WO2018161677A1 - Procédé de poussée de message, appareil et support de stockage - Google Patents

Procédé de poussée de message, appareil et support de stockage Download PDF

Info

Publication number
WO2018161677A1
WO2018161677A1 PCT/CN2017/116877 CN2017116877W WO2018161677A1 WO 2018161677 A1 WO2018161677 A1 WO 2018161677A1 CN 2017116877 W CN2017116877 W CN 2017116877W WO 2018161677 A1 WO2018161677 A1 WO 2018161677A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
message
pushed
library
identity tag
Prior art date
Application number
PCT/CN2017/116877
Other languages
English (en)
Chinese (zh)
Inventor
潘岸腾
Original Assignee
广州优视网络科技有限公司
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 广州优视网络科技有限公司 filed Critical 广州优视网络科技有限公司
Publication of WO2018161677A1 publication Critical patent/WO2018161677A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Definitions

  • the present invention relates to the field of information processing technologies, and in particular, to a method, an apparatus, and a storage medium for pushing a message.
  • the manner of pushing the message to the user may also be used.
  • the user is interested in the content of the message, there is a willingness to download the corresponding third-party application.
  • the present invention is directed to a method, apparatus, and storage medium for pushing messages to improve the above problems.
  • a first embodiment of the present invention provides a method for pushing a message, including:
  • the corresponding preset number of messages are selected and sent to the corresponding user according to the matching degree from the largest to the smallest, or the preset number of messages are randomly selected and pushed to the corresponding user based on the matching degree greater than the preset threshold.
  • the user in the pre-established user library is a user to be pushed, and each user information recorded in the user library includes one or more identity tags, where the identity tags are used to indicate user characteristics, including But not limited to: gender, interest, hobbies, age, geography, education, majors, skills.
  • the number of times the message in the preset message library is pushed to the corresponding user in the user library and the user who receives the message are counted based on the identity tag of the user in the pre-established user library.
  • the message in the preset message library is randomly pushed to some or all of the users in the user library that have not received the message based on the identity tag of the user in the pre-established user library. user.
  • the second embodiment of the present invention further provides an apparatus for pushing a message, including:
  • a memory having stored thereon a computer program executable on the processor, the following steps being implemented when the processor executes the computer program:
  • the method further includes: selecting a corresponding preset number of messages to be sent to the corresponding user according to the matching degree from the largest to the smallest, or for, based on being greater than a preset threshold, Matching degree, randomly selecting a preset number of messages to push to the corresponding user.
  • the processor when executing the computer program, further implements: pre-establishing a user library for a user to be pushed, and each user information recorded in the user library includes one or more identity tags.
  • the identity tag is used to indicate the characteristics of the user, including but not limited to: gender, interests, hobbies, age groups, geography, education, majors, and skills.
  • the program in the preset message library is randomly pushed to the user library according to the identity tag of the user in the pre-established user library, and is not received. Some or all of the users who have passed the message.
  • the processor calculates the contribution by using the following method:
  • ms i,t represents the contribution of the message i pushed to the user having the identity tag t to the click rate mc i,t of the user clicking on the message i;
  • Mc i,t represents the click rate, which is the ratio of the number of users who clicked on the message i to all users who pushed the message i to the user with the identity tag t and the number of all users who pushed the message i to the user with the identity tag t ;
  • Mp i,t represents the number of times the message i was pushed to all users having the identity tag t;
  • M represents the number of messages in the preset message library
  • T represents the number of different identity tags recorded in the user library.
  • the processor calculates the matching degree by using the following method:
  • Um u,i indicates whether the user u has received the message i, where um u,i is 1 indicates that it has been received, and um u,i is 0 indicates that it has not been received;
  • Ut u,t indicates whether the identity tag t is included in one or more identity tags of the user u, where ut u, t is 1 to include the identity tag t, ut u, and t is 0 to indicate that it is not included;
  • Ms i,t represents the contribution of the message i pushed to the user with the identity tag t to the click rate of the user clicking on the message i;
  • T represents the number of different identity tags recorded in the user library.
  • An embodiment of the present invention further provides a computer readable storage medium having stored thereon a computer program, the step of implementing the method for pushing a message when executed by a processor.
  • the method, device and storage medium for pushing a message according to the present invention it is possible to automatically push different messages to different users, that is, to push messages conforming to their needs according to the interests, hobbies, features, etc. of the user, thereby realizing automatic personalized push messages.
  • the effect is that the content of manually edited messages seen by different users is the same.
  • Figure 1 is a screenshot of an example of an existing message push
  • FIG. 2 is a flowchart of a method of pushing a message according to a first embodiment of the present invention
  • FIG. 3 is a flow chart of a method of pushing a message according to a second embodiment of the present invention.
  • FIG. 4 is a schematic block diagram of an apparatus for pushing a message according to a third embodiment of the present invention.
