WO2017202238A1 - 一种推广信息的投放方法、装置、系统及存储介质 - Google Patents

一种推广信息的投放方法、装置、系统及存储介质 Download PDF

Info

Publication number
WO2017202238A1
WO2017202238A1 PCT/CN2017/084861 CN2017084861W WO2017202238A1 WO 2017202238 A1 WO2017202238 A1 WO 2017202238A1 CN 2017084861 W CN2017084861 W CN 2017084861W WO 2017202238 A1 WO2017202238 A1 WO 2017202238A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
promotion information
friend
behavior data
advertised
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.)
Ceased
Application number
PCT/CN2017/084861
Other languages
English (en)
French (fr)
Inventor
刘大鹏
曹孝卿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to EP17802084.8A priority Critical patent/EP3467752A4/en
Publication of WO2017202238A1 publication Critical patent/WO2017202238A1/zh
Priority to US16/197,067 priority patent/US11501327B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0239—Online discounts or incentives
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a method, an apparatus, a system, and a storage medium for promoting information.
  • the user In the process of using the social application, the user usually receives the promotion information pushed by the server, for example, an advertisement for promoting a certain product or thing.
  • promotion information for example, an advertisement for promoting a certain product or thing.
  • the user when looking for a user to serve an advertisement, the user is generally first analyzed for the degree of interest in the advertisement, such as user behavior or user tags to determine the user's interest in the advertisement, thereby estimating the user's click on the advertisement. Rate, then rate the ad based on the clickthrough rate, and serve the ad to the user in descending order of the score.
  • This type of advertising is based on the estimation of the user's click-through rate. The delivery is not accurate and the delivery is not good.
  • the purpose of the application is to provide a method, a device and a system for placing promotion information, so as to solve the technical problem that the prior promotion information is poorly displayed and the delivery effect is poor.
  • the embodiment of the present application provides the following technical solutions:
  • a method for delivering promotional information including:
  • the delivery server obtains a collection of promotional information to be served to the user
  • the delivery server obtains the delivery recommendation degree corresponding to the user according to the to-be-advertised promotion information in the to-be-advertised promotion information set;
  • the delivery server determines the target promotion information from the set of to-be-advertised promotion information according to the delivery recommendation degree;
  • the delivery server delivers the target promotion information to the user equipment corresponding to the user.
  • the embodiment of the present application further provides the following technical solutions:
  • a delivery device for promoting information comprising:
  • a first obtaining module configured to acquire a to-be-advertised promotional information set to be delivered to a user
  • a second obtaining module configured to acquire, according to the to-be-advertised promotion information in the to-be-advertised promotion information set, the delivery recommendation degree corresponding to the user;
  • a determining module configured to determine target promotion information from the to-be-advertised promotion information set according to the delivery recommendation degree
  • the delivery module is configured to deliver the target promotion information to the user equipment corresponding to the user.
  • the embodiment of the present application further provides the following technical solutions:
  • a delivery system for promoting information comprising the delivery device of the promotion information according to any one of the above items.
  • the embodiment of the present application provides a computer storage medium for storing computer software instructions used by the delivery device for the promotion information, and includes a step for executing the delivery method of the promotion information.
  • the method, device, system, and storage medium for the promotion information described in the present application obtain the to-be-advertised information collection to be delivered to the user, and obtain the corresponding user according to the to-be-advertised promotion information in the to-be-advertised promotion information set.
  • the target promotion information is determined from the to-be-advertised promotion information set according to the delivery recommendation degree, and the target promotion information is delivered to the user, and the advertisement can be selected according to factors such as the user's willingness to click and the influence of the friend interaction. Delivered to users with high accuracy and good delivery.
  • FIG. 1 is a schematic diagram of a scenario of a promotion information delivery system provided by an embodiment of the present application.
  • FIG. 1b is a schematic flowchart of a method for placing promotion information according to an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of another method for placing promotion information according to an embodiment of the present application.
  • FIG. 2b is a schematic diagram of personal participation, social influence, and influence by friends according to an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of a device for placing promotion information according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a server according to an embodiment of the present application.
  • the embodiment of the present application provides a method, device, and system for placing promotion information.
  • the delivery system of the promotion information may include any delivery device of the promotion information provided by the embodiment of the present application, and the delivery device of the promotion information may be specifically integrated into a server (such as a delivery server).
  • the delivery system of the promotion information may further include other devices, such as a user device and a user server, where the user device (such as a smart phone, a computer, etc.) is used to receive the promotion information to be served by the delivery server, and the user server.
  • the behavior server collects the behavior data of each user for the promotion information that has been delivered, and the delivery server is configured to obtain the behavior data of the user from the user server, and calculate the recommendation recommendation of the user for the recommendation information to be delivered according to the behavior data.
  • the delivery server can obtain a to-be-served advertisement set that needs to be delivered to the user, and obtain the user to serve the advertisement.
  • a delivery recommendation of the to-be-advertised advertisement in the collection after which the delivery server determines the target advertisement from the to-be-served advertisement set according to the delivery recommendation degree, for example, determining that the delivery recommendation degree is high as the target advertisement, and the target is to be placed
  • the advertisement is sent to the user equipment for delivery, and the advertisement can be selected and placed on the user according to factors such as the user's willingness to click and the influence of the interaction of the friend.
  • the delivery accuracy is high and the delivery effect is good.
  • This embodiment will be described from the perspective of a delivery device for promoting information, and the delivery device of the promotion information can be integrated in the delivery server.
  • FIG. 1b specifically describes a method for placing promotion information provided by the first embodiment of the present application, which may include:
  • the to-be-advertised promotion information set is usually stored in the delivery server, and may include all promotion information that the delivery server does not deliver to the user.
  • the promotion information may be an advertisement, or may be other promotion and delivery. Information, etc., the promotion information is mainly used for some social applications, such as Weibo or some dating site clients.
  • the delivery server receives the delivery request sent by the user device, it obtains the to-be-advertised promotion information set to be delivered to the user.
  • the to-be-advertised promotion information collection is the sum of all the promotion information that has never been delivered to the user.
  • the delivery recommendation degree mainly points to the recommendation degree of the user to serve the promotion information to be served, which may be expressed as a score or a ratio.
  • the foregoing step S102 may specifically include:
  • the buddy behavior data mainly refers to the behavior data of all the buddies of the user
  • the user behavior data and the buddy behavior data are mainly historical behavior data of the user or the user buddy, which may be stored in the user server, and may specifically include the user. Or the behavior of the user's friends to view, comment, like, forward, or reply to the promoted information, as well as the chat and interaction between the user or the user's friends and others.
  • a user device such as a smart phone
  • the promotional information is served for viewing, commenting, like, forwarding, or replying
  • the user device sends the behavior data to the user server for storage.
  • the preset category may be determined according to actual needs, and may be a field in which the product in the promotion information is applied, a type of topic involved, or a promotion purpose of the promotion information, for example, may be a car, a mother or baby, Men's, women's or public welfare.
  • the preset category may be stored in the delivery server in advance, and a series of keywords are set for the preset category, so that the corresponding keyword can be matched according to the text content of the promotion information to be served, and the corresponding preset is obtained. category.
  • the user's personal participation degree, social influence degree, and friend influence degree are consideration factors for the delivery server to select a suitable promotion information to be served by the user.
  • the delivery server can accurately deliver the promotion information to the user. To improve the delivery effect.
  • the foregoing step (3) may specifically include:
  • (3A) determining, according to the friend behavior data and the user behavior data, the influence of the friend who has interacted with the promotion information to be served on the user, and obtaining the influence degree of the friend.
  • the influence degree of the friend mainly refers to the degree of influence of the user's friend's interaction operation on the promotion information on the user, and the interaction mainly refers to the operation of commenting, like or forwarding the promotion information, but does not include the viewing operation.
  • the interaction mainly refers to the operation of commenting, like or forwarding the promotion information, but does not include the viewing operation.
  • the foregoing step (3A) may specifically include:
  • the interaction operation affects the user's subsequent click operation on the promotion information to be served, such as viewing or interaction, and the influence size and the user's affinity with the first friend are closely related.
  • the intimacy mainly refers to the close relationship between the user and the first friend, such as the chat frequency, the degree of interest overlap, and the mutual interaction rate.
  • the mutual interaction rate may include praising the content published by the other party. How often to reply, comment, or forward.
  • the relationship between the first friend and the user's historical behavior data can be obtained, and the historical behavior data can be behavior data of the user or the user's friend within a month or a half year.
  • the specific time limit can be based on actual needs. set.
  • (3B) predicting the user's interest in the to-be-advertised promotion information according to the user behavior data and the preset category, and obtaining personal participation.
  • the degree of interest or personal participation mainly refers to the probability that the user himself clicks on the to-be-advertised promotion information without being affected by others.
  • the user's own characteristics and the characteristics of the to-be-advertised promotion information may be combined to predict the user's interest in the promotion information to be served, wherein the user's own characteristics may include information such as the gender, age, interest, or historical active area of the user. It can be obtained by analyzing the historical behavior data of the user, and the characteristics of the to-be-advertised promotion information mainly refer to the preset category to which it belongs, such as the field to which the product to be served in the promotion information is applied, the type of topic involved, or the purpose of promotion. .
  • the user's historical behavior data can be analyzed to determine the user's own characteristics, and the Logistic Regression (LR) algorithm or the deep learning algorithm is used to predict the user to be placed in association with the characteristics of the to-be-advertised promotion information. Promote the interest of the information to get the user's personal participation.
  • LR Logistic Regression
  • (3C) predicting the influence of the user on the society according to the friend behavior data, the user behavior data, and the preset category, and obtaining the social influence degree.
  • the social influence degree mainly refers to the degree of influence of the interaction operation on the user friend itself and the user friend on the friend after interacting with the promotion information, that is, the social influence degree package. Including the influence of the user and the influence of the user's friends after the user influences the friend.
  • the promotion information of the same user for different preset categories has different influences on the friends, and at the same time, the degree of influence of the users on different friends is different for the same promotion information.
  • the foregoing step (3C) may specifically include:
  • the user After the user interacts with the served promotion information according to the interaction data and the friend behavior data, the user clicks the first click rate of the served promotion information;
  • the friend of the user friend clicks the second click rate of the served promotion information
  • the interaction rate, the first click rate, and the second click rate are calculated according to a preset algorithm to predict the social influence of the user on the social information to be served.
  • the preset algorithm may be set according to actual needs, for example, may be a product of the interaction rate of the user and the first click rate and the second click rate of all user friends.
  • the other friend behavior data mainly refers to behavior data of all friends of the user's friends.
  • the interaction rate mainly refers to the probability that the user interacts with the promotion information belonging to the same preset category as the promotion information to be delivered in a preset time (for example, one month or half a year).
  • the click action mainly includes viewing, commenting, like or forwarding.
  • the recommendation recommendation can be calculated by the following formula:
  • u is the user
  • v is the user's friend
  • ad is the promotion information to be served.
  • Quality(u, Ad) is the user's comprehensive score for the promotion information to be placed, that is, the recommendation level.
  • Ptrr(u,ad) is the user's click rate of the promotion information to be served, including the user's voluntary click behavior and the click behavior affected by others, which can be calculated by the above steps (3A) and (3B). Influenced by friends and personal participation is calculated by a specific algorithm (such as addition or multiplication, etc.).
  • the diffusion(u,ad) is the social influence degree of the user to the promotion information to be served
  • pactive(u,ad) is the probability that the user interacts with the promotion information to be served, that is, the interaction rate mentioned in the above step (3C)
