as the weight of the characteristic attribute. Wherein the correlation coefficient corresponding to the characteristic attribute and the proportion of the correlation coefficient to the final correlation coefficient are as follows: and dividing the correlation coefficient corresponding to the characteristic attribute by the final correlation coefficient to obtain a result.
For example, if there are 3 feature attributes, which are respectively feature attribute 1, feature attribute 2 and feature attribute 3, where the correlation coefficient between feature attribute 1 and feature attribute 2 is a, the correlation coefficient between special attribute 1 and feature attribute 3 is b, and one of feature attribute 2 and feature attribute 3 is bThe correlation coefficient between c and d is c. Then, the sum of correlation coefficients corresponding to the characteristic attribute 1 is a + b; the sum of the correlation coefficients corresponding to the characteristic attribute 2 is a + c; the sum of the correlation coefficients corresponding to the characteristic attribute 3 is b + c; the final correlation coefficient is (a + b) + (a + c) + (b + c); the weight of the characteristic attribute 1 is
The weight of the characteristic attribute 2 is
Weight of feature attribute 3
Through the further introduction of the method for determining the weight of each feature attribute based on the determined feature value of each feature attribute of the first user and the determined feature value of each feature attribute of each second user, the advertisement recommendation method provided by the embodiment of the present application is clearer and more complete, and is convenient for a person skilled in the art to understand.
The method is described in detail in the embodiments disclosed above, and the method of the present invention can be implemented by various types of apparatuses, so that the present invention also discloses an apparatus, and the following detailed description will be given of specific embodiments.
Fig. 6 is a schematic structural diagram of an advertisement recommendation device according to an embodiment of the present application.
As shown in fig. 6, the apparatus includes:
a behavior data acquiring unit 61 configured to acquire behavior data of the first user, the behavior data including data information of at least one characteristic attribute related to the payment capability;
a feature value determining unit 62, configured to separately process data information of each feature attribute of the first user based on behavior data of at least one second user, so as to obtain a feature value of each feature attribute of the first user;
a weight determining unit 63, configured to determine a weight of each feature attribute by using a feature value of each feature attribute of the first user and a feature value of each feature attribute of each second user;
a first scoring result calculating unit 64, configured to obtain a score of each feature attribute of the first user according to the feature value and the corresponding weight of each feature attribute of the first user, and determine a scoring result of the first user according to the score of each feature attribute of the first user;
a first advertisement recommending unit 65, configured to determine a user rating to which the first user belongs based on the scoring result, and recommend an advertisement corresponding to the determined user rating to the first user.
Further, an advertisement recommendation device provided in an embodiment of the present application further includes:
the second scoring result calculating unit is used for obtaining the scores of the characteristic attributes of the second user by using the characteristic values and the corresponding weights of the characteristic attributes of the second user, and determining the scoring result of the second user according to the scores of the characteristic attributes of the second user;
and the second advertisement recommending unit is used for determining the user grade of the second user based on the scoring result and recommending the advertisement corresponding to the determined user grade to the second user.
In this embodiment of the application, preferably, the characteristic value determining unit is specifically configured to: and for each characteristic attribute, unifying the data information of the characteristic attribute of the first user and the data information of the characteristic attribute included in the behavior data of at least one second user to obtain the characteristic value of the characteristic attribute of the first user.
Fig. 7 shows an alternative structure of the eigenvalue determination unit 62 according to the embodiment of the present invention.
As shown in fig. 7, the feature value determination unit 62 includes:
a first determining unit 71, configured to determine, for each characteristic attribute, a numerical value represented by data information of the characteristic attribute of the first user;
a second determining unit 72, configured to determine, according to the value represented by the data information of the characteristic attribute of the first user, a ranking of the first user among all users, where the all users include the first user and the at least one second user;
a third determining unit 73, configured to obtain a feature value of the feature attribute of the first user based on the number of all users and the ranking order of the first user among all users.