  • FIG. 5 is a schematic block diagram of an apparatus for pushing a message according to a fourth embodiment of the present invention.
  • FIG. 2 is a flow chart of a method of pushing a message according to a first embodiment of the present invention. As shown in FIG. 2, the method of pushing a message according to the first embodiment of the present invention includes steps S1 to S4.
  • a user library needs to be established in advance, and the user information of the plurality of messages to be pushed is saved in the user library, and the saved number of users and user information can be updated periodically.
  • the user in the pre-established user library is a user to be pushed by the message, and each user information recorded in the user library includes one or more identity tags, and the identity tag is used to indicate the characteristics of the user, including but not Limited to: gender, interests, hobbies, age groups, geography, education, majors, skills.
  • User information can be collected by the user when registering a third-party application, or can be collected by other means, such as obtaining user information through questionnaires. When collecting user information, the more comprehensive and detailed the information is, the better.
  • the identity tag is used to represent the characteristics of the user to lay the groundwork for subsequent personalized push messages, including but not limited to: gender, interests, hobbies, age groups, geography, education, majors, skills, and the like.
  • other identification tags that indicate the characteristics of the user are all applicable to the method of pushing messages provided by the present invention.
  • the user information may further include: a user identifier (ID) for identifying different users; a message push result for recording a message identifier (ID) of the message that has been pushed to the user, the message identifier being used for Differentiate between different information.
  • ID user identifier
  • ID message push result
  • message identification of the user information record it is possible to know which messages are pushed to the user.
  • a message push statistics list may be established, where the message push statistics list is used to collect statistics of a message pushed within a period of time, and the message push statistics list may include, but is not limited to, a message identifier (ID). , identity tag, number of pushes, click rate of the message, user ID (ID), etc.
  • the message identifier (ID) is used to distinguish information of different content.
  • the number of pushes is used to record the number of times a message has been pushed to multiple users with a certain identity tag.
  • the same message will only be received once by the same user, that is, the same message will only be pushed once to the same user. Once a message has been pushed to a user, the message will no longer be pushed to the user.
  • a user A has two identity tags a and b.
  • the user A with the identity tags a and b will only receive
  • the user ID (ID) can be recorded in the statistics list to identify which users are pushed to a message.
  • the push to the user who has received the message is prohibited.
  • a push message and a user correspondence table may be separately established to record which users are sent to a message.
  • the click rate is based on the identity tag statistics, and the ratio of the number of users who clicked on the message to the number of all users having the identity tag among all users who have pushed a message to a user having an identity tag.
  • mc i,t represents the click rate, and among all users who have pushed the message i to the user having the identity tag t, the number of users who clicked on the message i and the number of all users who sent the message i to the user having the identity tag t Ratio
  • U i,t,d represents the number of users who have clicked on the message i among all users who have pushed the message i to the user having the identity tag t;
  • U i,t,n represents the number of all users who have pushed message i to the user with identity tag t.
  • the message push statistics list can be, for example, as follows:
  • the message 1 is pushed 1000 times to the user having the identity tag a in the user library, and the click rate of the user who receives the message 1 clicking the message 1 is 0.01; the message 1 is provided to the user library.
  • the user of the identity tag b pushes 2000 times, the click rate of the user who receives the message 1 clicks the message 1 is 0.05; the message 2 is pushed 500 times to the user with the identity tag c in the user library, and the message 2 is received.
  • the click rate of the user clicking on the message 2 is 0.01.
  • the number of times the message in the preset message library is pushed to the corresponding user in the user library and the user who receives the message are counted. Click on the clickthrough rate of the message instead of based on user stats.
  • the corresponding user can be found through the identity tag.
  • a push message and user correspondence table can also be established.
  • the following method can be used to calculate the contribution of the pushed message to the click rate:
  • ms i,t represents the contribution of the message i pushed to the user having the identity tag t to the click rate mc i,t of the user clicking on the message i;
  • Mc i,t represents the click rate, of all the users who have pushed the message i to the user with the identity tag t, the number of users who clicked on the message i and the number of all users who pushed the message i to the user with the identity tag t ratio;
  • Mp i,t represents the number of times the message i was pushed to all users having the identity tag t;
  • M represents the number of messages in the preset message library
  • T represents the number of different identity tags recorded in the user library.
  • S3 Determine the degree of matching between the user and the message based on the contribution.
  • Um u,i indicates whether the user u has received the message i, where um u,i is 1 indicates that it has been received, and um u,i is 0 indicates that it has not been received;
  • Ut u,t indicates whether the identity tag t is included in one or more identity tags of the user u, where ut u, t is 1 to include the identity tag t, ut u, and t is 0 to indicate that it is not included;
  • Ms i,t represents the contribution of the message i pushed to the user with the identity tag t to the click rate of the user clicking on the message i;