  • inf(u,v) is the probability that a user clicks on the user after interacting with the to-be-advertised promotion information (ie, the influence of the user), that is, the first click rate mentioned in the above step (3C)
  • I(v,ad) is the probability that a user's friend's friend clicks (ie, the influence of the user's friend) after interacting with the to-be-advertised promotion information, that is, the first mentioned in the above step (3C)
  • the second click rate according to the PageRank (page ranking) algorithm idea, the user's social influence degree (ie, the I(u, ad)) of the to-be-advertised promotion information is a summary of the influence of the user's
  • the foregoing step S103 may specifically include:
  • the to-be-advertised promotion information in the to-be-advertised promotion information set is arranged in order, and a corresponding resource list is generated;
  • the to-be-advertised promotion information corresponding to the previous preset number in the resource list is selected as the target promotion information.
  • the to-be-supplied recommendation information may be sorted in descending order of the delivery recommendation degree.
  • the preset number of bits can be determined according to actual needs, such as 1 or 3, and so on.
  • the way to promote the target promotion information can also be:
  • the to-be-advertised promotion information whose delivery recommendation degree is greater than the preset recommendation degree is determined as the target promotion information.
  • the preset recommendation degree may be determined according to actual needs.
  • the preset recommendation degree may be set to 8 points.
  • the to-be-advertised information can be determined as the target promotion information.
  • the target promotion information is delivered to the user equipment corresponding to the user.
  • the delivery server may send the target promotion information to the user equipment, such as a smart phone, and display the content to the user through an application in the user device (such as Weibo or Facebook in the social application) to achieve the target. Promote the delivery of information.
  • the user equipment such as a smart phone
  • the user device such as Weibo or Facebook in the social application
  • the method for delivering the promotion information obtains the to-be-advertised promotion information set to be delivered to the user, and obtains the delivery recommendation degree corresponding to the user according to the to-be-advertised promotion information in the to-be-advertised promotion information collection. And then, determining the target promotion information from the to-be-advertised promotion information set according to the delivery recommendation degree, and delivering the target promotion information to the user, and comprehensively considering factors such as the user's willingness to click and the influence of the friend interaction to select the advertisement to serve to the user. , the delivery accuracy is high, and the delivery effect is good.
  • the delivery device with the promotion information is integrated into the delivery server, and the promotion information is exemplified as an advertisement.
  • a method for delivering promotion information may be as follows:
  • the delivery server acquires a to-be-served advertisement set that needs to be delivered to the user.
  • the delivery server when the delivery server receives an advertisement delivery request sent by the user device, it can obtain all advertisements that have not been delivered to the user from its own database.
  • the delivery server acquires user behavior data and friend behavior data of the user.
  • the delivery server can obtain behavior data of the user and all friends of the user in the past six months, and the behavior data includes behavior data of the user or the user friend viewing, commenting, like, forwarding, or replying to the delivered advertisement, and the user. Or behavioral data of chats and interactions between user friends and others.
  • the delivery server determines a preset category to which the to-be-served advertisement in the to-be-advertised advertisement set belongs.
  • the preset category may be a preset theme type, which may include skin care, a car, a mother, a baby, or a women's wear.
  • the delivery server can match the corresponding keyword by the text information in the to-be-advertised advertisement, and obtain the corresponding preset category according to the matched keyword. For example, when the ad is pending When referring to cars or auto parts (such as car tires) many times, the keyword matching the server is the car or the tire, and the default category is the car.
  • the delivery server determines, according to the friend behavior data and the user behavior data, the influence of the friend who has interacted with the to-be-advertised advertisement on the user, and obtains the influence degree of the friend.
  • the foregoing step S204 may specifically include:
  • the user friend who has commented, liked, or forwarded the advertisement to be placed may be determined as the first friend according to the friend behavior data, and according to the historical chat frequency and interest between the first friend and the user. Data such as coincidence degree and mutual interaction rate are used to calculate the intimacy between the first friend and the user.
  • the delivery server predicts the user's interest in the advertisement to be placed according to the user behavior data and the preset category, and obtains personal participation.
  • the delivery server can count the viewing or interaction data of the user-applied automobile advertisement in the past six months, and calculate the predicted user to the advertisement to be placed through the LR algorithm. Interest level.
  • the delivery server predicts the influence of the user on the society according to the friend behavior data, the user behavior data, and the preset category, and obtains a social influence degree.
  • the foregoing step S206 may specifically include:
  • the user After the user interacts with the served advertisement according to the interaction data and the friend behavior data, the user clicks the first click rate of the served advertisement;
  • the interaction rate, the first click rate, and the second click rate are calculated according to a preset algorithm to predict the social influence of the user on the social to be placed.
  • the delivery server can obtain data of interactive behaviors such as comments, likes, or forwardings of the car advertisements that have been placed in the past six months as interactive data, and calculate the corresponding interaction rate pactive(u, ad).
  • the delivery server can also calculate the first click rate inf(u,v) of the user's friend clicking on the car advertisement after the user interacts with a car advertisement that has been delivered, and when the user friend clicks on the car class After the advertisement, the friend of the user's friend clicks on the second click rate I (v, ad) of the same car type advertisement, and obtains the user's interaction rate pactive(u, ad) and the first click rate of each user friend inf (
  • the delivery server calculates the delivery recommendation degree of the to-be-advertised advertisement to the user according to the personal participation degree, the social influence degree, and the influence degree of the friend.
  • the delivery server can calculate the delivery recommendation based on the following formula:
  • u is the user
  • v is the user's friend
  • ad is the advertisement to be placed.
  • Quality (u, ad) is the user's comprehensive score for the promotion information to be served, that is, the recommendation level.
  • Ptrr (u, ad) is the user's click rate of the promotion information to be served, which covers the user's willingness to click and the willingness of others to influence the click. Specifically, the user's acceptance can be calculated by the above steps S204 and S205. The influence of friends and personal participation are added together.
  • I(u,ad) and pactive The calculation of (u, ad) can be referred to the above step S206.
  • the delivery server sequentially sorts the to-be-served advertisements in the to-be-advertised advertisement set according to the delivery recommendation degree, and generates a corresponding resource list.
  • the delivery server may sort the to-be-advertised advertisements in descending order of delivery recommendation, and generate a corresponding resource list according to the sorted advertisements to be delivered.
  • the delivery server selects the to-be-advertised advertisement corresponding to the preset number of digits in the resource list as the target advertisement, and delivers the target advertisement to the user equipment corresponding to the user.
  • the delivery server obtains the to-be-served advertisement set to be delivered to the user, the user behavior data and the friend behavior data of the user, and determines the to-be-served advertisement set.
  • the placement server belongs to the preset category, and then the delivery server determines, according to the friend behavior data and the user behavior data, the influence of the friend who has interacted with the to-be-advertised advertisement on the user, and obtains the influence degree of the friend, according to the user behavior data.
  • the delivery server calculates the delivery recommendation degree of the to-be-served advertisement to the user according to the personal participation degree, the social influence degree, and the influence degree of the friend, and determines the delivery recommendation degree from the to-be-served advertisement set.
  • the advertisement to be placed that is greater than the preset recommendation degree is determined as the target advertisement by the advertisement recommendation with the recommendation degree greater than the preset recommendation degree, and the target advertisement is delivered to the user, which can comprehensively consider the user's willingness to click and the influence of the friend interaction.
  • Other factors to select the advertisement to serve to the user are beneficial to the user to view the advertisement and interact with the advertisement, and the delivery accuracy is high, and the delivery effect is good.
  • the information delivery device may include: a first acquisition module 10, a second acquisition module 20, a determination module 30, and a delivery module 40, wherein:
  • the first obtaining module 10 is configured to obtain a to-be-advertised promotional information set to be delivered to the user.
  • the to-be-advertised promotion information set is usually stored in the delivery server, and may include all promotion information that the delivery server does not deliver to the user.
  • the promotion information may be an advertisement, or may be other promotion and delivery. Information, etc., the promotion information is mainly used for some social applications, such as Weibo or some dating site clients.
  • the first obtaining module 10 obtains the to-be-advertised promotion information set to be delivered to the user.
  • the to-be-advertised promotion information collection is all the promotion that has never been delivered to the user. The sum of the information.
  • the second obtaining module 20 is configured to obtain the delivery recommendation degree corresponding to the user according to the to-be-advertised promotion information in the to-be-advertised promotion information set.
  • the delivery recommendation degree mainly points to the recommendation degree of the user to serve the promotion information to be served, which may be expressed as a score or a ratio.
  • the second obtaining module 20 may specifically include: an obtaining submodule, a first determining submodule, a second determining submodule, and a calculating submodule, where:
  • the obtaining sub-module is configured to obtain user behavior data and friend behavior data of the user.
  • the buddy behavior data mainly refers to the behavior data of all the buddies of the user
  • the user behavior data and the buddy behavior data are mainly historical behavior data of the user or the user buddy, which may be stored in the user server, and may specifically include the user. Or the behavior of the user's friends to view, comment, like, forward, or reply to the promoted information, as well as the chat and interaction between the user or the user's friends and others.
  • the user equipment In the actual application process, when the user or the user's friend views, comments, likes, forwards, or responds to the posted promotion information through the user equipment, such as a smart phone, the user equipment sends the behavior data to the user server. Stored in .
  • the first determining sub-module is configured to determine a preset category to which the to-be-advertised promotion information belongs in the to-be-advertised promotion information set.
  • the preset category may be determined according to actual needs, and may be a field in which the product in the promotion information is applied, a type of topic involved, or a promotion purpose of the promotion information, for example, may be a car, a mother or baby, Men's, women's or public welfare.
  • the preset category may be stored in the delivery server in advance, and a series of keywords are set for the preset category, so that the first determining sub-module can match the corresponding keyword according to the text content of the promotion information to be served. And according to the keyword, the corresponding preset category is obtained.
  • the second determining submodule is configured to determine, according to the preset category, the user behavior data, and the friend behavior data, the personal participation degree, the social influence degree, and the friend influence degree of the user for the to-be-advertised promotion information.
  • the user's personal participation degree, social influence degree, and friend influence degree are consideration factors for the delivery server to select a suitable promotion information to be served by the user.
  • the delivery server can accurately deliver the promotion information to the user. To improve the delivery effect.
  • the second determining submodule may specifically include: a determining unit, a first prediction unit, and a second prediction unit, where:
  • the determining unit is configured to determine, according to the friend behavior data and the user behavior data, the influence of the friend who has interacted with the to-be-advertised promotion information on the user, and obtain the influence degree of the friend.
  • the influence degree of the friend mainly refers to the degree of influence of the interaction operation of the promotion information by the user friend on the user, and the interaction mainly refers to the operation of commenting, like or forwarding the promotion information, but Does not include viewing operations.
  • the interaction mainly refers to the operation of commenting, like or forwarding the promotion information, but Does not include viewing operations.
  • the user's friend only when a user's friend interacts with the promotion information will the user be affected. If the user's friend only views or browses the promotion information, the user will not be affected.
  • the determining unit is specifically configured to:
  • the to-be-advertised promotion information has been delivered to the first friend
  • the first friend interacts with it, such as commenting, likes, or forwarding, in the process of placing the to-be-advertised promotion information to the user.
  • the user can see the interaction.
  • the interaction operation affects the user's subsequent click operation on the promotion information to be served, such as viewing or interaction, and the influence size and the user's affinity with the first friend are closely related.
  • the intimacy mainly refers to the close relationship between the user and the first friend, such as the chat frequency, the degree of interest overlap, and the mutual interaction rate.
  • the mutual interaction rate may include praising the content published by the other party. How often to reply, comment, or forward.
  • the determining unit may obtain the contact tightness by analyzing historical behavior data of the first friend and the user, and the historical behavior data may be behavior data of the user or the user friend within a month or a half year, of course, the specific time limit may be based on Depending on actual needs.