In the embodiment of the present application, preferably, the first determining unit 71 is specifically configured to:
for each characteristic attribute, if the data information of the characteristic attribute of the first user is non-numerical value information, converting the data information of the characteristic attribute of the first user into numerical value information, and calling a corresponding numerical value from the converted data information of the characteristic attribute of the first user;
and if the data information of the characteristic attribute of the first user is numerical value information, calling a corresponding numerical value from the data information of the characteristic attribute of the first user.
In this embodiment of the present application, preferably, the behavior data acquiring unit 61 includes:
the original behavior data determining unit is used for determining original behavior data of the first user;
and the removing unit is used for removing abnormal data in the original behavior data and acquiring the behavior data of the first user.
Fig. 8 shows an alternative structure of the weight determining unit 63 according to the embodiment of the present invention.
As shown in fig. 8, the weight determination unit 63 includes:
a variation value determining unit 81, configured to perform exponential transformation on the feature values of the first users and the feature values of each second user with the same feature attribute to obtain variation values with the same spatial differentiation;
a weight determining subunit 82, configured to determine a weight of each of the feature attributes according to the obtained variation value respectively corresponding to each of the feature attributes.
In the embodiment of the present application, it is preferable that the weight determination subunit 82 includes:
a correlation coefficient determining unit, configured to determine a correlation coefficient between every two feature attributes according to the obtained change value corresponding to each feature attribute;
and the characteristic attribute weight determining unit is used for determining the weight of each characteristic attribute based on the determined correlation coefficient between every two characteristic attributes.
The embodiment of the application also provides an advertisement recommendation server. As shown in fig. 9, which is a schematic structural diagram of an advertisement recommendation server provided in an embodiment of the present application, the advertisement recommendation server includes: a processor 91 and a memory 92.
The processor 91, the memory 92 and the communication interface 93 are communicated with each other through a communication bus 94.
Alternatively, the communication interface 93 may be an interface of a communication module, such as an interface of a GSM module. And a processor 91 for executing the program.
The processor 91 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention.
And a memory 92 for storing programs.
The program may include program code including computer operating instructions. In an embodiment of the present invention, the program may include a program corresponding to the user interface editor.
Among them, the procedure can be specifically used for:
acquiring behavior data of a first user, wherein the behavior data comprises data information of at least one characteristic attribute related to the payment capacity;
respectively processing the data information of each characteristic attribute of the first user based on the behavior data of at least one second user to obtain a characteristic value of each characteristic attribute of the first user;
determining a weight of each of the feature attributes using the feature value of each of the feature attributes of the first user and the feature value of each of the feature attributes of each of the second users;
obtaining scores of all the characteristic attributes of the first user according to the characteristic values and the corresponding weights of all the characteristic attributes of the first user, and determining the score result of the first user according to the scores of all the characteristic attributes of the first user;
and determining a user grade to which the first user belongs based on the scoring result, and recommending advertisements corresponding to the determined user grade to the first user.
The embodiment of the invention discloses an advertisement recommendation device and a server, wherein behavior data of a first user is obtained, and the behavior data comprises data information of at least one characteristic attribute related to payment capacity; processing the data information of each characteristic attribute of the first user respectively to obtain a characteristic value of each characteristic attribute of the first user; determining a weight for each of the feature attributes; determining a scoring result of the first user according to the characteristic value and the corresponding weight of each characteristic attribute of the first user; and determining the user grade to which the first user belongs based on the scoring result, and recommending the advertisement corresponding to the determined user grade to the first user, so that the payment capacity of the user is evaluated based on the behavior data of the user which is more prone to reflecting the payment capacity of the user, and further the effective popularization of the advertisement in computer application is ensured.