  • T represents the number of different identity tags recorded in the user library.
  • the function of the formula is to calculate the degree of matching between a user u and a message i that it has not received. If the user u has received the message i, the matching degree is recorded as 0 because it is not necessary to repeatedly push the second message i to it.
  • the purpose of (1-um u,i ) is to remove the user of the received message i, that is, the user and message that has received the message i.
  • the degree of matching between i is recorded as 0.
  • S4 Select a preset number of messages to be pushed to the corresponding user according to the matching degree according to a preset manner.
  • the preset number of messages may be selected and pushed to the corresponding user according to the matching degree value according to a preset manner.
  • a preset number of messages may be randomly selected and pushed to the corresponding user based on the matching degree greater than the preset threshold.
  • a threshold may be set in advance, and a preset number of messages are randomly selected from messages corresponding to the matching degree greater than or equal to the preset threshold. Push to the user, you can select 3-5 messages; or select a message corresponding to the maximum matching degree to push to the user. It is assumed that the maximum matching degree corresponds to multiple messages, and the multiple messages may be pushed to the user, or one or several messages may be randomly selected and pushed to the user.
  • the message preset in the message library can be randomly pushed to a part of the user in the user library, for example, can be randomly pushed to the user library. Some or all of the users who have not received the message. That is, based on counting the number of times the message in the preset message library is pushed to the corresponding user in the user library and the user receiving the message clicking the click rate of the message, based on the identity tag of the user in the pre-established user library.
  • the attribute randomly pushes the message in the preset message library to a part of the user's library with the identity tag, and can randomly push some or all of the users in the user library that have the identity tag but have not received the message. user.
  • identity tags such as identity tags a and b
  • the user who has the corresponding two or more different identity tags is After receiving the message for the first time, the message will not be received repeatedly.
  • the rule that the same message is only pushed to the same user is required. The advantage of this is that you can get click-through rate data for different messages for users with different identity tags.
  • the content recorded in the user information of the user library is updated as follows:
  • the message push result contained in the user information is updated.
  • the message push statistics list in the preset message library is updated as follows:
  • the message push statistics list is updated.
  • the push message and the user correspondence table are updated as follows:
  • FIG. 3 is a flow chart of a method of pushing a message according to a second embodiment of the present invention. As shown in FIG. 3, the method described in the second embodiment differs from the method described in the first embodiment only in that the preset mode is further defined in step S4, and the other steps S1-S3 and the corresponding embodiment are described. The technical solutions are exactly the same.
  • the method for pushing a message according to the second embodiment of the present invention includes the step S4 as follows:
  • S4 Select a corresponding preset number of messages to be sent to the corresponding user according to the matching degree from large to small.
  • the selection is ranked in the descending order of the matching degree.
  • a plurality of messages corresponding to the plurality of matching degrees are pushed to the user, for example, 3-5 messages may be selected; or a message corresponding to the maximum matching degree is selected and pushed to the user. If the maximum matching degree corresponds to multiple messages, the multiple messages may be pushed to the user, or one or several messages may be randomly selected and pushed to the user. It can be seen that the selection condition of the push message described in the second embodiment is that one or more messages with the greatest matching degree with the user are selected and pushed to the user.
  • FIG. 4 is a schematic block diagram of an apparatus for pushing a message according to a third embodiment of the present invention. As shown in FIG. 4, the apparatus for pushing a message according to the third embodiment of the present invention includes:
  • a statistical unit configured to count, according to the identity tag of the user in the pre-established user library, the number of times the message in the preset message library is pushed to the corresponding user in the user library, and the user who receives the message clicks the message Click rate
  • a contribution determining unit configured to determine a contribution degree of the pushed message to the click rate based on a number of times of the statistical message push and the click rate
  • a matching degree determining unit configured to determine a degree of matching between the user and the message based on the contribution degree
  • the pushing unit is configured to select a preset number of messages to be pushed to the corresponding user according to the matching degree in a preset manner.
  • the identity tag is used to indicate characteristics of the user, including but not limited to: gender, interests, hobbies, age groups, regions, education, majors, and skills.
  • the contribution determining unit is configured to calculate the contribution degree by using the following method:
  • ms i,t represents the contribution of the message i pushed to the user having the identity tag t to the click rate mc i,t of the user clicking on the message i;
  • Mc i,t represents the click rate, which is the ratio of the number of users who clicked on the message i to all users who pushed the message i to the user with the identity tag t and the number of all users who pushed the message i to the user with the identity tag t ;
  • Mp i,t represents the number of times the message i was pushed to all users having the identity tag t;