  • the first prediction unit is configured to predict the user's interest in the to-be-advertised promotion information according to the user behavior data and the preset category, and obtain personal participation.
  • the degree of interest or personal participation mainly refers to the probability that the user himself clicks on the to-be-advertised promotion information without being affected by others, and the click operation includes viewing and interaction.
  • the first prediction unit may predict the user's interest in the to-be-advertised promotion information by combining the user's own characteristics and the characteristics of the to-be-advertised promotion information, where the user's own characteristics may include the user's gender, age, interest, or historical active area.
  • the feature of the to-be-advertised promotion information mainly refers to the preset category to which the user belongs, for example, to be cast
  • the first prediction unit may determine the user's own characteristics by analyzing the historical behavior data of the user, and predict the user's promotion information to be served by using an LR algorithm or a deep learning algorithm in combination with the feature of the to-be-advertised promotion information. Interest level to get the user's personal participation.
  • the second prediction unit is configured to predict the influence of the user on the society according to the friend behavior data, the user behavior data, and the preset category, and obtain the social influence degree.
  • the social influence degree mainly refers to the interaction between the user and the promotion information, the interaction operation on the user friend itself, and the user friend's influence on the friend, that is, the social influence degree includes the user influence and the user influences the friend. After that, the influence of the user's friends.
  • the promotion information of the same user for different preset categories has different influences on the friends, and at the same time, the degree of influence of the users on different friends is different for the same promotion information.
  • the second prediction unit is specifically configured to:
  • the user After the user interacts with the served promotion information according to the interaction data and the friend behavior data, the user clicks the first click rate of the served promotion information;
  • the friend of the user friend clicks the second click rate of the served promotion information
  • the interaction rate, the first click rate, and the second click rate are calculated according to a preset algorithm to predict the social influence of the user on the social information to be served.
  • the preset algorithm may be set according to actual needs, for example, it may be a product of the interaction rate of the user and the first click rate and the second click rate of all user friends.
  • the other friend behavior data mainly refers to behavior data of all friends of the user's friends.
  • the interaction rate mainly refers to the probability that the user interacts with the promotion information belonging to the same preset category as the promotion information to be delivered in a preset time (for example, one month or half a year).
  • the click action mainly includes viewing, commenting, like or forwarding.
  • the calculation sub-module is configured to calculate, according to the personal participation degree, the social influence degree, and the influence degree of the friend, the delivery recommendation degree of the to-be-advertised promotion information to the user.
  • the calculation sub-module 24 can calculate the delivery recommendation degree by the following formula:
  • u is the user
  • v is the user's friend
  • ad is the promotion information to be served.
  • Quality (u, ad) is the user's comprehensive score for the promotion information to be served, that is, the recommendation level.
  • Ptrr(u, ad) is the user's click rate of the promotion information to be served, which includes the user's voluntary click behavior and the click behavior affected by others, and the user's acceptance can be calculated by the above determining unit and the first prediction unit.
  • Friend influence and personal engagement are calculated by specific algorithms (such as addition or multiplication, etc.).
  • the diffusion (u, ad) is the social influence degree of the user to the promotion information to be served
  • pactive(u, ad) is the probability that the user interacts with the promotion information to be served, that is, the interaction rate calculated by the second prediction unit
  • Inf(u,v) is the probability that a user clicks on the user after interacting with the promotion information to be served (ie, the influence of the user), that is, the first click rate calculated by the second prediction unit
  • I ( v, ad) the probability that a user friend's friend clicks (ie, the influence of the user's friend) after the user's friend interacts with the to-be-advertised promotion information, that is, the second click rate calculated by the second prediction unit
  • the determining module 30 is configured to determine target promotion information from the to-be-advertised promotion information set according to the delivery recommendation degree.
  • the determining module 30 is specifically configured to:
  • the to-be-advertised promotion information in the to-be-advertised promotion information set is arranged in order, and a corresponding resource list is generated;
  • the to-be-advertised promotion information corresponding to the previous preset number in the resource list is selected as the target promotion information.
  • the determining module 30 may sort the to-be-supplied recommendation information in descending order of the delivery recommendation degree.
  • the preset number of bits can be determined according to actual needs, such as 1 or 3, and so on.
  • determining module 30 can also be used to:
  • the to-be-advertised promotion information whose delivery recommendation degree is greater than the preset recommendation degree is determined as the target promotion information.
  • the preset recommendation degree may be determined according to actual needs. For example, the preset recommendation degree may be set to 8 points. When the calculated promotion information set to be placed has a recommendation degree of more than 8 points. After the promotion information is to be served, the determining module 30 may determine the to-be-advertised promotion information as the target promotion information.
  • the delivery module 40 is configured to deliver the target promotion information to the user equipment corresponding to the user.
  • the delivery module 40 may send the target promotion information to the user equipment, such as a smart phone, and display it to the user through an application in the user device (such as a microblog in the social application) to implement the target promotion information. Delivery operation.
  • the user equipment such as a smart phone
  • an application in the user device such as a microblog in the social application
  • the foregoing units may be implemented as a separate entity, or may be implemented in any combination, and may be implemented as the same or a plurality of entities.
  • the foregoing method embodiments and details are not described herein.
  • the device for promoting the promotion information obtains the to-be-advertised promotion information set to be delivered to the user through the first acquisition module 10, and according to the to-be-served promotion information set via the second acquisition module 20
  • the delivery promotion information is used to obtain the delivery promotion degree corresponding to the user, and then the determination module 30 determines the target promotion information from the to-be-advertised promotion information set according to the delivery recommendation degree, and delivers the target promotion information to the user via the delivery module 40, It can comprehensively consider the user's willingness to click and the influence of friend interaction to select the advertisement to be delivered to the user, and the delivery accuracy is high, and the delivery effect is high. it is good.
  • the embodiment of the present application further provides a delivery system for the promotion information, which includes any delivery device for the promotion information provided by the embodiment of the present application.
  • the delivery device of the promotion information may be specifically integrated into a server, such as a delivery server, for example, as follows:
  • the delivery server is configured to obtain a to-be-advertised promotion information set to be delivered to the user, obtain a delivery recommendation degree corresponding to the user according to the to-be-advertised promotion information in the to-be-advertised promotion information set, and obtain the promotion information from the to-be-served promotion information according to the delivery recommendation degree.
  • the target promotion information is determined in the collection, and the target promotion information is delivered to the user equipment corresponding to the user.
  • the delivery system of the promotion information may include any one of the promotion information delivery devices provided by the embodiments of the present application. Therefore, the beneficial effects that can be implemented by any of the promotion information delivery devices provided by the embodiments of the present application can be achieved. For details, refer to the previous embodiment, and details are not described herein again.
  • the embodiment of the present application further provides a server, which can integrate any of the promotion information delivery devices provided by the embodiments of the present application, as shown in FIG. 4, which shows the structure of the server involved in the embodiment of the present application.
  • FIG. 4 shows the structure of the server involved in the embodiment of the present application.
  • the server may include one or more processing core processor 51, one or more computer readable storage medium memories 52, a radio frequency (RF) circuit 53, a power source 54, an input unit 55, and a display unit 56, etc. component.
  • RF radio frequency
  • the processor 51 is the control center of the server, which connects various parts of the entire server using various interfaces and lines, by running or executing software programs and/or modules stored in the memory 52, and calling The data stored in the memory 52 performs various functions of the server and processes the data, thereby integrally monitoring the server.
  • the processor 51 may include one or more processing cores; preferably, the processor 51 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application, and the like.
  • the modem processor primarily handles wireless communications. It can be understood that the above modem processor may not be integrated into the processor 51.
  • the memory 52 can be used to store software programs and modules, and the processor 51 executes various functional applications and data processing by running software programs and modules stored in the memory 52.
  • the memory 52 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to Data created by the use of the server, etc.
  • memory 52 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 52 may also include a memory controller to provide access to memory 52 by processor 51.
  • the RF circuit 53 can be used for receiving and transmitting signals during the transmission and reception of information. Specifically, after receiving the downlink information of the base station, it is processed by one or more processors 51; in addition, the data related to the uplink is transmitted to the base station.
  • the RF circuit 53 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, and a Low Noise Amplifier (LNA). , duplexer, etc.
  • SIM Subscriber Identity Module
  • LNA Low Noise Amplifier
  • the RF circuit 53 can also communicate with the network and other devices through wireless communication.
  • the wireless communication may use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), and Code Division Multiple Access (CDMA). , Code Division Multiple Access), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), e-mail, Short Messaging Service (SMS), and the like.
  • GSM Global System of Mobile communication
  • GPRS General Packet Radio Service
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • LTE Long Term Evolution
  • SMS Short Messaging Service
  • the server also includes a power source 54 (such as a battery) that supplies power to the various components.
  • a power source 54 can be logically coupled to the processor 51 via a power management system to manage functions such as charging, discharging, and power management through the power management system.
  • the power source 54 can also include one or more DC or Any component such as AC power, recharging system, power failure detection circuit, power converter or inverter, power status indicator.
  • the server can also include an input unit 55 that can be used to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.
  • input unit 55 can include a touch-sensitive surface as well as other input devices. Touch-sensitive surfaces, also known as touch screens or trackpads, collect touch operations on or near the user (such as the user using a finger, stylus, etc., any suitable object or accessory on a touch-sensitive surface or touch-sensitive Operation near the surface), and drive the corresponding connecting device according to a preset program.
  • the touch sensitive surface may include two parts of a touch detection device and a touch controller.
  • the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information.
  • the processor 51 is provided and can receive commands from the processor 51 and execute them.
  • touch-sensitive surfaces can be implemented in a variety of types, including resistive, capacitive, infrared, and surface acoustic waves.
  • the input unit 55 can also include other input devices. Specifically, other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.
  • the server can also include a display unit 56 that can be used to display information entered by the user or information provided to the user and various graphical user interfaces of the server, which can be represented by graphics, text, icons, video, and It is composed of any combination.
  • the display unit 56 may include a display panel.
  • the display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.
  • the touch-sensitive surface may cover the display panel, and when the touch-sensitive surface detects a touch operation thereon or nearby, it is transmitted to the processor 51 to determine the type of the touch event, and then the processor 51 displays the type according to the type of the touch event. A corresponding visual output is provided on the panel.
  • the touch-sensitive surface and display panel are implemented as two separate components to perform input and input functions, in some embodiments, the touch-sensitive surface can be integrated with the display panel to implement input and output functions.
  • the server may further include a camera, a Bluetooth module, and the like, and details are not described herein again.
  • the processor 51 in the server loads the executable file corresponding to the process of one or more applications into the memory 52 according to the following instructions, and is stored in the memory by the processor 51.
  • the application in 52 thus implementing various functions, as follows:
  • the target promotion information is delivered to the user equipment corresponding to the user.
  • the server provided in this embodiment can obtain the to-be-advertised promotion information set to be delivered to the user, and obtain the delivery recommendation degree corresponding to the user according to the to-be-advertised promotion information in the to-be-advertised promotion information set. Determining the target promotion information from the to-be-advertised promotion information set according to the delivery recommendation degree, and delivering the target promotion information to the user, and comprehensively considering the user's click intention and the influence of the friend interaction to select the advertisement to be delivered to the user, and the delivery is accurate. High degree.
  • the program may be stored in a computer readable storage medium, and the storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.
  • ROM Read Only Memory
  • RAM Random Access Memory

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本申请公开了一种推广信息的投放方法、装置、系统及存储介质，该推广信息的投放方法包括：获取需要向用户投放的待投放推广信息集合；根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度；根据该投放推荐度从该待投放推广信息集合中确定目标推广信息；向该用户投放该目标推广信息。上述推广信息的投放方法能综合考虑用户的点击意愿和好友互动影响等因素来选择广告向用户投放，投放精准度高，投放效果好。

Description

一种推广信息的投放方法、装置、系统及存储介质
本申请要求于2016年5月25日提交中国专利局、申请号201610352701.0，发明名称为“一种推广信息的投放方法、装置及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种推广信息的投放方法、装置，系统及存储介质。
背景技术
用户在使用社交应用的过程中，通常会接收到服务器推送的推广信息，譬如，用于推广某一产品或事物的广告。这些推广信息对于广告商来说意义重大，因此，如何对推广信息进行投放，一直以来是业界关注的重点。
目前，在为广告寻找投放用户时，一般都会先分析用户对广告的感兴趣程度，比如通过用户行为或用户标签等方式来确定用户对广告的感兴趣程度，从而预估用户对该广告的点击率，然后基于该点击率对广告进行打分，按分数从高到低的顺序向用户投放广告。这种广告投放方式由于只考虑了用户点击率的预估，投放并不精准，投放效果不佳。
发明内容
本申请的目的在于提供一种推广信息的投放方法、装置及系统，以解决现有推广信息投放精准性差、投放效果不佳的技术问题。
为解决上述技术问题，本申请实施例提供以下技术方案：
一种推广信息的投放方法，其包括：
投放服务器获取需要向用户投放的待投放推广信息集合；
投放服务器根据所述待投放推广信息集合中的待投放推广信息获取所述用户对应的投放推荐度；
投放服务器根据所述投放推荐度从所述待投放推广信息集合中确定目标推广信息；
投放服务器向所述用户对应的用户设备投放所述目标推广信息。
为解决上述技术问题，本申请实施例还提供以下技术方案：
一种推广信息的投放装置，其包括：
第一获取模块，用于获取需要向用户投放的待投放推广信息集合；
第二获取模块，用于根据所述待投放推广信息集合中的待投放推广信息获取所述用户对应的投放推荐度；
确定模块，用于根据所述投放推荐度从所述待投放推广信息集合中确定目标推广信息；
投放模块，用于向所述用户对应的用户设备投放所述目标推广信息。
为解决上述技术问题，本申请实施例还提供以下技术方案：
一种推广信息的投放系统，其包括上述任意一项所述的推广信息的投放装置。
本申请实施例提供了一种计算机存储介质，用于储存为上述推广信息的投放装置所用的计算机软件指令，其包含用于执行上述推广信息的投放方法的步骤。
本申请所述的推广信息的投放方法、装置、系统及存储介质，通过获取需要向用户投放的待投放推广信息集合，并根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度，之后，根据该投放推荐度从该待投放推广信息集合中确定目标推广信息，并向该用户投放该目标推广信息，能综合考虑用户的点击意愿和好友互动影响等因素来选择广告向用户投放，投放精准度高，投放效果好。
附图说明
下面结合附图，通过对本申请的具体实施方式详细描述，将使本申请的技术方案及其它有益效果显而易见。
图1a是本申请实施例提供的推广信息的投放系统的场景示意图。
图1b为本申请实施例提供的推广信息的投放方法的流程示意图。
图2a为本申请实施例提供的推广信息的另一投放方法的流程示意图。
图2b为本申请实施例提供的个人参与度、社会影响度和受好友影响度的示意图。
图3为本申请实施例提供的推广信息的投放装置的结构示意图。
图4为本申请实施例提供的服务器的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请实施例提供一种推广信息的投放方法、装置及系统。
请参阅图1a，该推广信息的投放系统可以包括本申请实施例所提供的任一种推广信息的投放装置，该推广信息的投放装置具体可以集成在服务器(如投放服务器)中。此外，该推广信息的投放系统还可以包括其他的设备，比如用户设备和用户服务器，其中，用户设备(比如智能手机、电脑等)用于接收投放服务器所需投放的待投放推广信息，用户服务器用于收集各个用户针对已投放的推广信息的行为数据，投放服务器用于从用户服务器中获取用户的行为数据，并根据该行为数据计算该用户针对该待投放推荐信息的投放推荐度。
如图1a所示，在通过网络对某用户投放广告之前，需要选择合适的广告进行投放，因此，投放服务器可以获取需要向该用户投放的待投放广告集合，并获取该用户针对该待投放广告集合中的待投放广告的投放推荐度，之后，投放服务器根据该投放推荐度从该待投放广告集合中确定目标广告，比如，将投放推荐度高的确定为目标广告，并将该目标待投放广告发送至用户设备以进行投放，能综合考虑用户的点击意愿和好友互动影响等因素来选择广告向用户投放，投放精准度高，投放效果好。
以下将分别进行详细说明。需说明的是，以下实施例的序号不作为实施例优先顺序的限定。
第一实施例
本实施例将从推广信息的投放装置的角度进行描述，该推广信息的投放装置可以集成在投放服务器中。
请参阅图1b，图1b具体描述了本申请第一实施例提供的推广信息的投放方法，其可以包括：
S101、获取需要向用户投放的待投放推广信息集合。
本实施例中，该待投放推广信息集合通常存储在投放服务器中，其可以包括投放服务器未向该用户投放的所有推广信息，该推广信息可以是广告，也可以是其他一些需要进行推广和投放的信息，等等，该推广信息主要用于投放在一些社交应用中，比如微博或一些交友网站的客户端等。当投放服务器接收到用户设备发送的投放请求时，其会获取需要向用户投放的待投放推广信息集合，通常，该待投放推广信息集合为从未向该用户投放过的所有推广信息总和。
S102、根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度。
本实施例中，该投放推荐度主要指向用户投放该待投放推广信息的推荐程度，其可以表现为分数或者比值。
优选的，上述步骤S102具体可以包括：
(1)获取该用户的用户行为数据和好友行为数据。
本实施例中，该好友行为数据主要指用户的所有好友的行为数据，该用户行为数据和好友行为数据主要为用户或用户好友的历史行为数据，其可以储存在用户服务器中，具体可以包括用户或用户好友对已投放的推广信息进行查看、评论、点赞、转发或回复等行为，以及用户或用户好友与他人的聊天和互动行为。
实际应用过程中，当用户或用户好友通过用户设备，比如智能手机，对已 投放的推广信息进行查看、评论、点赞、转发或回复等行为时，用户设备会将该行为数据发送至用户服务器中进行存储。
(2)确定该待投放推广信息集合中的待投放推广信息所属的预设类别。
本实施例中，该预设类别可以根据实际需求而定，其可以是推广信息中的产品所应用的领域、涉及的主题类型或者该推广信息的推广目的，比如，可以是汽车、母婴、男装、女装或者公益类等。实际应用时，可以预先将该预设类别储存在投放服务器中，并对该预设类别设置一系列关键词，从而可以根据待投放推广信息的文字内容匹配对应的关键词，得到对应的预设类别。
(3)根据该预设类别、用户行为数据和好友行为数据确定该用户针对该待投放推广信息的个人参与度、社会影响度和受好友影响度。
本实施例中，用户的个人参与度、社会影响度和受好友影响度是投放服务器选择适合用户的待投放推广信息的考虑因素，通过参考这些因素，投放服务器可以较精准的向用户投放推广信息，提高投放效果。
优选的，上述步骤(3)具体可以包括：
(3A)根据该好友行为数据和用户行为数据确定已与该待投放推广信息互动的好友对该用户产生的影响力，得到受好友影响度。
本实施例中，该受好友影响度主要指用户好友对推广信息的互动操作对该用户的影响程度，该互动主要指对推广信息进行评论、点赞或转发等操作，但不包括查看操作。通常，只有当用户好友对推广信息进行互动之后，才会对用户产生影响，若用户好友只是查看或者浏览该推广信息，则不会对用户产生影响。
优选的，上述步骤(3A)具体可以包括：
根据该好友行为数据确定已与该待投放推广信息互动的第一好友，并从该好友行为数据中获取该第一好友的好友行为子数据；
根据该用户行为数据和该好友行为子数据统计该用户与该第一好友的亲密度，并将该亲密度确定为该用户的受好友影响度。
本实施例中，当该待投放推广信息已向第一好友投放时，若该第一好友对 其进行互动，譬如评论、点赞或转发，则在该待投放推广信息向用户投放的过程中，用户可以看到该互动操作。通常，该互动操作会影响用户后续对该待投放推广信息的点击操作，比如查看或互动，并且该影响力的大小和用户与该第一好友间的亲密度息息相关。
具体的，该亲密度主要指用户与该第一好友间的联系紧密程度，比如聊天频率、兴趣重合度以及双方互动率等，其中，该双方互动率可以包括向对方所发表内容进行点赞、回复、评论或转发等操作的频率。可以通过分析该第一好友和用户的历史行为数据得到联系紧密度，该历史行为数据可以为近期一个月内或者半年内该用户或用户好友的行为数据，当然，具体时间期限可以根据实际需求而定。
(3B)根据该用户行为数据和预设类别预测该用户对该待投放推广信息的兴趣度，得到个人参与度。
本实施例中，该兴趣度或个人参与度主要指在不受他人影响的情况下，用户自身对该待投放推广信息进行点击操作的概率。可以结合用户自身特征和该待投放推广信息的特征来预测该用户对该待投放推广信息的兴趣度，其中，该用户自身特征可以包括用户的性别、年龄、兴趣或者历史活跃领域等信息，其可以通过对用户的历史行为数据分析来获得，该待投放推广信息的特征主要指其所属的预设类别，比如该待投放推广信息中的产品所应用的领域、涉及的主题类型或者推广目的等。
具体的，可以通过分析用户的历史行为数据来确定该用户的自身特征，并结合该待投放推广信息的特征通过逻辑回归(Logistic Regression，LR)算法或者深度学习算法来预测该用户对该待投放推广信息的兴趣度，以得到用户的个人参与度。
(3C)根据该好友行为数据、用户行为数据和预设类别预测该用户对社会产生的影响力，得到社会影响度。
本实施例中，该社会影响度主要指用户与推广信息进行互动后，该互动操作对用户好友本身，以及用户好友对其好友的影响程度，也即该社会影响度包 括用户影响力和用户影响好友后，用户好友的影响力。通常，同一用户针对不同预设类别的推广信息，其对好友的影响程度是不同的，同时，对于同一推广信息，用户对不同好友的影响程度也是不同的。
优选的，上述步骤(3C)具体可以包括：
获取用户好友的其他好友行为数据；
从该用户行为数据中获取该用户与属于该预设类别的所有已投放推广信息互动的互动数据，并统计对应的互动率；
根据该互动数据和该好友行为数据统计该用户与该已投放推广信息互动后，该用户好友点击该已投放推广信息的第一点击率；
根据该好友行为数据和其他好友行为数据统计该用户好友与该已投放推广信息互动后，该用户好友的好友点击该已投放推广信息的第二点击率；
根据该互动率、第一点击率和第二点击率按照预置算法计算，以预测该用户针对该待投放推广信息对社会的社会影响度。
本实施例中，该预置算法可以根据实际需求进行设定，譬如，可以是该用户的互动率与所有用户好友的第一点击率和第二点击率之间的乘积。该其他好友行为数据主要指用户好友的所有好友的行为数据。该互动率主要指在以往预设时间内(比如一个月或半年)，用户对与该待投放推广信息属于同一预设类别的推广信息进行互动的概率。该点击操作主要包括查看、评论、点赞或转发等行为。
(4)根据该个人参与度、社会影响度和受好友影响度计算向该用户投放该待投放推广信息的投放推荐度。
本实施例中，可以通过以下公式计算该投放推荐度：
quality(u，ad)
＝pctr(u，ad)+diffusion(u，ad)
＝pctr(u，ad)+Σv∈F(u)pactive(u，ad)*inf(u，v)*I(v，ad)
＝pctr(u，ad)+pactive(u，ad)*I(u，ad)
其中，u表示用户，v表示用户好友，ad表示待投放推广信息。quality(u， ad)为用户对该待投放推广信息的综合得分，也即该投放推荐度。pctr(u，ad)为用户对该待投放推广信息的点击率，其包括用户自愿点击行为和受他人影响点击行为，具体可以由上述步骤(3A)和(3B)计算得出的该用户的受好友影响度和个人参与度通过特定算法(比如加法或者乘法等等)计算出。
diffusion(u，ad)为用户对该待投放推广信息的社会影响度，pactive(u，ad)为用户与该待投放推广信息互动的概率，也即上述步骤(3C)中提及的互动率，inf(u，v)为用户与该待投放推广信息互动后，某一用户好友点击的概率(即该用户的影响力)，也即上述步骤(3C)中提及的第一点击率，I(v，ad)为某一用户好友与该待投放推广信息互动后，该用户好友的好友点击的概率(即该用户好友的影响力)，也即上述步骤(3C)中提及的第二点击率，根据PageRank(网页排名)算法思路，用户对该待投放推广信息的社会影响度(即该I(u，ad))为用户好友的影响力传播汇总，也即，I(u，ad)＝Σv∈F(u)inf(u，v)*I(v，ad)。
S103、根据该投放推荐度从该待投放推广信息集合中确定目标推广信息。
优选的，上述步骤S103具体可以包括：
根据该投放推荐度将该待投放推广信息集合中的待投放推广信息按顺序排列，并生成相应的资源列表；
选取该资源列表中前预设位数对应的该待投放推广信息作为目标推广信息。
本实施例中，可以按照投放推荐度从高到低的顺序将该待投放推荐信息进行排序。该预设位数可以根据实际需求而定，比如可以为1或者3，等等。
当然，该目标推广信息的确定方式还可以为：
从该待投放推广信息集合中确定该投放推荐度大于预设推荐度的待投放推广信息；
将该投放推荐度大于预设推荐度的待投放推广信息确定为目标推广信息。
本实施例中，该预设推荐度可以根据实际需求而定，比如，该预设推荐度可以设定为8分，当计算得出的该待投放推广信息集合中存在投放推荐度大于8分的待投放推广信息，则可以将这些待投放推广信息确定为目标推广信息。
S104、向该用户对应的用户设备投放该目标推广信息。
本实施例中，投放服务器可以将该目标推广信息发送至用户设备，比如智能手机，并通过用户设备中的应用程序(比如社交应用中的微博或Facebook等)向用户显示，以实现该目标推广信息的投放操作。
由上述可知，本实施例提供的推广信息的投放方法，通过获取需要向用户投放的待投放推广信息集合，并根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度，之后，根据该投放推荐度从该待投放推广信息集合中确定目标推广信息，并向该用户投放该目标推广信息，能综合考虑用户的点击意愿和好友互动影响等因素来选择广告向用户投放，投放精准度高，投放效果好。
第二实施例
根据实施例一所描述的方法，以下将举例作进一步详细说明。
在本实施例中，将以该推广信息的投放装置集成在投放服务器中，该推广信息为广告为例进行详细说明。
如图2a所示，一种推广信息的投放方法，具体流程可以如下：
S201、投放服务器获取需要向用户投放的待投放广告集合。
譬如，当投放服务器接收到用户设备发送的广告投放请求时，其可以从自身数据库中获取未向该用户投放过的所有广告。
S202、投放服务器获取该用户的用户行为数据和好友行为数据。
譬如，投放服务器可以获取近半年内该用户以及该用户所有好友的行为数据，该行为数据包括用户或用户好友对已投放的广告进行查看、评论、点赞、转发或回复等行为数据，以及用户或用户好友与他人的聊天和互动的行为数据。
S203、投放服务器确定该待投放广告集合中的待投放广告所属的预设类别。
譬如，该预设类别可以为预设主题类型，其可以包括护肤、汽车、母婴、男装或女装等。投放服务器可以通过该待投放广告中的文字信息匹配对应的关键词，并根据匹配出的关键词得到对应的预设类别。比如，当该待投放广告中 多次提及汽车或者汽车配件(比如汽车轮胎)时，投放服务器匹配的关键词即为汽车或轮胎，得出的预设类别为汽车。
S204、投放服务器根据该好友行为数据和用户行为数据确定已与该待投放广告互动的好友对该用户产生的影响力，得到受好友影响度。
优选的，上述步骤S204具体可以包括：
根据该好友行为数据确定已与该待投放广告互动的第一好友，并从该好友行为数据中获取该第一好友的好友行为子数据；
根据该用户行为数据和该好友行为子数据统计该用户与该第一好友的亲密度，并将该亲密度确定为该用户的受好友影响度。
譬如，可以根据该好友行为数据确定出已对该待投放广告进行评论、点赞或者转发等行为的用户好友作为该第一好友，并根据该第一好友与用户之间的历史聊天频率、兴趣重合度和双方互动率等数据来计算该第一好友与用户间的亲密度。
S205、投放服务器根据该用户行为数据和预设类别预测该用户对该待投放广告的兴趣度，得到个人参与度。
譬如，当该待投放广告属于汽车类时，投放服务器可以统计在近半年内，用户对已投放的汽车类广告的查看或互动数据，并通过LR算法来计算预测该用户对该待投放广告的兴趣度。
S206、投放服务器根据该好友行为数据、用户行为数据和预设类别预测该用户对社会产生的影响力，得到社会影响度。
优选的，上述步骤S206具体可以包括：
获取用户好友的其他好友行为数据；
从该用户行为数据中获取该用户与属于该预设类别的所有已投放广告互动的互动数据，并统计对应的互动率；
根据该互动数据和该好友行为数据统计该用户与该已投放广告互动后，该用户好友点击该已投放广告的第一点击率；
根据该好友行为数据和其他好友行为数据统计该用户好友与该已投放广告 互动后，该用户好友的好友点击该已投放广告的第二点击率；
根据该互动率、第一点击率和第二点击率按照预置算法计算，以预测该用户针对该待投放广告对社会的社会影响度。
譬如，投放服务器可以获取近半年内用户对已投放的汽车类广告进行评论、点赞或转发等互动行为的数据作为互动数据，并计算出对应的互动率pactive(u，ad)。同时，投放服务器还可以计算当该用户与某个已投放的汽车类广告进行互动后，用户好友点击该汽车类广告的第一点击率inf(u，v)，以及当用户好友点击该汽车类广告后，用户好友的好友点击同一汽车类广告的第二点击率I(v，ad)，并通过获取该用户的互动率pactive(u，ad)与每一用户好友的第一点击率inf(u，v)和第二点击率I(v，ad)之间乘积的总和来计算该用户的社会影响度I(u，ad)，也即，I(u，ad)＝Σv∈F(u)inf(u，v)*I(v，ad)。
S207、投放服务器根据该个人参与度、社会影响度和受好友影响度计算向该用户投放该待投放广告的投放推荐度。
譬如，投放服务器可以根据以下公式计算该投放推荐度：
quality(u，ad)
＝pctr(u，ad)+diffusion(u，ad)
＝pctr(u，ad)+Σv∈F(u)pactive(u，ad)*inf(u，v)*I(v，ad)
＝pctr(u，ad)+pactive(u，ad)*I(u，ad)
其中，u表示用户，v表示用户好友，ad表示待投放广告。quality(u，ad)为用户对该待投放推广信息的综合得分，也即该投放推荐度。pctr(u，ad)为用户对该待投放推广信息的点击率，其涵盖了用户自愿点击意愿和受他人影响点击意愿，具体可以通过将上述步骤S204和S205中计算得出的该用户的受好友影响度和个人参与度相加得出。diffusion(u，ad)为用户对该待投放推广信息的社会影响度，diffusion(u，ad)＝pactive(u，ad)*I(u，ad)，其中，I(u，ad)和pactive(u，ad)的计算可以参见上述步骤S206。
比如，如图2b所示，对于待投放的护肤类广告Ad1，若该用户的受好友影响度为0.6，用户的个人参与度为0.3，则pctr(u，ad)＝0.6+0.3＝0.9。若用户对一 部分好友的社会影响度为0.2，对另一部分好友的社会影响度为0.1，则diffusion(u，ad)＝0.2+0.1＝0.3，最后，该待投放广告Ad1的投放推荐度quality(u，ad1)＝0.9+0.3＝1.2；
对于待投放的汽车类广告Ad2，若该用户的受好友影响度为0.3，用户的个人参与度为0.4，则pctr(u，ad)＝0.3+0.4＝0.7。若用户对一部分好友的社会影响度为0.4，对另一部分好友的社会影响度为0.3，则diffusion(u，ad)＝0.4+0.3＝0.7，最后，该待投放广告Ad2的投放推荐度quality(u，ad2)＝0.7+0.7＝1.4。
S208、投放服务器根据该投放推荐度将该待投放广告集合中的待投放广告按顺序排序，并生成相应的资源列表。
譬如，投放服务器可以按照投放推荐度从高到低的顺序将待投放广告进行排序，并根据排序后的待投放广告生成相应的资源列表。
S209、投放服务器选取该资源列表中前预设位数对应的待投放广告作为目标广告，并向该用户对应的用户设备投放该目标广告。
譬如，投放服务器可以将资源列表上的第一个待投放广告作为目标广告，比如，对于待投放广告集合Ad1和Ad2，由于quality(u，ad1)＝1.2＜quality(u，ad2)＝1.4，故Ad2为资源列表上的第一个待投放广告，从而该投放服务器确定的目标广告为Ad2，之后，该投放服务器可以将Ad2投放至用户设备中的微博等社交应用中。
由上述可知，本实施例提供的推广信息的投放方法，投放服务器通过获取需要向用户投放的待投放广告集合和该用户的用户行为数据和好友行为数据，并确定该待投放广告集合中的待投放广告所属的预设类别，接着，投放服务器根据该好友行为数据和用户行为数据确定已与该待投放广告互动的好友对该用户产生的影响力，得到受好友影响度，根据该用户行为数据和预设类别预测该用户对该待投放广告的兴趣度，得到个人参与度，并根据该好友行为数据、用户行为数据和预设类别预测该用户对社会产生的影响力，得到社会影响度，之后，投放服务器根据该个人参与度、社会影响度和受好友影响度计算向该用户投放该待投放广告的投放推荐度，并从该待投放广告集合中确定该投放推荐度 大于预设推荐度的待投放广告，最后将该投放推荐度大于预设推荐度的待投放广告确定为目标广告，并向该用户投放该目标广告，能综合考虑用户的点击意愿和好友互动影响等因素来选择广告向用户投放，有利于用户查看该广告并与广告发生互动，投放精准度高，投放效果好。
第三实施例
在实施例一和实施例二所述方法的基础上，本实施例将从推广信息的投放装置的角度进一步进行描述，请参阅图3，图3具体描述了本申请第三实施例提供的推广信息的投放装置，其可以包括：第一获取模块10、第二获取模块20、确定模块30和投放模块40，其中：
(1)第一获取模块10
第一获取模块10，用于获取需要向用户投放的待投放推广信息集合。
本实施例中，该待投放推广信息集合通常存储在投放服务器中，其可以包括投放服务器未向该用户投放的所有推广信息，该推广信息可以是广告，也可以是其他一些需要进行推广和投放的信息，等等，该推广信息主要用于投放在一些社交应用中，比如微博或一些交友网站的客户端等。当投放服务器接收到用户设备发送的投放请求时，第一获取模块10会获取需要向用户投放的待投放推广信息集合，通常，该待投放推广信息集合为从未向该用户投放过的所有推广信息总和。
(2)第二获取模块20
第二获取模块20，用于根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度。
本实施例中，该投放推荐度主要指向用户投放该待投放推广信息的推荐程度，其可以表现为分数或者比值。
优选的，该第二获取模块20具体可以包括：获取子模块、第一确定子模块、第二确定子模块和计算子模块，其中：
获取子模块，用于获取该用户的用户行为数据和好友行为数据。
本实施例中，该好友行为数据主要指用户的所有好友的行为数据，该用户行为数据和好友行为数据主要为用户或用户好友的历史行为数据，其可以储存在用户服务器中，具体可以包括用户或用户好友对已投放的推广信息进行查看、评论、点赞、转发或回复等行为，以及用户或用户好友与他人的聊天和互动行为。
实际应用过程中，当用户或用户好友通过用户设备，比如智能手机，对已投放的推广信息进行查看、评论、点赞、转发或回复等行为时，用户设备会将该行为数据发送至用户服务器中进行存储。
第一确定子模块，用于确定该待投放推广信息集合中的待投放推广信息所属的预设类别。
本实施例中，该预设类别可以根据实际需求而定，其可以是推广信息中的产品所应用的领域、涉及的主题类型或者该推广信息的推广目的，比如，可以是汽车、母婴、男装、女装或者公益类等。实际应用时，可以预先将该预设类别储存在投放服务器中，并对该预设类别设置一系列关键词，从而第一确定子模块可以根据待投放推广信息的文字内容匹配对应的关键词，并根据该关键词得到对应的预设类别。
第二确定子模块，用于根据该预设类别、用户行为数据和好友行为数据确定该用户针对该待投放推广信息的个人参与度、社会影响度和受好友影响度。
本实施例中，用户的个人参与度、社会影响度和受好友影响度是投放服务器选择适合用户的待投放推广信息的考虑因素，通过参考这些因素，投放服务器可以较精准的向用户投放推广信息，提高投放效果。
优选的，该第二确定子模块具体可以包括：确定单元、第一预测单元和第二预测单元，其中：
确定单元，用于根据该好友行为数据和用户行为数据确定已与该待投放推广信息互动的好友对该用户产生的影响力，得到受好友影响度。
本实施例中，该受好友影响度主要指用户好友对推广信息的互动操作对该用户的影响程度，该互动主要指对推广信息进行评论、点赞或转发等操作，但 不包括查看操作。通常，只有当用户好友对推广信息进行互动之后，才会对用户产生影响，若用户好友只是查看或者浏览该推广信息，则不会对用户产生影响。
优选的，该确定单元具体可以用于：
根据该好友行为数据确定已与该待投放推广信息互动的第一好友，并从该好友行为数据中获取该第一好友的好友行为子数据；
根据该用户行为数据和该好友行为子数据统计该用户与该第一好友的亲密度，并将该亲密度确定为该用户的受好友影响度。
本实施例中，当该待投放推广信息已向第一好友投放时，若该第一好友对其进行互动，譬如评论、点赞或转发，则在该待投放推广信息向用户投放的过程中，用户可以看到该互动操作。通常，该互动操作会影响用户后续对该待投放推广信息的点击操作，比如查看或互动，并且该影响力的大小和用户与该第一好友间的亲密度息息相关。
具体的，该亲密度主要指用户与该第一好友间的联系紧密程度，比如聊天频率、兴趣重合度以及双方互动率等，其中，该双方互动率可以包括向对方所发表内容进行点赞、回复、评论或转发等操作的频率。该确定单元可以通过分析该第一好友和用户的历史行为数据得到联系紧密度，该历史行为数据可以为近期一个月内或者半年内该用户或用户好友的行为数据，当然，具体时间期限可以根据实际需求而定。
第一预测单元，用于根据该用户行为数据和预设类别预测该用户对该待投放推广信息的兴趣度，得到个人参与度。
本实施例中，该兴趣度或个人参与度主要指在不受他人影响的情况下，用户自身对该待投放推广信息进行点击操作的概率，该点击操作包括查看和互动。第一预测单元可以结合用户自身特征和该待投放推广信息的特征来预测该用户对该待投放推广信息的兴趣度，其中，该用户自身特征可以包括用户的性别、年龄、兴趣或者历史活跃领域等信息，其可以通过对用户的历史行为数据进行分析来获得，该待投放推广信息的特征主要指其所属的预设类别，比如该待投 放推广信息中的产品所应用的领域、涉及的主题类型或者推广目的等。
具体的，第一预测单元可以通过分析用户的历史行为数据来确定该用户的自身特征，并结合该待投放推广信息的特征通过LR算法或者深度学习算法来预测该用户对该待投放推广信息的兴趣度，以得到用户的个人参与度。
第二预测单元，用于根据该好友行为数据、用户行为数据和预设类别预测该用户对社会产生的影响力，得到社会影响度。
本实施例中，该社会影响度主要指用户与推广信息进行互动后，该互动操作对用户好友本身，以及用户好友对其好友的影响，也即该社会影响度包括用户影响力和用户影响好友后，用户好友的影响力。通常，同一用户针对不同预设类别的推广信息，其对好友的影响程度是不同的，同时，对于同一推广信息，用户对不同好友的影响程度也是不同的。
优选的，该第二预测单元具体可以用于：
获取用户好友的其他好友行为数据；
从该用户行为数据中获取该用户与属于该预设类别的所有已投放推广信息互动的互动数据，并统计对应的互动率；
根据该互动数据和该好友行为数据统计该用户与该已投放推广信息互动后，该用户好友点击该已投放推广信息的第一点击率；
根据该好友行为数据和其他好友行为数据统计该用户好友与该已投放推广信息互动后，该用户好友的好友点击该已投放推广信息的第二点击率；
根据该互动率、第一点击率和第二点击率按照预置算法计算，以预测该用户针对该待投放推广信息对社会的社会影响度。
本实施例中，该预置算法可以根据实际需求进行设定，例如，其可以是该用户的互动率与所有用户好友的第一点击率和第二点击率之间的乘积。该其他好友行为数据主要指用户好友的所有好友的行为数据。该互动率主要指在以往预设时间内(比如一个月或半年)，用户对与该待投放推广信息属于同一预设类别的推广信息进行互动的概率。该点击操作主要包括查看、评论、点赞或转发等行为。
计算子模块，用于根据该个人参与度、社会影响度和受好友影响度计算向该用户投放该待投放推广信息的投放推荐度。
本实施例中，计算子模块24可以通过以下公式计算该投放推荐度：
quality(u，ad)
＝pctr(u，ad)+diffusion(u，ad)
＝pctr(u，ad)+Σv∈F(u)pactive(u，ad)*inf(u，v)*I(v，ad)
＝pctr(u，ad)+pactive(u，ad)*I(u，ad)
其中，u表示用户，v表示用户好友，ad表示待投放推广信息。quality(u，ad)为用户对该待投放推广信息的综合得分，也即该投放推荐度。pctr(u，ad)为用户对该待投放推广信息的点击率，其包括用户自愿点击行为和受他人影响点击行为，具体可以由上述确定单元和第一预测单元计算得出的该用户的受好友影响度和个人参与度通过特定算法(比如加法或者乘法等等)计算出。
diffusion(u，ad)为用户对该待投放推广信息的社会影响度，pactive(u，ad)为用户与该待投放推广信息互动的概率，也即上述第二预测单元计算出的互动率，inf(u，v)为用户与该待投放推广信息互动后，某一用户好友点击的概率(即该用户的影响力)，也即上述第二预测单元计算出的第一点击率，I(v，ad)为某一用户好友与该待投放推广信息互动后，该用户好友的好友点击的概率(即该用户好友的影响力)，也即上述第二预测单元计算出的第二点击率，根据PageRank(网页级别)算法思路，用户对该待投放推广信息的社会影响度(即该I(u，ad))为用户好友的影响力传播汇总，也即，I(u，ad)＝Σv∈F(u)inf(u，v)*I(v，ad)。
(3)确定模块30
确定模块30，用于根据该投放推荐度从该待投放推广信息集合中确定目标推广信息。
优选的，该确定模块30具体可以用于：
根据该投放推荐度将该待投放推广信息集合中的待投放推广信息按顺序排列，并生成相应的资源列表；
选取该资源列表中前预设位数对应的该待投放推广信息作为目标推广信息。
本实施例中，确定模块30可以按照投放推荐度从高到低的顺序将该待投放推荐信息进行排序。该预设位数可以根据实际需求而定，比如可以为1或者3，等等。
当然，该确定模块30还可以用于：
从该待投放推广信息集合中确定该投放推荐度大于预设推荐度的待投放推广信息；
将该投放推荐度大于预设推荐度的待投放推广信息确定为目标推广信息。
本实施例中，该预设推荐度可以根据实际需求而定，比如，该预设推荐度可以设定为8分，当计算得出的该待投放推广信息集合中存在投放推荐度大于8分的待投放推广信息，则确定模块30可以将这些待投放推广信息确定为目标推广信息。
(4)投放模块40
投放模块40，用于向该用户对应的用户设备投放该目标推广信息。
本实施例中，投放模块40可以将该目标推广信息发送至用户设备，比如智能手机，并通过用户设备中的应用程序(比如社交应用中的微博)向用户显示，以实现该目标推广信息的投放操作。
具体实施时，以上各个单元可以作为独立的实体来实现，也可以进行任意组合，作为同一或若干个实体来实现，以上各个单元的具体实施可参见前面的方法实施例，在此不再赘述。
由上述可知，本实施例提供的推广信息的投放装置，通过第一获取模块10获取需要向用户投放的待投放推广信息集合，并经由第二获取模块20根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度，之后，通过确定模块30根据该投放推荐度从该待投放推广信息集合中确定目标推广信息，并经由投放模块40向该用户投放该目标推广信息，能综合考虑用户的点击意愿和好友互动影响等因素来选择广告向用户投放，投放精准度高，投放效果 好。
第四实施例
相应的，本申请实施例还提供一种推广信息的投放系统，包括本申请实施例所提供的任一种推广信息的投放装置，该推广信息的投放装置具体可参见实施例三。
其中，该推广信息的投放装置具体可以集成在服务器，如投放服务器等设备中，例如，可以如下：
投放服务器，用于获取需要向用户投放的待投放推广信息集合，根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度，根据该投放推荐度从该待投放推广信息集合中确定目标推广信息，并向该用户对应的用户设备投放该目标推广信息。
以上各个设备的具体实施可参见前面的实施例，在此不再赘述。
由于该推广信息的投放系统可以包括本申请实施例所提供的任一种推广信息的投放装置，因此，可以实现本申请实施例所提供的任一种推广信息的投放装置所能实现的有益效果，详见前面的实施例，在此不再赘述。
第五实施例
本申请实施例还提供一种服务器，该服务器可以集成本申请实施例所提供的任一种推广信息的投放装置，如图4所示，其示出了本申请实施例所涉及的服务器的结构示意图，具体来讲：
该服务器可以包括一个或者一个以上处理核心的处理器51、一个或一个以上计算机可读存储介质的存储器52、射频(Radio Frequency，RF)电路53、电源54、输入单元55、以及显示单元56等部件。本领域技术人员可以理解，图4中示出的服务器结构并不构成对服务器的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
处理器51是该服务器的控制中心，利用各种接口和线路连接整个服务器的各个部分，通过运行或执行存储在存储器52内的软件程序和/或模块，以及调用 存储在存储器52内的数据，执行服务器的各种功能和处理数据，从而对服务器进行整体监控。可选的，处理器51可包括一个或多个处理核心；优选的，处理器51可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器51中。
存储器52可用于存储软件程序以及模块，处理器51通过运行存储在存储器52的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器52可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据服务器的使用所创建的数据等。此外，存储器52可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器52还可以包括存储器控制器，以提供处理器51对存储器52的访问。
RF电路53可用于收发信息过程中，信号的接收和发送，特别地，将基站的下行信息接收后，交由一个或者一个以上处理器51处理；另外，将涉及上行的数据发送给基站。通常，RF电路53包括但不限于天线、至少一个放大器、调谐器、一个或多个振荡器、用户身份模块(SIM)卡、收发信机、耦合器、低噪声放大器(LNA，Low Noise Amplifier)、双工器等。此外，RF电路53还可以通过无线通信与网络和其他设备通信。所述无线通信可以使用任一通信标准或协议，包括但不限于全球移动通讯系统(GSM，Global System of Mobile communication)、通用分组无线服务(GPRS，General Packet Radio Service)、码分多址(CDMA，Code Division Multiple Access)、宽带码分多址(WCDMA，Wideband Code Division Multiple Access)、长期演进(LTE，Long Term Evolution)、电子邮件、短消息服务(SMS，Short Messaging Service)等。
服务器还包括给各个部件供电的电源54(比如电池)，优选的，电源54可以通过电源管理系统与处理器51逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源54还可以包括一个或一个以上的直流或 交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
该服务器还可包括输入单元55，该输入单元55可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入。具体地，在一个具体的实施例中，输入单元55可包括触敏表面以及其他输入设备。触敏表面，也称为触摸显示屏或者触控板，可收集用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触敏表面上或在触敏表面附近的操作)，并根据预先设定的程式驱动相应的连接装置。可选的，触敏表面可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测用户的触摸方位，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成触点坐标，再送给处理器51，并能接收处理器51发来的命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触敏表面。除了触敏表面，输入单元55还可以包括其他输入设备。具体地，其他输入设备可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
该服务器还可包括显示单元56，该显示单元56可用于显示由用户输入的信息或提供给用户的信息以及服务器的各种图形用户接口，这些图形用户接口可以由图形、文本、图标、视频和其任意组合来构成。显示单元56可包括显示面板，可选的，可以采用液晶显示器(LCD，Liquid Crystal Display)、有机发光二极管(OLED，Organic Light-Emitting Diode)等形式来配置显示面板。进一步的，触敏表面可覆盖显示面板，当触敏表面检测到在其上或附近的触摸操作后，传送给处理器51以确定触摸事件的类型，随后处理器51根据触摸事件的类型在显示面板上提供相应的视觉输出。虽然在图4中，触敏表面与显示面板是作为两个独立的部件来实现输入和输入功能，但是在某些实施例中，可以将触敏表面与显示面板集成而实现输入和输出功能。
尽管未示出，服务器还可以包括摄像头、蓝牙模块等，在此不再赘述。具 体在本实施例中，服务器中的处理器51会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器52中，并由处理器51来运行存储在存储器52中的应用程序，从而实现各种功能，如下：
获取需要向用户投放的待投放推广信息集合；
根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度；
根据该投放推荐度从该待投放推广信息集合中确定目标推广信息；
向该用户对应的用户设备投放该目标推广信息。
以上各操作的实现方法具体可参见上述实施例，此处不再赘述。
由上述可知，本实施例提供的服务器，可以通过获取需要向用户投放的待投放推广信息集合，并根据该待投放推广信息集合中的待投放推广信息获取该用户对应的投放推荐度，之后，根据该投放推荐度从该待投放推广信息集合中确定目标推广信息，并向该用户投放该目标推广信息，能综合考虑用户的点击意愿和好友互动影响等因素来选择广告向用户投放，投放精准度高。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)、磁盘或光盘等。
以上对本申请实施例所提供的一种推广信息的投放方法、装置和系统进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (14)

  1. 一种推广信息的投放方法，其特征在于，包括：
    投放服务器获取需要向用户投放的待投放推广信息集合；
    投放服务器根据所述待投放推广信息集合中的待投放推广信息获取所述用户对应的投放推荐度；
    投放服务器根据所述投放推荐度从所述待投放推广信息集合中确定目标推广信息；以及
    投放服务器向所述用户对应的用户设备投放所述目标推广信息。
  2. 根据权利要求1所述的推广信息的投放方法，其特征在于，所述投放服务器根据所述待投放推广信息集合中的待投放推广信息获取所述用户对应的投放推荐度的步骤具体包括：
    投放服务器获取所述用户的用户行为数据和好友行为数据；
    投放服务器确定所述待投放推广信息集合中的待投放推广信息所属的预设类别；
    投放服务器根据所述预设类别、用户行为数据和好友行为数据确定所述用户针对所述待投放推广信息的个人参与度、社会影响度和受好友影响度，其中，个人参与度为用户对待该投放推广信息进行点击操作的概率，社会影响度为用户与推广信息进行互动后，该互动操作对用户好友本身，以及用户好友对其好友的影响程度，受好友影响度为用户好友对推广信息的互动操作对该用户的影响程度；以及
    投放服务器根据所述个人参与度、社会影响度和受好友影响度计算向所述用户投放所述待投放推广信息的投放推荐度。
  3. 根据权利要求2所述的推广信息的投放方法，其特征在于，投放服务器所述根据所述预设类别、用户行为数据和好友行为数据确定所述用户针对所述待投放推广信息的个人参与度、社会影响度和受好友影响度的步骤具体包括：
    投放服务器根据所述好友行为数据和用户行为数据确定已与所述待投放推广信息互动的好友对所述用户产生的影响力，得到受好友影响度；
    投放服务器根据所述用户行为数据和预设类别预测所述用户对所述待投放推广信息的兴趣度，得到个人参与度；以及
    投放服务器根据所述好友行为数据、用户行为数据和预设类别预测所述用户对社会产生的影响力，得到社会影响度。
  4. 根据权利要求3所述的推广信息的投放方法，其特征在于，投放服务器所述根据所述好友行为数据、用户行为数据和预设类别预测所述用户对社会的影响力，得到社会影响度的步骤具体包括：
    投放服务器获取用户好友的其他好友行为数据；
    投放服务器从所述用户行为数据中获取所述用户与属于所述预设类别的所有已投放推广信息互动的互动数据，并统计对应的互动率；
    投放服务器根据所述互动数据和所述好友行为数据统计所述用户与所述已投放推广信息互动后，所述用户好友点击所述已投放推广信息的第一点击率；
    投放服务器根据所述好友行为数据和其他好友行为数据统计所述用户好友与所述已投放推广信息互动后，所述用户好友的好友点击所述已投放推广信息的第二点击率；以及
    投放服务器根据所述互动率、第一点击率和第二点击率按照预置算法计算，以预测所述用户针对所述待投放推广信息对社会的社会影响度。
  5. 根据权利要求3所述的推广信息的投放方法，其特征在于，投放服务器所述根据所述好友行为数据和用户行为数据确定已与所述待投放推广信息互动的好友对所述用户产生的影响力，得到受好友影响度的步骤具体包括：
    投放服务器根据所述好友行为数据确定已与所述待投放推广信息互动的第一好友，并从所述好友行为数据中获取所述第一好友的好友行为子数据；以及
    投放服务器根据所述用户行为数据和所述好友行为子数据统计所述用户与所述第一好友的亲密度，并将所述亲密度确定为所述用户的受好友影响度。
  6. 根据权利要求1-5中任意一项所述的推广信息的投放方法，其特征在于， 所述投放服务器根据所述投放推荐度从所述待投放推广信息集合中确定目标推广信息的步骤具体包括：
    投放服务器根据所述投放推荐度将所述待投放推广信息集合中的待投放推广信息按顺序排列，并生成相应的资源列表；以及
    投放服务器选取所述资源列表中前预设位数对应的所述待投放推广信息作为目标推广信息。
  7. 一种推广信息的投放装置，其特征在于，包括：
    第一获取模块，用于获取需要向用户投放的待投放推广信息集合；
    第二获取模块，用于根据所述待投放推广信息集合中的待投放推广信息获取所述用户对应的投放推荐度；
    确定模块，用于根据所述投放推荐度从所述待投放推广信息集合中确定目标推广信息；以及
    投放模块，用于向所述用户对应的用户设备投放所述目标推广信息。
  8. 根据权利要求7所述的推广信息的投放装置，其特征在于，所述第二获取模块具体包括：
    获取子模块，用于获取所述用户的用户行为数据和好友行为数据；
    第一确定子模块，用于确定所述待投放推广信息集合中的待投放推广信息所属的预设类别；
    第二确定子模块，用于根据所述预设类别、用户行为数据和好友行为数据确定所述用户针对所述待投放推广信息的个人参与度、社会影响度和受好友影响度，其中，个人参与度为用户对待该投放推广信息进行点击操作的概率，社会影响度为用户与推广信息进行互动后，该互动操作对用户好友本身，以及用户好友对其好友的影响程度，受好友影响度为用户好友对推广信息的互动操作对该用户的影响程度；以及
    计算子模块，用于根据所述个人参与度、社会影响度和受好友影响度计算向所述用户投放所述待投放推广信息的投放推荐度。
  9. 根据权利要求8所述的推广信息的投放装置，其特征在于，所述第二确 定子模块具体包括：
    确定单元，用于根据所述好友行为数据和用户行为数据确定已与所述待投放推广信息互动的好友对所述用户产生的影响力，得到受好友影响度；
    第一预测单元，用于根据所述用户行为数据和预设类别预测所述用户对所述待投放推广信息的兴趣度，得到个人参与度；以及
    第二预测单元，用于根据所述好友行为数据、用户行为数据和预设类别预测所述用户对社会产生的影响力，得到社会影响度。
  10. 根据权利要求9所述的推广信息的投放装置，其特征在于，所述第二预测单元具体用于：
    获取用户好友的其他好友行为数据；
    从所述用户行为数据中获取所述用户与属于所述预设类别的所有已投放推广信息互动的互动数据，并统计对应的互动率；
    根据所述互动数据和所述好友行为数据统计所述用户与所述已投放推广信息互动后，所述用户好友点击所述已投放推广信息的第一点击率；
    根据所述好友行为数据和其他好友行为数据统计所述用户好友与所述已投放推广信息互动后，所述用户好友的好友点击所述已投放推广信息的第二点击率；以及
    根据所述互动率、第一点击率和第二点击率按照预置算法计算，以预测所述用户针对所述待投放推广信息对社会的社会影响度。
  11. 根据权利要求8所述的推广信息的投放装置，其特征在于，所述确定单元具体用于：
    根据所述好友行为数据确定已与所述待投放推广信息互动的第一好友，并从所述好友行为数据中获取所述第一好友的好友行为子数据；以及
    根据所述用户行为数据和所述好友行为子数据统计所述用户与所述第一好友的亲密度，并将所述亲密度确定为所述用户的受好友影响度。
  12. 根据权利要求7-11中任意一项所述的推广信息的投放装置，其特征在于，所述确定模块具体用于：
    根据所述投放推荐度将所述待投放推广信息集合中的待投放推广信息按顺序排列，并生成相应的资源列表；以及
    选取所述资源列表中前预设位数对应的所述待投放推广信息作为目标推广信息。
  13. 一种推广信息的投放系统，其特征在于，包括权利要求7至12中任意一项所述的推广信息的投放装置。
  14. 一种非易失性存储介质，用于存储一个或多个计算机程序，其中，所述计算机程序包括具有一个或多个存储器的处理器可运行的指令，所述指令被计算机执行时，使得所述计算机执行以下操作：
    获取需要向用户投放的待投放推广信息集合；
    根据所述待投放推广信息集合中的待投放推广信息获取所述用户对应的投放推荐度；
    根据所述投放推荐度从所述待投放推广信息集合中确定目标推广信息；以及
    向所述用户对应的用户设备投放所述目标推广信息。
PCT/CN2017/084861 2016-05-25 2017-05-18 一种推广信息的投放方法、装置、系统及存储介质 Ceased WO2017202238A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP17802084.8A EP3467752A4 (en) 2016-05-25 2017-05-18 METHOD, APPARATUS AND SYSTEM FOR DISTRIBUTING PROMOTION INFORMATION, AND STORAGE MEDIUM
US16/197,067 US11501327B2 (en) 2016-05-25 2018-11-20 Method, apparatus, and system for delivering promotion information, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610352701.0A CN107437189B (zh) 2016-05-25 2016-05-25 一种推广信息的投放方法、装置及系统
CN201610352701.0 2016-05-25

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/197,067 Continuation US11501327B2 (en) 2016-05-25 2018-11-20 Method, apparatus, and system for delivering promotion information, and storage medium

Publications (1)

Publication Number Publication Date
WO2017202238A1 true WO2017202238A1 (zh) 2017-11-30

Family

ID=60412132

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/084861 Ceased WO2017202238A1 (zh) 2016-05-25 2017-05-18 一种推广信息的投放方法、装置、系统及存储介质

Country Status (4)

Country Link
US (1) US11501327B2 (zh)
EP (1) EP3467752A4 (zh)
CN (1) CN107437189B (zh)
WO (1) WO2017202238A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109242575A (zh) * 2018-09-27 2019-01-18 武汉聚鸿传媒文化有限公司 一种基于区块链的广告投放系统

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11238518B2 (en) * 2017-12-14 2022-02-01 Wells Fargo Bank, N.A. Customized predictive financial advisory for a customer
CN108596647B (zh) * 2018-03-16 2021-12-17 北京奇艺世纪科技有限公司 一种广告投放方法、装置及电子设备
CN109067897B (zh) * 2018-08-24 2021-11-09 优视科技新加坡有限公司 消息推送方法及其装置、设备/终端/服务器、计算机可读介质
CN109379330A (zh) * 2018-09-07 2019-02-22 阿里巴巴集团控股有限公司 内容投放的实现方法和装置
CN109919656A (zh) * 2019-01-23 2019-06-21 平安科技（深圳）有限公司 广告投放方法、装置、计算机设备及存储介质
CN111798280B (zh) * 2020-09-08 2020-12-15 腾讯科技（深圳）有限公司 多媒体信息推荐方法、装置和设备及存储介质
CN113378040A (zh) * 2021-05-24 2021-09-10 山东浪潮爱购云链信息科技有限公司 一种用于推广的用户行为分析方法及设备
CN113505308B (zh) * 2021-09-09 2022-02-18 北京轻松筹信息技术有限公司 一种用户年龄的预测方法及装置、可读存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008032297A2 (en) * 2006-09-11 2008-03-20 Alcatel Lucent Targeted electronic content delivery control systems and methods
CN102592235A (zh) * 2011-12-28 2012-07-18 北京品友互动信息技术有限公司 一种互联网广告投放系统
CN104967679A (zh) * 2015-06-09 2015-10-07 深圳市腾讯计算机系统有限公司 信息推荐系统、方法及装置
CN105512916A (zh) * 2015-12-18 2016-04-20 北京讯达网脉科技有限公司 广告精准投放方法和系统

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8170912B2 (en) * 2003-11-25 2012-05-01 Carhamm Ltd., Llc Database structure and front end
US10373173B2 (en) * 2004-06-14 2019-08-06 Facebook, Inc. Online content delivery based on information from social networks
US20060242663A1 (en) * 2005-04-22 2006-10-26 Inclue, Inc. In-email rss feed delivery system, method, and computer program product
US20080103907A1 (en) * 2006-10-25 2008-05-01 Pudding Ltd. Apparatus and computer code for providing social-network dependent information retrieval services
US20080177635A1 (en) * 2007-01-23 2008-07-24 David Brian Handel Method, system, and apparatus for suggesting or requesting a proxy transaction
US20080281687A1 (en) * 2007-05-08 2008-11-13 Motorola, Inc. Method for determining user interest in products and services for targeted advertising
US8499247B2 (en) * 2008-02-26 2013-07-30 Livingsocial, Inc. Ranking interactions between users on the internet
US20100076850A1 (en) * 2008-09-22 2010-03-25 Rajesh Parekh Targeting Ads by Effectively Combining Behavioral Targeting and Social Networking
US8478697B2 (en) * 2010-09-15 2013-07-02 Yahoo! Inc. Determining whether to provide an advertisement to a user of a social network
US20120166285A1 (en) * 2010-12-28 2012-06-28 Scott Shapiro Defining and Verifying the Accuracy of Explicit Target Clusters in a Social Networking System
US8954503B2 (en) * 2011-03-03 2015-02-10 Facebook, Inc. Identify experts and influencers in a social network
US9846916B2 (en) * 2011-07-10 2017-12-19 Facebook, Inc. Clustering a user's connections in a social networking system
US9262791B2 (en) * 2012-03-23 2016-02-16 Facebook, Inc. Targeting stories based on influencer scores
CN103514215A (zh) * 2012-06-28 2014-01-15 北京奇虎科技有限公司 生成用户社交影响力信息的方法及装置
US20140006195A1 (en) * 2012-06-28 2014-01-02 Naomi Wilson Checkout system and method
US20140358668A1 (en) * 2012-07-25 2014-12-04 Google Inc. System and method for integrating supplemental content within a webpage
US20140081720A1 (en) * 2012-09-19 2014-03-20 Mastercard International Incorporated Method and system for processing coupons in a near field transaction
US9235865B1 (en) * 2012-10-26 2016-01-12 Sprint Communications Company L.P. Identifying influencers using social information
US9015128B2 (en) * 2012-11-28 2015-04-21 Sharethis, Inc. Method and system for measuring social influence and receptivity of users
CN104052714B (zh) * 2013-03-12 2019-02-26 腾讯科技（深圳）有限公司 多媒体信息的推送方法及服务器
CN104063476A (zh) * 2014-06-30 2014-09-24 北京奇虎科技有限公司 基于社交网络的内容推荐方法和系统
US20160055164A1 (en) * 2014-08-25 2016-02-25 Tll, Llc News alert system and method
US20160364492A1 (en) * 2015-06-12 2016-12-15 Duby, LLC Systems and methods for a viral social network
US20170277691A1 (en) * 2016-03-22 2017-09-28 Facebook, Inc. Quantifying Social Influence

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008032297A2 (en) * 2006-09-11 2008-03-20 Alcatel Lucent Targeted electronic content delivery control systems and methods
CN102592235A (zh) * 2011-12-28 2012-07-18 北京品友互动信息技术有限公司 一种互联网广告投放系统
CN104967679A (zh) * 2015-06-09 2015-10-07 深圳市腾讯计算机系统有限公司 信息推荐系统、方法及装置
CN105512916A (zh) * 2015-12-18 2016-04-20 北京讯达网脉科技有限公司 广告精准投放方法和系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3467752A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109242575A (zh) * 2018-09-27 2019-01-18 武汉聚鸿传媒文化有限公司 一种基于区块链的广告投放系统

Also Published As

Publication number Publication date
EP3467752A4 (en) 2019-11-13
US20190087846A1 (en) 2019-03-21
EP3467752A1 (en) 2019-04-10
CN107437189A (zh) 2017-12-05
CN107437189B (zh) 2021-01-08
US11501327B2 (en) 2022-11-15

Similar Documents

Publication Publication Date Title
WO2017202238A1 (zh) 一种推广信息的投放方法、装置、系统及存储介质
US20220398277A1 (en) Method for recommending works and server
US11270343B2 (en) Method and apparatus for generating targeted label, and storage medium
CN108280115B (zh) 识别用户关系的方法及装置
US10454889B2 (en) Automatic anomaly detection framework for grid resources
US10133789B2 (en) Real-time trend detection in a social network
CN108197224B (zh) 用户群分类方法、存储介质以及终端
US10462217B2 (en) Pivot interface element for a messaging system
CN106302094B (zh) 消息推送方法及装置
US11157942B2 (en) Dynamic information presentation system, method, and apparatus, and terminal
TW201833845A (zh) 資訊獲取方法、提供方法、裝置及系統、儲存介質
WO2016197758A1 (zh) 信息推荐系统、方法及装置
CN108334887A (zh) 一种用户选取方法和装置
WO2016110182A1 (zh) 匹配表情图像的方法、装置及终端
WO2014169661A1 (en) Method and system for processing report information
WO2017190706A1 (zh) 一种信息推送方法、装置及系统、计算机存储介质
WO2016015471A1 (zh) 一种预测用户离网的方法及装置
US20170344610A1 (en) Methods and Systems for Assigning Affinity Scores to Contacts
US9367624B2 (en) Identity workflow that utilizes multiple storage engines to support various lifecycles
CN114430504B (zh) 一种媒体内容的推荐方法以及相关装置
CN111666485B (zh) 一种信息推荐方法、装置及终端
CN108966340B (zh) 一种设备定位方法及装置
CN106294087B (zh) 一种对业务执行操作的操作频率的统计方法及装置
CN112862289B (zh) 一种临床研究从业者的信息匹配方法和装置
CN106131296A (zh) 信息展示方法及装置

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17802084

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017802084

Country of ref document: EP

Effective date: 20190102