To sum up:
the embodiment of the invention discloses an advertisement recommendation method, an advertisement recommendation device and a server, wherein behavior data of a first user are obtained, and the behavior data comprise data information of at least one characteristic attribute related to payment capacity; processing the data information of each characteristic attribute of the first user respectively to obtain a characteristic value of each characteristic attribute of the first user; determining a weight for each of the feature attributes; determining a scoring result of the first user according to the characteristic value and the corresponding weight of each characteristic attribute of the first user; and determining the user grade to which the first user belongs based on the scoring result, and recommending the advertisement corresponding to the determined user grade to the first user, so that the payment capacity of the user is evaluated based on the behavior data of the user which is more prone to reflecting the payment capacity of the user, and further the effective popularization of the advertisement in computer application is ensured.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (12)
1. An advertisement recommendation method, comprising:
acquiring behavior data of a first user, wherein the behavior data comprises data information of at least one characteristic attribute related to the payment capacity;
respectively processing the data information of each characteristic attribute of the first user based on the behavior data of at least one second user to obtain a characteristic value of each characteristic attribute of the first user;
determining a weight of each of the feature attributes using the feature value of each of the feature attributes of the first user and the feature value of each of the feature attributes of each of the second users;
obtaining scores of all the characteristic attributes of the first user according to the characteristic values and the corresponding weights of all the characteristic attributes of the first user, and determining the score result of the first user according to the scores of all the characteristic attributes of the first user;
determining a user grade to which the first user belongs based on the scoring result, and recommending advertisements corresponding to the determined user grade to the first user;
wherein the determining a weight of each of the feature attributes using the feature value of each of the feature attributes of the first user and the feature value of each of the feature attributes of each of the second users comprises:
performing exponential transformation on the feature values of the first users and the feature values of each second user with the same feature attribute to obtain variation values with the same spatial discrimination;
and determining the weight of each characteristic attribute according to the obtained variation value respectively corresponding to each characteristic attribute.
2. The method of claim 1, further comprising:
obtaining scores of the characteristic attributes of the second user by using the characteristic values and the corresponding weights of the characteristic attributes of the second user, and determining the score result of the second user according to the scores of the characteristic attributes of the second user;
and determining the user grade of the second user based on the grading result, and recommending advertisements corresponding to the determined user grade to the second user.
3. The method according to claim 1, wherein the processing data information of each feature attribute of the first user based on behavior data of at least one second user to obtain a feature value of each feature attribute of the first user comprises:
and for each characteristic attribute, unifying the data information of the characteristic attribute of the first user and the data information of the characteristic attribute included in the behavior data of at least one second user to obtain the characteristic value of the characteristic attribute of the first user.
4. The method according to claim 3, wherein the unifying, for each feature attribute, the data information of the feature attribute of the first user and the data information of the feature attribute included in the behavior data of at least one second user to obtain the feature value of the feature attribute of the first user comprises:
for each characteristic attribute, determining a numerical value represented by the data information of the characteristic attribute of the first user;
determining the ranking of the first user among all users according to the value represented by the data information of the characteristic attribute of the first user, wherein all users comprise the first user and the at least one second user;
and obtaining the characteristic value of the characteristic attribute of the first user based on the number of all users and the sorting ordinal of the first user in all users.
5. The method of claim 4, wherein the determining, for each characteristic attribute, a value represented by the data information of the characteristic attribute of the first user comprises:
for each characteristic attribute, if the data information of the characteristic attribute of the first user is non-numerical value information, converting the data information of the characteristic attribute of the first user into numerical value information, and calling a corresponding numerical value from the converted data information of the characteristic attribute of the first user;
and if the data information of the characteristic attribute of the first user is numerical value information, calling a corresponding numerical value from the data information of the characteristic attribute of the first user.
6. The method of claim 5, wherein the obtaining behavioral data of the first user comprises:
determining original behavior data of a first user;
and eliminating abnormal data in the original behavior data to obtain the behavior data of the first user.
7. The method of claim 1, wherein determining the weight of each of the feature attributes according to the obtained variation value respectively corresponding to each of the feature attributes comprises:
determining a correlation coefficient between every two characteristic attributes according to the obtained variation values respectively corresponding to the characteristic attributes;
determining a weight of each of the feature attributes based on the determined correlation coefficient between two of the feature attributes.