  • M represents the number of messages in the preset message library
  • T represents the number of different identity tags recorded in the user library.
  • the matching degree determining unit is configured to calculate the matching degree by using the following method:
  • Um u,i indicates whether user u has received message i, where um u,i is 1 means received, um u,i is 0 means no reception;
  • Ut u,t indicates whether the identity tag t is included in one or more identity tags of the user u, where ut u, t is 1 to include the identity tag t, ut u, and t is 0 to indicate that it is not included;
  • Ms i,t represents the contribution of the message i pushed to the user with the identity tag t to the click rate of the user clicking on the message i;
  • T represents the number of different identity tags recorded in the user library.
  • the push unit is further configured to: according to the matching degree, select a corresponding preset number of messages to be sent to the corresponding user according to the matching degree. Or, based on the matching degree greater than the preset threshold, the preset number of messages are randomly selected and pushed to the corresponding user, for example, 3-5 messages are selected; or a message corresponding to the maximum matching degree is selected and pushed to the user. This is the same as the specific process described in the first embodiment and the second embodiment, and the detailed description thereof will not be repeated.
  • FIG. 5 is a schematic block diagram of an apparatus for pushing a message according to a fourth embodiment of the present invention. As shown in FIG. 5, the apparatus for pushing a message further includes:
  • a user library establishing unit configured to pre-establish a user library for a user to be pushed by the message, where each user information recorded in the user library includes one or more identity tags; the identity tag is used to represent the characteristics of the user, including Not limited to: gender, interest, hobbies, age, geography, education, majors, skills.
  • the device for pushing a message may further include a pre-push message unit, configured to pre-push the message in the preset message library to the user library in advance based on the identity tag of the user in the pre-established user library before the statistic unit works.
  • a pre-push message unit configured to pre-push the message in the preset message library to the user library in advance based on the identity tag of the user in the pre-established user library before the statistic unit works.
  • the device for pushing a message it is possible to automatically push different messages to different users, that is, to push messages conforming to their needs according to the interests, hobbies, features, and the like of the user, thereby realizing the effect of automatically and personalizedly pushing the messages.
  • the computer program product of the method for pushing a message provided by the embodiment of the present invention includes a computer readable storage medium storing program code, and the program code includes instructions for executing the method described in the foregoing method embodiment, and implementing the method. Refer to the method embodiment, and details are not described herein again.
  • the functions may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a standalone product.
  • the technical solution of the present invention which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
  • the instructions are used to cause a computer device (which may be a personal computer, tablet, smartphone, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a removable hard disk, a read only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
  • An embodiment of the present invention further provides an apparatus for pushing a message, including:
  • a memory having stored thereon a computer program executable on the processor, the following steps being implemented when the processor executes the computer program:
  • the processor can also implement when executing the computer program:
  • the user information recorded in the user library includes one or more identity tags; the identity tag is used to indicate the characteristics of the user, including but not limited to: gender, interest, Hobbies, age, geography, education, majors, skills.
  • the processor calculates the contribution using the following method:
  • ms i,t represents the contribution of the message i pushed to the user having the identity tag t to the click rate mc i,t of the user clicking on the message i;
  • Mc i,t represents the click rate, which is the ratio of the number of users who clicked on the message i to all users who pushed the message i to the user with the identity tag t and the number of all users who pushed the message i to the user with the identity tag t ;
  • Mp i,t represents the number of times the message i was pushed to all users having the identity tag t;
  • M represents the number of messages in the preset message library
  • T represents the number of different identity tags recorded in the user library.
  • the processor calculates the matching degree using the following method:
  • Um u,i indicates whether the user u has received the message i, where um u,i is 1 indicates that it has been received, and um u,i is 0 indicates that it has not been received;
  • Ut u,t indicates whether the identity tag t is included in one or more identity tags of the user u, where ut u, t is 1 to include the identity tag t, ut u, and t is 0 to indicate that it is not included;
  • Ms i,t represents the contribution of the message i pushed to the user with the identity tag t to the click rate of the user clicking on the message i;
  • T represents the number of different identity tags recorded in the user library.
  • the processor can also implement when executing the computer program:
  • the message in the preset message library is preliminarily pushed to some or all of the users in the user library who have not received the message based on the identity tag of the user in the pre-established user library.
  • the processor can also implement when executing the computer program:
  • An embodiment of the present invention further provides a computer readable storage medium having stored thereon a computer program, the step of implementing the method for pushing a message when executed by a processor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

L'invention concerne un procédé, un appareil et un support de stockage de poussée de message, le procédé consistant : sur la base des étiquettes d'identification d'utilisateurs dans une base de données d'utilisateur préétablie, à calculer le nombre de fois qu'un message dans une base de données de messages préétablie est poussé vers des utilisateurs correspondants dans la base de données d'utilisateurs et le taux de clics publicitaires sur le message des utilisateurs recevant le message (S1) ; sur la base du nombre calculé de temps de poussée de message et du taux de clics publicitaires, à déterminer la contribution du message poussé au taux de clics publicitaires (S2) ; sur la base de la contribution, à déterminer le degré de correspondance entre les utilisateurs et le message (S3) ; sur la base du degré de correspondance et selon un procédé préétabli, à sélectionner un nombre préétabli correspondant de messages à pousser vers des utilisateurs correspondants (S4).
PCT/CN2017/116877 2017-03-07 2017-12-18 Procédé de poussée de message, appareil et support de stockage WO2018161677A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2017101308475 2017-03-07
CN201710130847.5A CN106919692B (zh) 2017-03-07 2017-03-07 一种推送消息的方法和装置

Publications (1)

Publication Number Publication Date
WO2018161677A1 true WO2018161677A1 (fr) 2018-09-13

Family

ID=59460243

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/116877 WO2018161677A1 (fr) 2017-03-07 2017-12-18 Procédé de poussée de message, appareil et support de stockage

Country Status (2)

Country Link
CN (1) CN106919692B (fr)
WO (1) WO2018161677A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106919692B (zh) * 2017-03-07 2021-02-19 阿里巴巴（中国）有限公司 一种推送消息的方法和装置
CN107222566B (zh) * 2017-07-06 2020-09-04 阿里巴巴（中国）有限公司 信息推送方法、装置及服务器
CN110347915A (zh) * 2019-06-10 2019-10-18 贝壳技术有限公司 一种信息推送方法和装置
CN111460294B (zh) * 2020-03-31 2023-09-15 汉海信息技术(上海)有限公司 消息推送方法、装置、计算机设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130151539A1 (en) * 2011-12-07 2013-06-13 Yanxin Shi Real-Time Online-Learning Object Recommendation Engine
CN104579912A (zh) * 2013-10-29 2015-04-29 深圳市腾讯计算机系统有限公司 数据推送的方法及装置
CN104735117A (zh) * 2013-12-24 2015-06-24 腾讯科技（北京）有限公司 一种信息处理方法、装置和系统
CN105208113A (zh) * 2015-08-31 2015-12-30 北京百度网讯科技有限公司 信息推送的方法和装置
CN105760400A (zh) * 2014-12-19 2016-07-13 阿里巴巴集团控股有限公司 一种基于搜索行为的推送消息排序方法及装置
CN106919692A (zh) * 2017-03-07 2017-07-04 广州优视网络科技有限公司 一种推送消息的方法和装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7984056B1 (en) * 2007-12-28 2011-07-19 Amazon Technologies, Inc. System for facilitating discovery and management of feeds
CN102810104B (zh) * 2011-06-03 2015-05-20 阿里巴巴集团控股有限公司 信息调整方法及装置
CN103870454A (zh) * 2012-12-07 2014-06-18 盛乐信息技术（上海）有限公司 数据推荐方法及系统
CN104424291B (zh) * 2013-09-02 2018-12-21 阿里巴巴集团控股有限公司 一种对搜索结果进行排序的方法及装置
CN104133837B (zh) * 2014-06-24 2017-10-31 上海交通大学 一种基于分布式计算的互联网信息投放渠道优化系统
CN105279204B (zh) * 2014-07-25 2019-04-09 阿里巴巴集团控股有限公司 信息推送方法和装置
CN104598643A (zh) * 2015-02-13 2015-05-06 成都品果科技有限公司 一种物品相似度贡献系数、相似度获取方法及物品推荐方法及其系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130151539A1 (en) * 2011-12-07 2013-06-13 Yanxin Shi Real-Time Online-Learning Object Recommendation Engine
CN104579912A (zh) * 2013-10-29 2015-04-29 深圳市腾讯计算机系统有限公司 数据推送的方法及装置
CN104735117A (zh) * 2013-12-24 2015-06-24 腾讯科技（北京）有限公司 一种信息处理方法、装置和系统
CN105760400A (zh) * 2014-12-19 2016-07-13 阿里巴巴集团控股有限公司 一种基于搜索行为的推送消息排序方法及装置
CN105208113A (zh) * 2015-08-31 2015-12-30 北京百度网讯科技有限公司 信息推送的方法和装置
CN106919692A (zh) * 2017-03-07 2017-07-04 广州优视网络科技有限公司 一种推送消息的方法和装置

Also Published As

Publication number Publication date
CN106919692B (zh) 2021-02-19
CN106919692A (zh) 2017-07-04

Similar Documents

Publication Publication Date Title
WO2018161677A1 (fr) Procédé de poussée de message, appareil et support de stockage
US9959551B1 (en) Customer-level cross-channel message planner
KR102378855B1 (ko) 소셜 미디어를 이용하는 사용자의 통계를 추정하는 방법 및 장치
US20160307131A1 (en) Method, apparatus, and system for controlling delivery task in social networking platform
US8631122B2 (en) Determining demographics based on user interaction
US9367603B2 (en) Systems and methods for behavioral segmentation of users in a social data network
US9679044B2 (en) Assigning social networking system users to households
US8909542B2 (en) Systems and methods for managing brand loyalty
WO2017211191A1 (fr) Procédé et dispositif permettant de pousser des informations
WO2017121314A1 (fr) Procédé et appareil de recommandation d'informations
CN106940705A (zh) 一种用于构建用户画像的方法与设备
EP3021264A1 (fr) Procédé de recommandation d'informations et appareil de réseau social
US20230014418A1 (en) Recommending contents using a base profile
WO2019076017A1 (fr) Procédé et appareil de traitement d'informations de rétroaction, dispositif terminal et support
US9241079B1 (en) Mobile application usage monitor
CN105868267B (zh) 一种移动社交网络用户兴趣的建模方法
WO2018149337A1 (fr) Procédé, dispositif et serveur de distribution d'informations
WO2019062021A1 (fr) Procédé de distribution sélective d'une publicité de prêt dans un programme d'application, dispositif électronique, et support
US20140156341A1 (en) Identifying potential customers using social networks
US9607340B2 (en) Method and system for implementing author profiling
TW201443812A (zh) 社群媒體影響性評估（二）
US10133878B2 (en) Stochastic privacy
Ungerman et al. Model of communication usable for small and medium-sized companies for the consumer communication in social media
CN103577505A (zh) 媒体文件的兴趣度预测方法和系统
CN105389714B (zh) 一种从行为数据识别用户特性的方法

Legal Events

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

Ref document number: 17899930

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17899930

Country of ref document: EP

Kind code of ref document: A1