8. An advertisement recommendation apparatus, comprising:
a behavior data acquisition unit for acquiring behavior data of a first user, the behavior data including data information of at least one characteristic attribute related to payment capability;
a feature value determining unit, configured to separately process data information of each feature attribute of the first user based on behavior data of at least one second user, to obtain a feature value of each feature attribute of the first user;
a weight determination unit configured to determine a weight of each of the feature attributes using a feature value of each of the feature attributes of the first user and a feature value of each of the feature attributes of each of the second users;
the first scoring result calculating unit is used for obtaining the scores of the characteristic attributes of the first user according to the characteristic values and the corresponding weights of the characteristic attributes of the first user and determining the scoring result of the first user according to the scores of the characteristic attributes of the first user;
the first advertisement recommending unit is used for determining the user grade of the first user based on the scoring result and recommending the advertisement corresponding to the determined user grade to the first user;
wherein the weight determination unit includes:
the change value determining unit is used for performing exponential transformation on the feature values of the first users and the feature values of each second user with the same feature attribute to obtain change values with the same spatial discrimination;
and the weight determining subunit is configured to determine the weight of each feature attribute according to the obtained variation value respectively corresponding to each feature attribute.
9. The apparatus of claim 8, further comprising:
the second scoring result calculating unit is used for obtaining the scores of the characteristic attributes of the second user by using the characteristic values and the corresponding weights of the characteristic attributes of the second user, and determining the scoring result of the second user according to the scores of the characteristic attributes of the second user;
and the second advertisement recommending unit is used for determining the user grade of the second user based on the scoring result and recommending the advertisement corresponding to the determined user grade to the second user.
10. The apparatus according to claim 8, wherein the eigenvalue determination unit is specifically configured to: and for each characteristic attribute, unifying the data information of the characteristic attribute of the first user and the data information of the characteristic attribute included in the behavior data of at least one second user to obtain the characteristic value of the characteristic attribute of the first user.
11. The apparatus of claim 10, wherein the eigenvalue determination unit comprises:
a first determining unit configured to determine, for each of the characteristic attributes, a numerical value indicated by the data information of the characteristic attribute of the first user;
a second determining unit, configured to determine, according to a numerical value represented by the data information of the characteristic attribute of the first user, a ranking of the first user among all users, where the all users include the first user and the at least one second user;
and the third determining unit is used for obtaining the characteristic value of the characteristic attribute of the first user based on the number of all users and the sorting ordinal of the first user in all users.
12. An advertisement recommendation server comprising a memory for storing a program and a processor for calling the program, the program for:
acquiring behavior data of a first user, wherein the behavior data comprises data information of at least one characteristic attribute related to the payment capacity;
respectively processing the data information of each characteristic attribute of the first user based on the behavior data of at least one second user to obtain a characteristic value of each characteristic attribute of the first user;
determining a weight of each of the feature attributes using the feature value of each of the feature attributes of the first user and the feature value of each of the feature attributes of each of the second users;
obtaining scores of all the characteristic attributes of the first user according to the characteristic values and the corresponding weights of all the characteristic attributes of the first user, and determining the score result of the first user according to the scores of all the characteristic attributes of the first user;
determining a user grade to which the first user belongs based on the scoring result, and recommending advertisements corresponding to the determined user grade to the first user;
wherein the determining a weight of each of the feature attributes using the feature value of each of the feature attributes of the first user and the feature value of each of the feature attributes of each of the second users comprises:
performing exponential transformation on the feature values of the first users and the feature values of each second user with the same feature attribute to obtain variation values with the same spatial discrimination;
and determining the weight of each characteristic attribute according to the obtained variation value respectively corresponding to each characteristic attribute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710304206.7A CN108804462B (en) | 2017-05-03 | 2017-05-03 | Advertisement recommendation method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710304206.7A CN108804462B (en) | 2017-05-03 | 2017-05-03 | Advertisement recommendation method and device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108804462A CN108804462A (en) | 2018-11-13 |
| CN108804462B true CN108804462B (en) | 2021-08-27 |
Family
ID=64054398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710304206.7A Active CN108804462B (en) | 2017-05-03 | 2017-05-03 | Advertisement recommendation method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108804462B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639972A (en) * | 2020-05-29 | 2020-09-08 | 中国联合网络通信集团有限公司 | Multimedia data delivery method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102075573A (en) * | 2011-01-07 | 2011-05-25 | 北京邮电大学 | Method and system for automatically recommending learning partner in distance education social network service (ESNS) |
| CN102163310A (en) * | 2010-02-22 | 2011-08-24 | 深圳市腾讯计算机系统有限公司 | Information pushing method and device based on credit rating of user |
| CN102637170A (en) * | 2011-02-10 | 2012-08-15 | 北京百度网讯科技有限公司 | Question pushing method and system |
| CN103927673A (en) * | 2014-03-24 | 2014-07-16 | 腾讯科技（深圳）有限公司 | Method and device for recommending service information |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101802332B1 (en) * | 2010-11-25 | 2017-12-29 | 삼성전자주식회사 | Method for providing contents and the system thereof |
-
2017
- 2017-05-03 CN CN201710304206.7A patent/CN108804462B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102163310A (en) * | 2010-02-22 | 2011-08-24 | 深圳市腾讯计算机系统有限公司 | Information pushing method and device based on credit rating of user |
| CN102075573A (en) * | 2011-01-07 | 2011-05-25 | 北京邮电大学 | Method and system for automatically recommending learning partner in distance education social network service (ESNS) |
| CN102637170A (en) * | 2011-02-10 | 2012-08-15 | 北京百度网讯科技有限公司 | Question pushing method and system |
| CN103927673A (en) * | 2014-03-24 | 2014-07-16 | 腾讯科技（深圳）有限公司 | Method and device for recommending service information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108804462A (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241415B (en) | Project recommendation method and device, computer equipment and storage medium | |
| CN108833458B (en) | Application recommendation method, device, medium and equipment | |
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| JP6713238B2 (en) | Electronic device, method for constructing retail store evaluation model, system and storage medium | |
| CN109299356B (en) | Activity recommendation method and device based on big data, electronic equipment and storage medium | |
| CN104081392A (en) | Influence scores for social media profiles | |
| US11748452B2 (en) | Method for data processing by performing different non-linear combination processing | |
| US10621641B2 (en) | Method and device for pushing information | |
| CN111401700A (en) | Data analysis method, device, computer system and readable storage medium | |
| CN108062692B (en) | Recording recommendation method, device, equipment and computer readable storage medium | |
| CN110825977A (en) | Data recommendation method and related equipment | |
| CN113312578B (en) | Fluctuation attribution method, device, equipment and medium of data index | |
| CN106778843B (en) | Method, server and system for predicting gender of mobile terminal user | |
| CN107679680A (en) | A kind of financial forward prediction method, apparatus, equipment and storage medium | |
| CN107798125B (en) | Access judgment method, system, equipment and storage medium based on intimacy model | |
| CN108804462B (en) | Advertisement recommendation method and device and server | |
| CN112650921A (en) | Object recommendation method, device, equipment and storage medium | |
| CN113763077A (en) | Method and apparatus for detecting false trade orders | |
| CN110930226A (en) | Financial product recommendation method and device, electronic equipment and storage medium | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN109472455B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN113344660A (en) | House source information processing method and device, electronic equipment and storage medium | |
| CN107665189B (en) | method, terminal and equipment for extracting central word | |
| CN110852807A (en) | User determination method and device, computer equipment and storage medium | |
| CN109146122A (en) | A kind of probability forecasting method, device, electronic equipment and computer 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |