WO2021196097A1 - 用户画像列表构建方法、装置、服务器以及存储介质 - Google Patents

用户画像列表构建方法、装置、服务器以及存储介质 Download PDF

Info

Publication number
WO2021196097A1
WO2021196097A1 PCT/CN2020/082842 CN2020082842W WO2021196097A1 WO 2021196097 A1 WO2021196097 A1 WO 2021196097A1 CN 2020082842 W CN2020082842 W CN 2020082842W WO 2021196097 A1 WO2021196097 A1 WO 2021196097A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
portrait
current
list
target
Prior art date
Application number
PCT/CN2020/082842
Other languages
English (en)
French (fr)
Inventor
贾欣
Original Assignee
深圳市欢太科技有限公司
Oppo广东移动通信有限公司
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 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to PCT/CN2020/082842 priority Critical patent/WO2021196097A1/zh
Priority to CN202080094726.XA priority patent/CN115004210A/zh
Publication of WO2021196097A1 publication Critical patent/WO2021196097A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising

Definitions

  • This application relates to the field of information push technology, and more specifically, to a method, device, server, and storage medium for constructing a user portrait list.
  • the server generally pushes content to the electronic device for display on the electronic device.
  • this application proposes a method, device, server and storage medium for constructing a user portrait list to solve the above-mentioned problems.
  • an embodiment of the present application provides a method for constructing a user portrait list.
  • the method includes: collecting user data of each of a plurality of users in the current construction period; The data is aggregated to obtain the user portrait of each user in the current construction period; the user portrait of each user in the current construction period is updated to the distributed storage system, wherein the distribution The storage system includes the user portrait of each user in the historical construction period; based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period , Build the user portrait list of each user.
  • an embodiment of the present application provides an apparatus for constructing a user portrait list.
  • the apparatus includes: a user data collection module for collecting user data of each of multiple users in the current construction period; users
  • the portrait acquisition module is used to aggregate the user data of each user to obtain the user portrait of each user in the current construction period;
  • the user portrait update module is used to aggregate the user data of each user in the current construction period.
  • the user portraits in the current construction period are updated to the distributed storage system, where the distributed storage system includes the user portraits of each user in the historical construction period;
  • the user portrait list construction module is used to build a user portrait list based on the The user portrait of each user in the current construction period and the user portrait of each user in the historical construction period to construct a user portrait list of each user.
  • an embodiment of the present application provides a server, including a memory and a processor, the memory is coupled to the processor, the memory stores instructions, and when the instructions are executed by the processor, the The processor executes the above method.
  • an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores program code, and the program code can be invoked by a processor to execute the above method.
  • the user portrait list construction method, device, server, and storage medium provided by the embodiments of the present application collect user data of each of multiple users in the current construction cycle, aggregate the user data of each user, and obtain each user data.
  • the user portrait of each user in the current construction cycle, and the user portrait of each user in the current construction cycle is updated to the distributed storage system.
  • the distributed storage system includes the user portrait of each user in the historical construction cycle. Based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period, construct a list of user portraits of each user, so as to collect the user data aggregation of each user in a certain construction period
  • User portraits are updated to the distributed storage system in real time to participate in the construction of user portrait lists to improve the update efficiency and accuracy of user portrait lists.
  • FIG. 1 shows a schematic diagram of an application environment that can be used in a method for constructing a user portrait list provided by an embodiment of the present application
  • FIG. 2 shows a schematic flowchart of a method for constructing a user portrait list provided by an embodiment of the present application
  • FIG. 3 shows a schematic flowchart of a method for constructing a user portrait list provided by another embodiment of the present application
  • FIG. 4 shows a schematic flowchart of an embodiment of step S250 of the method for constructing a user portrait list shown in FIG. 3 of the present application;
  • FIG. 5 shows a schematic flowchart of another embodiment of step S250 of the method for constructing a user portrait list shown in FIG. 3 of the present application;
  • FIG. 6 shows a schematic flowchart of another embodiment of step S250 of the method for constructing a user portrait list shown in FIG. 3 of the present application;
  • FIG. 7 shows a schematic flowchart of a method for constructing a user portrait list provided by still another embodiment of the present application.
  • FIG. 8 shows a schematic flowchart of a method for constructing a user portrait list provided by another embodiment of the present application.
  • FIG. 9 shows a schematic flowchart of a method for constructing a user portrait list according to another embodiment of the present application.
  • Fig. 10 shows a schematic flowchart of an embodiment of step S550 of the method for constructing a user portrait list shown in Fig. 9 of the present application;
  • FIG. 11 shows a schematic flowchart of another embodiment of step S550 of the method for constructing a user portrait list shown in FIG. 9 of the present application;
  • FIG. 12 shows a schematic flowchart of an embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application;
  • FIG. 13 shows a schematic flowchart of another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application;
  • FIG. 14 shows a schematic flowchart of still another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application;
  • FIG. 15 shows a schematic flowchart of another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application;
  • FIG. 16 shows a schematic flowchart of still another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application;
  • Fig. 17 shows a block diagram of a user portrait list construction device provided by an embodiment of the present application.
  • FIG. 18 shows a block diagram of a server used to execute the method for constructing a user portrait list according to an embodiment of the present application
  • FIG. 19 shows a storage unit for storing or carrying program codes for implementing the method for constructing a user portrait list according to an embodiment of the present application.
  • Operators generally push content to electronic devices to achieve operational goals.
  • the operator will obtain user portraits (user characteristics) before pushing.
  • user portraits also known as user roles, are an effective tool for delineating target users, contacting user demands and design directions.
  • User portraits have been widely used in various fields. Applications.
  • User portraits usually contain multiple dimensions of portrait features to characterize the appearance of users. For promotional activities, each activity needs to correspond to some user portrait features. All user portrait features targeted by the activity can form an activity portrait.
  • the inventor has discovered through long-term research and proposed the user portrait list construction method, device, server, and storage medium provided by the embodiments of this application.
  • the user can be obtained by collecting user data aggregation of each user within a certain construction period.
  • the portraits are updated to the distributed storage system in real time to participate in the construction of the user portrait list to improve the update efficiency and accuracy of the user portrait list.
  • the specific method for constructing the user portrait list will be described in detail in the subsequent embodiments.
  • the following describes a schematic diagram of an environment that can be used in the method for constructing a user portrait list provided in the embodiments of the present application.
  • FIG. 1 shows a schematic diagram of an application environment that can be used for the content pushing method provided in the embodiments of the present application. It includes a server 100 and an electronic device 200, and the electronic device 200 and the server 100 are in communication connection to realize data interaction.
  • the server 100 can send push content to the electronic device 200.
  • the electronic device 200 and the server 100 can be connected via a data network or a wireless network.
  • the electronic device 200 and the server 100 can be connected via a 2G network, a 3G network, a 4G network, a 5G network, etc.
  • the electronic device 200 and the server 100 can be connected through a wireless fidelity WiFi network, which is not limited here.
  • the electronic device 200 can be a smart phone, a tablet computer, a wearable electronic device, etc.
  • the server 100 can be a traditional server, a cloud server, etc., which is not limited herein.
  • FIG. 2 shows a schematic flowchart of a method for constructing a user portrait list provided by an embodiment of the present application.
  • the method for constructing a user portrait list is used to obtain user portraits by collecting user data aggregation of each user within a certain construction period, and updating to the distributed storage system in real time to participate in the construction of the user portrait list, so as to improve the update of the user portrait list. Efficiency and accuracy.
  • the method for building a user portrait list is applied to the user portrait list building device 300 shown in FIG. 17 and the server 100 (FIG. 18) configured with the user portrait list building device 300.
  • the following will take a server as an example to illustrate the specific process of this embodiment, where the server applied in this embodiment may be a cloud server or a traditional server, which is not limited here.
  • the process shown in FIG. 2 will be described in detail below, and the method for constructing a user portrait list may specifically include the following steps:
  • Step S110 In the current construction period, collect user data of each of the multiple users.
  • the construction period can be preset.
  • different time periods of each day may be preset as a construction period, one day may be preset as a construction period, or a week may be set as a construction period, etc., which is not limited here.
  • the current time may be acquired, the construction period in which the current time is located is determined as the current construction period, and user data of each of the multiple users can be collected. For example, if the preset build cycle is a different time period every day, and the current time is 9:00, you can use 8:00 to 12:00 as the current build cycle, and the build cycle is from 8:00 to 12:00 Collect user data for each of multiple users within.
  • the user data of each user in the video application program, the user data of each user in the search application program of the collection of multiple users, etc., are not limited here.
  • the collected user data of each user among the multiple users may include: the age of each user, the gender of each user, the occupation of each user, the income of each user, and each user
  • the hobbies, the apps downloaded by each user, and the ratings of the apps by each user are not limited here.
  • Step S120 Aggregate the user data of each user to obtain a user portrait of each user in the current construction period.
  • the user data of each user can be aggregated to obtain a user portrait of each user in the current construction period.
  • user data collected from different applications, services, systems, etc. can be aggregated to obtain the user’s current build User portraits during the cycle.
  • the user's basic portrait, business portrait, behavior portrait and other global user portraits can be constructed and combined Aggregate to obtain user portraits of users in the current construction cycle.
  • the user’s basic profile can be constructed based on the user’s age, gender, income, etc. collected from different applications, businesses, systems, etc.
  • the user’s business profile can be constructed based on user preferences collected from different applications, businesses, systems, etc. , Build user behavior portraits based on applications downloaded and installed by users collected from different applications, businesses, systems, etc., which are not limited here.
  • Step S130 Update the user portrait of each user in the current construction period to the distributed storage system, where the distributed storage system includes the user portrait of each user in the historical construction period.
  • the user portrait of each user in the current construction period can be updated to the distributed storage system, where the distributed storage system includes each User portraits of users in the historical construction period.
  • the distributed storage system includes each User portraits of users in the historical construction period.
  • the user portrait of each user in the historical construction period may be the user profile of each user in all construction periods before the current construction period. portrait; when the historical construction cycle is the construction cycle within the specified time before the current construction cycle, the user portrait of each user in the historical construction cycle can be the construction cycle of each user within the specified time before the current construction cycle User portrait.
  • Step S140 Construct a user portrait list of each user based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period.
  • the constructed user portrait list may include multiple users and user portraits corresponding to each of the multiple users. For example, it may include the user identification of each of the multiple users and the user profile of each of the multiple users. Each user’s user ID corresponds to the user portrait.
  • the constructed user portrait list may include multiple users and multiple user portraits corresponding to each of the multiple users. For example, it may include the user identification and multiple user identifications of each of the multiple users. Multiple user portraits corresponding to the user identification of each user in the users, where the multiple user portraits may include basic portraits, business portraits, behavior portraits, etc., which are not limited here.
  • the user portrait list construction method collects user data of each of multiple users in the current construction cycle, aggregates the user data of each user, and obtains that each user is in the current construction cycle.
  • the user portrait of each user in the current construction period is updated to the distributed storage system.
  • the distributed storage system includes the user portrait of each user in the historical construction period.
  • the user portrait in the construction period and the user portrait of each user in the historical construction period, and the user portrait list of each user is constructed, so that the user portrait is obtained by collecting the user data of each user in a certain construction period and updated in real time. Participate in the construction of the user portrait list in the distributed storage system to improve the update efficiency and accuracy of the user portrait list.
  • FIG. 3 shows a schematic flowchart of a method for constructing a user portrait list according to another embodiment of the present application.
  • the following will elaborate on the process shown in FIG. 3, and the method for constructing a list in the user portrait may specifically include the following steps:
  • Step S210 In the current construction period, collect user data of each of the multiple users.
  • Step S220 Aggregate the user data of each user to obtain a user portrait of each user in the current construction period.
  • Step S230 Update the user portrait of each user in the current construction period to the distributed storage system, where the distributed storage system includes the user portrait of each user in the historical construction period.
  • step S210 to step S230 please refer to step S110 to step S130, which will not be repeated here.
  • Step S240 Obtain the current user portrait of each user based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period.
  • the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period may be based on the user portrait of each user in the current construction period and each user The user portrait in the historical construction period is analyzed to obtain the current user portrait of each user.
  • the weight value of the user portrait of each user in the current construction period may be preset as the first weight value
  • the weight value of the user portrait of each user in the historical construction period may be set as the second weight value.
  • it can be based on the user portrait and the first weight value of each user in the current construction period, and the historical construction of each user
  • the user portrait in the period and the second weight value are used to obtain the current user portrait of each user.
  • the first weight value may be greater than the second weight value.
  • the user portrait characterization of the user in the historical construction period may be preset as the first weight value
  • the weight value of the user portrait of each user in the historical construction period may be set as the second weight value.
  • the user is more inclined to take out at 8 p.m., and the user portrait characterization of the user in the current construction period.
  • the user is more inclined to take out at 7 p.m.
  • the user portrait of the user and the current user portrait obtained from the user portrait of the user in the current construction period can be taken out at 7 o'clock in the evening.
  • Step S250 Construct a user portrait list of each user based on the current user portrait of each user.
  • a user portrait list of each user can be constructed based on the current user portrait of each user.
  • the current user portrait of each user can be taken as a whole to construct a user portrait list of each user to improve the comprehensiveness of the user portrait list corresponding to each user. sex.
  • the current user portrait of each user can be divided into different types of multiple current user portraits based on different types of current user portraits, and based on different types of current user portraits. Put more current user portraits, and build a user portrait list of each user separately, that is, build a list of multiple user portraits for each user.
  • FIG. 4 shows a schematic flowchart of an embodiment of step S250 of the method for constructing a user portrait list shown in FIG. 3 of the present application.
  • the following will elaborate on the process shown in FIG. 4, and the method may specifically include the following steps:
  • Step S251A Based on the current user portrait of each user, obtain the current basic portrait of each user.
  • the current user portrait of each user may include multiple different types of user portraits.
  • the current user portrait of each user may include current basic portraits, current business portraits, current behavior portraits, etc.
  • the service isolation current limit is used, and the access traffic of different services does not affect each other, and the corresponding type of user portrait is automatically obtained according to the service configuration.
  • the QPS can reach 20W+ and can be continuously expanded, the average service response time is 2ms, and the P99 response time is 10ms, which meets the demand for business traffic at the same time Basically, the access delay of the business system itself will not be blocked, and the user experience will not be affected.
  • the current basic portrait of each user may be obtained based on the current user portrait of each user.
  • user portrait filtering or user portrait extraction may be performed on the current user portrait of each user to obtain the current basic portrait from the current user portrait.
  • the current basic portrait may include: age, gender, occupation, etc., which are not limited here.
  • Step S252A Based on the current basic portrait of each user, construct a first user portrait list of each user.
  • a first user portrait list of each user may be constructed based on the current basic portrait of each user.
  • the first user portrait list is constructed based on the current basic portrait, if the user portrait that a user needs to use when accessing certain services is only related to the basic portrait, the user can be directly obtained from the first user list
  • the current basic portrait of the company in order to achieve business isolation and current limitation, and speed up the acquisition of the current basic portrait.
  • FIG. 5 shows a schematic flowchart of another embodiment of step S250 of the method for constructing a user portrait list shown in FIG. 3 of the present application.
  • the following will elaborate on the process shown in FIG. 5, and the method may specifically include the following steps:
  • Step S251B Based on the current user portrait of each user, obtain the current business portrait of each user.
  • the current business portrait of each user may be obtained based on the current user portrait of each user.
  • user portrait filtering or user portrait extraction may be performed on the current user portrait of each user to obtain the current business portrait from the current user portrait.
  • the current business portrait may include: user hobbies, user habits, etc., for example, may include the user's hobbies for game characters, game types, game screens, etc., which are not limited here.
  • Step S252B Construct a second user portrait list of each user based on the current business portrait of each user.
  • a second user portrait list of each user can be constructed based on the current business portrait of each user.
  • the second user portrait list is constructed based on the current business portrait, if the user portrait that a user needs to use when accessing certain services is only related to the business portrait, the user can be obtained directly from the second user list To achieve business isolation and current limiting, speed up the acquisition of current business portraits.
  • FIG. 6 shows a schematic flowchart of another embodiment of step S250 of the method for constructing a user portrait list shown in FIG. 3 of the present application.
  • the process shown in FIG. 6 will be described in detail below, and the method may specifically include the following steps:
  • Step S251C Based on the current user portrait of each user, obtain the current behavior portrait of each user.
  • the current behavior portrait of each user may be obtained based on the current user portrait of each user.
  • user portrait filtering or user portrait extraction may be performed on the current user portrait of each user to obtain the current behavior portrait from the current user portrait.
  • the current behavior profile may include: the user's download of the application, the user's installation of the application, the user's rating of the application, etc., which are not limited here.
  • Step S252C Construct a third user portrait list of each user based on the current behavior portrait of each user.
  • a third user portrait list of each user may be constructed based on the current behavior portrait of each user.
  • the third user portrait list is constructed based on the current behavior portrait, if the user portrait that a user needs to use when accessing certain services is only related to the behavior portrait, the user can be obtained directly from the third user list Current behavioral portraits to achieve business isolation and current limiting, and speed up the acquisition of current behavioral portraits.
  • the user data of each of the multiple users is collected, and the user data of each user is aggregated to obtain the current construction of each user.
  • the user portrait in the cycle the user portrait of each user in the current construction cycle is updated to the distributed storage system.
  • the distributed storage system includes the user portrait of each user in the historical construction cycle, based on the user portrait of each user in the historical construction cycle.
  • the user portrait in the current construction period and the user portrait of each user in the historical construction period the current user portrait of each user is obtained, and the user portrait list of each user is constructed based on the current user portrait of each user.
  • this embodiment Compared with the user portrait list construction method shown in Figure 2, this embodiment also obtains the current user of each user based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period.
  • the portrait participates in the construction of the user portrait list to improve the efficiency and accuracy of the constructed user portrait list.
  • FIG. 7 shows a schematic flowchart of a method for constructing a user portrait list according to another embodiment of the present application.
  • the process shown in FIG. 7 will be described in detail below, and the method for constructing a user portrait list may specifically include the following steps:
  • Step S310 In the current construction period, collect user data of each of the multiple users.
  • Step S320 Aggregate the user data of each user to obtain a user portrait of each user in the current construction period.
  • Step S330 Update the user portrait of each user in the current construction period to the distributed storage system, where the distributed storage system includes the user portrait of each user in the historical construction period.
  • step S310 to step S330 please refer to step S110 to step S130, which will not be repeated here.
  • Step S340 Obtain the user identification of each user.
  • the user identification of each user can be obtained, where the user identification can include a user identification number ID, that is, the user ID of each user can be obtained.
  • the user identification of each user can be obtained from the login information of each user, the user identification of each user can be obtained from the input information of each user, or the user identification of each user can be obtained from the verification information of each user. Obtain the user ID of each user, etc., which are not limited here.
  • Step S350 Based on the user identification of each user, the user portrait of each user in the current construction period, and the user portrait of each user in the historical construction period, construct each A list of user portraits of users.
  • the user identification of each user after the user identification of each user is obtained, the user identification of each user, the user portrait of each user in the current construction period, and the user portrait of each user in the historical construction period can be used to construct A list of user portraits for each user.
  • the constructed user portrait list of each user may include multiple user identities, user portraits of multiple users in the current construction period, and user portraits of multiple users in the historical construction period.
  • User portraits, where multiple user identities, user portraits of multiple users in the current construction period, and user portraits of multiple users in the historical construction period can be in one-to-one correspondence.
  • User ID User portraits in the current build cycle User portraits during the historical construction period User ID 1 User portrait A1 User portrait B1 User ID 2 User portrait A2 User portrait B2 User ID 3 User portrait A3 User portrait B3
  • the user data of each of the multiple users is collected, and the user data of each user is aggregated to obtain the current construction of each user.
  • the user portrait in the cycle the user portrait of each user in the current construction cycle is updated to the distributed storage system.
  • the distributed storage system includes the user portrait of each user in the historical construction cycle, and obtains the user portrait of each user.
  • User identification based on the user identification of each user, the user portrait of each user in the current construction period, and the user portrait of each user in the historical construction period, construct a user portrait list of each user.
  • this embodiment also obtains the user identification of each user with reference to the construction of the user portrait list, so as to improve the relevance of the user and the user portrait in the user portrait list, and enhance the user portrait The query speed.
  • FIG. 8 shows a schematic flowchart of a method for constructing a user portrait list according to another embodiment of the present application.
  • the process shown in FIG. 8 will be described in detail below, and the user list construction method may specifically include the following steps:
  • Step S410 Acquire the current user data corresponding to the current construction period from a preset mapping relationship table, where the preset mapping relationship table includes correspondences between multiple construction periods and multiple user data.
  • the server may obtain and record multiple construction periods and multiple user data in advance, and the correspondence between multiple construction periods and multiple user data.
  • a mapping relationship table between the multiple construction periods and the multiple user data is established as the preset mapping relationship table.
  • the preset mapping relationship table can include multiple build periods and multiple user data, where multiple build periods can correspond to multiple data data, and multiple build periods can correspond to one user data.
  • a weekly construction period can correspond to multiple user data, etc., which is not limited here.
  • the server may obtain current user data corresponding to the current construction period according to the current construction period.
  • the server may compare the current build period with multiple build periods in the preset mapping table established in advance to obtain a build period that matches the current build period.
  • the user data corresponding to the construction period matching the current construction period in the preset mapping relationship table is determined as the current user data.
  • Step S420 In the current construction period, collect current user data of each of the multiple users.
  • the current user data of each of the multiple users can be collected in the current construction period, so as to collect different users in different construction periods.
  • Data to meet the rationality of data collection For example, if the current user data corresponding to the current build period is the age of the user, the user age of each of the multiple users can be collected in the current build period; if the current user data corresponding to the current build period is the application installed by the user In the case of programs, you can collect the applications installed by each of multiple users in the current build cycle.
  • Step S430 Aggregate the user data of each user to obtain a user portrait of each user in the current construction period.
  • Step S440 Update the user portrait of each user in the current construction period to the distributed storage system, where the distributed storage system includes the user portrait of each user in the historical construction period.
  • Step S450 Construct a user portrait list of each user based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period.
  • step S430 to step S450 please refer to step S120 to step S140, which will not be repeated here.
  • the user portrait list construction method obtaineds current user data corresponding to the current construction period from a preset mapping relationship table, where the preset mapping relationship table includes multiple construction periods and multiple user households.
  • the current construction cycle collect the current user data of each user among multiple users, aggregate the user data of each user, obtain the user portrait of each user in the current construction cycle, and divide each user
  • the user portraits in the current construction cycle are updated to the distributed storage system, where the distributed storage system includes the user portraits of each user in the historical construction cycle, based on the user portraits of each user in the current construction cycle and each User portraits of users in the history construction cycle, and build a list of user portraits of each user.
  • this embodiment also obtains current user data corresponding to the current construction period based on the preset mapping relationship table, thereby obtaining different user data based on different construction periods, and improving the acquired users The accuracy and rationality of the data.
  • FIG. 9 shows a schematic flowchart of a method for constructing a user portrait list according to another embodiment of the present application.
  • the process shown in FIG. 9 will be described in detail below.
  • the method for constructing a user portrait list may specifically include the following steps:
  • Step S510 In the current construction period, collect user data of each of the multiple users.
  • Step S520 Aggregate the user data of each user to obtain the user portrait of each user in the current construction period.
  • Step S530 Update the user portrait of each user in the current construction period to the distributed storage system, where the distributed storage system includes the user portrait of each user in the historical construction period.
  • Step S540 Construct a user portrait list of each user based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period.
  • step S510 to step S540 please refer to step S110 to step S140, which will not be repeated here.
  • Step S550 When the service access of the target user is received, obtain the user portrait of the target user from the user portrait list.
  • the user portrait of the target user can be obtained from the user portrait list to increase the speed of obtaining the user portrait of the user.
  • the target user may be recorded in the user portrait list. Any user of multiple users.
  • the business access can be triggered on the electronic device, and the target user’s business access request is sent to the server.
  • the server receives When a target user's business access request is made, the target user's user portrait can be obtained from the user portrait list in response to the target user's business visit.
  • FIG. 10 shows a schematic flowchart of an embodiment of step S550 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • the process shown in FIG. 10 will be described in detail below, and the method may specifically include the following steps:
  • Step S551A When receiving the service access of the target user, obtain the user identification of the target user.
  • the user identification of the target user can be obtained, where the user identification of the target user may include: the user ID of the target user, the ID number of the target user, and the target user’s Telephone numbers, etc., are not limited here.
  • the target user's user identification can be obtained from the target user's basic information, login information, verification information, and the like.
  • Step S552A Based on the user identification of the target user, obtain the user portrait of the target user from the user portrait list.
  • the user portrait of the target user may be obtained from the user portrait list based on the user identification of the target user. For example, as shown in Table 1, when the user ID of the target user is user ID 1, when the target user’s business access is received, user portrait A1 and user portrait B1 can be obtained from the user portrait list as the target user’s users Portrait; when the user ID of the target user is user ID 2, when the target user's business access is received, user portrait A2 and user portrait B2 can be obtained from the user portrait list as the user portrait of the target user.
  • FIG. 11 shows a schematic flowchart of another embodiment of step S550 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • step S550 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • the process shown in FIG. 11 will be described in detail below.
  • the method may specifically include the following steps:
  • Step S551B When receiving the service access of the target user, obtain the service type of the service access.
  • the user portrait list may include a first user portrait list, a second user portrait list, and a third user portrait list, and the first user portrait list is constructed based on the user's basic portrait, and the second user portrait list is based on The user’s business portrait is constructed, and the third user portrait list is constructed based on the user’s behavior portrait.
  • the first user portrait list can correspond to the type of business related to the basic portrait
  • the second user portrait list can correspond to the business related to the business portrait.
  • the third user portrait list may correspond to the service type related to the behavior portrait, which is not limited here.
  • multiple user portrait lists can be created to achieve service isolation and current limiting, and the effect of different service accesses does not affect each other. Therefore, in this embodiment, when a target user's service access is received, the service type of the service access can be obtained.
  • Step S552B Obtain a target user portrait list corresponding to the service type from the multiple user portrait lists.
  • the target user portrait list corresponding to the service type may be obtained from multiple user portrait lists.
  • the target user portrait list corresponding to the current type may be obtained from the first user portrait list, the second user portrait list, and the third user portrait list.
  • the first user portrait list can be obtained from multiple user portrait lists as the target user portrait list; when the business type of the business visit is related to the business portrait, the first user portrait list can be obtained from multiple user portrait lists.
  • the second user portrait list is obtained from the user portrait list as the target user portrait list; when the type of service accessed by the business is related to the behavior portrait, the third user portrait list can be obtained from multiple user portrait lists as the target user portrait list.
  • Step S553B Obtain the user portrait of the target user from the target user portrait list.
  • the user portrait of the target user can be obtained from the target user portrait list, so that the user portrait required by the service type of the service access can be efficiently obtained. Satisfy the demand for obtaining user portraits.
  • the target user portrait list is the first user portrait list
  • the basic portrait of the target user can be obtained from the first user portrait list
  • the target user portrait list is the second user portrait list
  • the target user portrait list can be obtained from the first user portrait list. 2. Obtain the business portrait of the target user from the user portrait list.
  • Step S560 Based on the user portrait of the target user, obtain the content to be pushed corresponding to the user portrait of the target user.
  • the content to be pushed corresponding to the user portrait of the target user may be obtained based on the user portrait of the target user.
  • the user portrait of the target user is obtained as: male, office worker, preferred game, and 8 o'clock in the evening is the peak period for using mobile phones, so you can target the target user from 8 o'clock in the evening to the evening
  • Game-related content between ten o’clock is determined as the corresponding content to be pushed
  • the user portrait of the target user obtained is: female, prefer shopping, and use mobile phone at five o’clock in the afternoon
  • the shopping-related content between 4 pm and 6 pm can be determined as the corresponding content to be pushed for the target user.
  • Step S570 Push the content to be pushed to the target user.
  • the pushed content may be pushed to the target user, that is, the content to be pushed is pushed to the target user.
  • the content to be pushed is pushed to the target user.
  • FIG. 12 shows a schematic flowchart of an embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • the process shown in FIG. 12 will be described in detail below, and the method may specifically include the following steps:
  • Step S571A Based on the user portrait of the target user, obtain the push time for pushing the content to be pushed to the target user.
  • the time period during which the target user frequently uses the electronic device may be obtained based on the user portrait of the target user, and the period during which the target user frequently uses the electronic device is determined as the target user.
  • the push time for users to push the content to be pushed to improve the reach and conversion rate of the content to be pushed.
  • Step S572A Push the content to be pushed to the target user based on the push time.
  • the content to be pushed may be pushed to the target user based on the push time, so that the content to be pushed is pushed to the target user at the user’s high level.
  • the user is more likely to click to convert the content to be pushed.
  • FIG. 13 shows a schematic flowchart of another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • the process shown in FIG. 13 will be described in detail below, and the method may specifically include the following steps:
  • Step S571B Based on the user portrait of the target user, obtain the number of times of pushing the content to be pushed to the target user.
  • the number of conversions of the target user to each of the multiple contents may be obtained based on the user portrait of the target user, and the content to be pushed is compared with the content to be pushed.
  • the content is compared to obtain content that is consistent or similar to the content to be pushed, and the number of user conversions to the content that is consistent or similar to the content to be pushed is obtained, and the number of conversions is determined as the minimum number of content to be pushed to the target user The number of pushes to increase the conversion rate of the content to be pushed.
  • Step S572B Push the content to be pushed to the target user based on the number of push times.
  • the content to be pushed may be pushed to the target user based on the number of pushes, so that the number of pushes of the content to be pushed to the target user is more reasonable. In the case of frequent interruptions to target users, increase the conversion rate of the content to be pushed.
  • FIG. 14 shows a schematic flowchart of another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • the process shown in FIG. 14 will be described in detail below, and the method may specifically include the following steps:
  • Step S571C Based on the user portrait of the target user, obtain the formatting mode of the content to be pushed that is pushed to the target user.
  • the server may record the target user's display preferences for the content displayed by the electronic device, for example, record the target user's preference for the display position of the content displayed by the electronic device, the display size preference of the displayed content, and the displayed content
  • the preference of the display color, the preference of the display duration of the displayed content, etc. are not limited here, and the display preference is stored in the target database as the user portrait of the target user. Therefore, in this embodiment, after obtaining the user portrait of the target user, the typesetting method for pushing the content to be pushed to the target user may be obtained based on the user portrait of the target user.
  • Step S572C Push the content to be pushed to the target user based on the typesetting method.
  • the content to be pushed can be pushed to the target user based on the typesetting method, so that when the electronic device receives and displays the content to be pushed, it follows the set typesetting method.
  • the display is more in line with the user's display preference and improves the conversion rate of the content to be pushed.
  • FIG. 15 shows a schematic flowchart of another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • the process shown in FIG. 15 will be described in detail below, and the method may specifically include the following steps:
  • Step S571D Based on the user portrait of the target user, obtain a user matching the user portrait of the target user as a reference user.
  • the user portrait of the target user can be used to characterize the target user’s interest preferences, payment behavior, push conversion rate, etc.
  • the user portrait can be used to characterize the target user’s preferred game type, preferred video type, Purchasing power, click-through rate for push content, download rate for push content, etc.
  • the server may obtain and record user portraits of multiple users and each of the multiple users in advance, and establish a mapping relationship between multiple users and multiple user portraits, as shown in Table 3.
  • the mapping relationship can include multiple users and multiple user portraits, where multiple users can correspond to multiple user portraits, multiple users can correspond to one user portrait, one user can correspond to multiple user portraits, etc. Not limited.
  • the server may obtain a user who matches the user portrait of the target user as a reference user according to the user portrait of the target user.
  • the reference user can be determined from multiple users based on the user portrait.
  • the server may compare the user portrait of the target user with multiple user portraits in the pre-established mapping relationship to obtain the user portrait of the target user.
  • the matched user portrait based on the mapping relationship, obtains the user corresponding to the user portrait matching the user portrait of the target user.
  • the user can be determined as a reference user.
  • the server can search for interest preferences that match the target user’s interest preferences from multiple interest preferences, and based on the mapping relationship, search for users corresponding to the interest preferences that match the target user’s interest preferences.
  • the arrived user is determined as the reference user.
  • the server may obtain the user portrait of the target user and the content to be pushed, and may first filter multiple users based on the content to be pushed, so as to filter out the users who have received the content to be pushed from the multiple users.
  • the user who has received the content to be pushed and selected from multiple users is determined to be the user to be referred, and then the user portrait of the target user can be compared with the user portrait of the multiple users to be referred in the pre-established mapping relationship.
  • the user to be referenced can be determined as the reference user.
  • Step S572D Obtain the conversion rate of the reference user for the content to be pushed as a reference conversion rate.
  • the number of determined reference users is one or more. Wherein, when the number of determined reference users is one, the conversion rate of the reference user for the content to be pushed can be obtained, and the conversion rate of the reference user for the content to be pushed is used as the reference conversion rate. When the number of determined reference users is multiple, the conversion rate of the multiple reference users to the content to be pushed can be obtained separately, and the conversion rate of each reference user to the content to be pushed is calculated based on the conversion rate of each reference user to the content to be pushed The average conversion rate of, and use the average conversion rate as the reference conversion rate.
  • the server may count and record the number of times the content to be pushed is sent to the reference user and the number of times the reference user converts the content to be pushed, where the content pushed by the reference user conversion includes from browsing to the content to be pushed to click to jump, from From browsing to content to be pushed to click to download, from browsing to content to be pushed to click to purchase, etc., there is no limitation here.
  • the server may calculate the conversion rate of the reference user for the pushed content as the reference conversion rate by calculating the recorded number of times the content to be pushed is sent to the reference user and the number of times the reference user converts the content to be pushed.
  • Step S473D Determine a manner of pushing the content to be pushed to the target user based on the reference conversion rate.
  • the server may determine the processing method for the pushed content according to the reference conversion rate. It is understandable that because the user portraits of the reference user and the target user match, the method of pushing the content to be pushed to the target user is determined based on the reference conversion rate of the reference user for the pushed content, which can make the processing method more in line with the preferences of the target user. It can improve the conversion rate of pushed content and the target user's experience.
  • the mapping relationship between the reference conversion rate and the processing method may be established in advance, and the mapping relationship may include multiple reference conversion rates and multiple methods.
  • One reference conversion rate can correspond to one method
  • one reference conversion rate can correspond to multiple methods, and so on.
  • the reference conversion rate of the reference user for the pushed content can be obtained, and then the reference conversion rate of the reference user for the pushed content is compared with the conversion rate in the pre-established mapping relationship to obtain and the reference user for the pushed content
  • a method corresponding to the conversion rate matching the reference conversion rate of the reference user for the pushed content is obtained based on the mapping relationship, and the obtained processing method is determined as the method of the electronic device for pushing the content.
  • the method may include pushing the content to be pushed to the target user, not pushing the content to be pushed to the target user, controlling the duration of pushing the content to be pushed to the target user, controlling the number of times that the content to be pushed is pushed to the target user, and controlling The time when the content to be pushed is pushed to the target user is not limited here.
  • a designated conversion rate may be preset and stored, and the designated conversion rate is used as a judgment basis for the reference conversion rate. Therefore, after the reference conversion rate is obtained, the reference conversion rate can be compared with the specified conversion rate to determine whether the reference conversion rate is greater than the specified conversion rate. When the judgment result indicates that the reference conversion rate is greater than the specified conversion rate, the target The user pushes the content to be pushed, and when the reference conversion rate is not greater than the specified conversion rate, the content to be pushed may not be pushed to the target user.
  • FIG. 16 shows a schematic flowchart of another embodiment of step S570 of the method for constructing a user portrait list shown in FIG. 9 of the present application.
  • the process shown in FIG. 16 will be described in detail below, and the method may specifically include the following steps:
  • Step S571E Based on the user portrait of the target user, obtain a user who matches the user portrait of the target user as a reference user.
  • step S571E For the specific description of step S571E, please refer to step S571D, which will not be repeated here.
  • Step S572E Obtain the score of the reference user for the content to be pushed as a reference score.
  • the number of determined reference users is one or more. Wherein, when the number of determined reference users is one, the score of the reference user for the content to be pushed can be obtained, and the score of the reference user for the content to be pushed can be used as the reference score. When the number of determined reference users is multiple, the scores of the multiple reference users for the content to be pushed can be obtained separately, and the average of the multiple reference users for the content to be pushed is calculated based on the scores of each reference user for the content to be pushed Score, and use the average score as a reference score.
  • Step S473E Determine a manner of pushing the content to be pushed to the target user based on the reference score.
  • the server may determine the processing method for the pushed content according to the reference score. It is understandable that because the user portraits of the reference user and the target user are matched, the method of pushing the content to be pushed to the target user is determined based on the reference score of the reference user for the pushed content, which can make the processing method more in line with the preferences of the target user. Improve the conversion rate of pushed content and the target user's experience.
  • a mapping relationship between reference scores and processing methods may be established in advance, and the mapping relationship may include multiple reference scores and multiple methods, wherein multiple reference scores and multiple methods can be one-to-one corresponding to multiple reference scores. It can correspond to one way, one reference score can correspond to multiple ways, and so on.
  • the reference score of the reference user for the pushed content can be obtained, and then the reference score of the reference user for the pushed content is compared with the score in the pre-established mapping relationship to obtain the reference score of the reference user for the pushed content.
  • a method corresponding to the score matching the reference score of the reference user for the pushed content is acquired based on the mapping relationship, and the acquired processing method is determined as the method of the electronic device for pushing the content.
  • the method may include pushing the content to be pushed to the target user, not pushing the content to be pushed to the target user, controlling the duration of pushing the content to be pushed to the target user, controlling the number of times that the content to be pushed is pushed to the target user, and controlling The time when the content to be pushed is pushed to the target user is not limited here.
  • a designated score can be preset and stored, and the designated score is used as a basis for determining the reference score. Therefore, after obtaining the reference score, the reference score can be compared with the specified score to determine whether the reference score is greater than the specified score. When the judgment result indicates that the reference score is greater than the specified score, the content to be pushed can be pushed to the target user. When the reference score is not greater than the specified score, the content to be pushed may not be pushed to the target user.
  • the user portrait list construction method provided in another embodiment of the present application collects user data of each of multiple users in the current construction cycle, aggregates the user data of each user, and obtains the current construction period of each user.
  • the user portrait in the construction cycle is updated to the distributed storage system for the user portrait of each user in the current construction cycle.
  • the distributed storage system includes the user portrait of each user in the historical construction cycle, based on each user
  • the user portraits in the current construction cycle and the users of each user in the historical construction cycle build a list of user portraits for each user, and when the target user’s business access is received, the target user’s user is obtained from the user portrait list Portrait, based on the user portrait of the target user, obtain the content to be pushed corresponding to the user portrait of the target user, and push the content to be pushed to the target user.
  • this implementation obtains the user portrait of the target user according to the user portrait list when receiving the business access of the target user, and determines the content to be pushed based on the user portrait of the target user , In order to realize the personalized content push of thousands of people in business services.
  • FIG. 17 shows a block diagram of a user portrait list building apparatus 300 provided by an embodiment of the present application.
  • the user portrait list construction device 300 includes: a user data collection module 310, a user portrait acquisition module 320, a user portrait update module 330, and a user portrait list construction module 340, in which:
  • the user data collection module 310 is used to collect user data of each of the multiple users in the current construction period.
  • the user data collection module 310 includes: a current user data acquisition sub-module and a current user data collection sub-module, wherein:
  • the current user data obtaining sub-module is used to obtain the current user data corresponding to the current construction period from a preset mapping relationship table, wherein the preset mapping relationship table includes a plurality of construction periods and a plurality of user data correspondences .
  • the current user data collection sub-module is configured to collect current user data of each of the multiple users in the current construction period.
  • the user portrait obtaining module 320 is configured to aggregate the user data of each user to obtain the user portrait of each user in the current construction period.
  • the user portrait update module 330 is configured to update the user portrait of each user in the current construction period to the distributed storage system, where the distributed storage system includes the historical construction period of each user User portraits inside.
  • the user portrait list construction module 340 is configured to construct a user portrait of each user based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period List of portraits.
  • the user portrait list building module 340 includes: a current user portrait obtaining submodule and a first user portrait list building submodule, wherein:
  • the current user portrait obtaining sub-module is used to obtain the current user portrait of each user based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period. User portrait.
  • the first user portrait list construction sub-module is used to construct the user portrait list of each user based on the current user portrait of each user.
  • the first user portrait list construction sub-module includes: a current basic portrait acquisition unit and a first user portrait list construction unit, wherein:
  • the current basic portrait obtaining unit is configured to obtain the current basic portrait of each user based on the current user portrait of each user.
  • the first user portrait list construction unit is configured to construct the first user portrait list of each user based on the current basic portrait of each user.
  • the first user portrait list construction sub-module includes: a current business portrait acquisition unit and a second user portrait list construction unit, wherein:
  • the current business portrait acquiring unit is configured to acquire the current business portrait of each user based on the current user portrait of each user.
  • the second user portrait list construction unit is configured to construct a second user portrait list of each user based on the current business portrait of each user.
  • the first user portrait list construction sub-module includes: a current behavior portrait acquisition unit and a third user portrait list construction unit, wherein:
  • the current behavior portrait acquiring unit is configured to acquire the current behavior portrait of each user based on the current user portrait of each user.
  • the third user portrait list construction unit is configured to construct a third user portrait list of each user based on the current behavior portrait of each user.
  • the user portrait list construction module 340 includes: a user identification acquisition sub-module and a second user portrait list construction sub-module, wherein:
  • the user identification acquisition sub-module is used to acquire the user identification of each user.
  • the second user portrait list construction sub-module is configured to be based on the user identification of each user, the user portrait of each user in the current construction period, and the history of each user in the history construction period. User portrait, construct a user portrait list of each user.
  • the user portrait list construction module 300 further includes: a target user portrait acquisition module, a content to be pushed acquisition module, and a content push module to be pushed, wherein:
  • the target user portrait obtaining module is used to obtain the user portrait of the target user from the user portrait list when the target user's business access is received.
  • the target user portrait obtaining module includes: a user identification obtaining submodule and a first target user portrait obtaining submodule, wherein:
  • the user identification acquisition sub-module is configured to acquire the user identification of the target user when the business access of the target user is received.
  • the first target user portrait obtaining sub-module is configured to obtain the user portrait of the target user from the user portrait list based on the user identification of the target user.
  • the target user portrait acquisition module includes: a business type acquisition submodule, a target user portrait list
  • the acquisition sub-module and the target user portrait acquisition sub-module including:
  • the service type obtaining submodule is used to obtain the service type of the service access when the service access of the target user is received.
  • the target user portrait list obtaining submodule is used to obtain a target user portrait list corresponding to the service type from the multiple user portrait lists.
  • the target user portrait obtaining sub-module is used to obtain the user portrait of the target user from the target user portrait list.
  • the content to be pushed acquisition module is configured to acquire the content to be pushed corresponding to the user portrait of the target user based on the user portrait of the target user.
  • the content to be pushed push module is used to push the content to be pushed to the target user.
  • the content pushing module to be pushed includes: a pushing time acquisition submodule and a first content pushing submodule to be pushed, wherein:
  • the push time acquisition sub-module is configured to acquire the push time for pushing the content to be pushed to the target user based on the user portrait of the target user.
  • the first to-be-pushed content pushing sub-module is configured to push the to-be-pushed content to the target user based on the pushing time.
  • the content pushing module to be pushed includes: a number of pushing times obtaining submodule and a second content pushing submodule to be pushed, wherein:
  • the push times acquisition submodule is configured to acquire the push times of pushing the content to be pushed to the target user based on the user portrait of the target user.
  • the second content to be pushed push submodule is configured to push the content to be pushed to the target user based on the number of pushes.
  • the content push module to be pushed includes: a typesetting method acquisition submodule and a third content push submodule to be pushed, wherein:
  • the typesetting mode obtaining sub-module is used to obtain the typesetting mode of the content to be pushed pushed to the target user based on the user portrait of the target user.
  • the third content to be pushed push submodule is configured to push the content to be pushed to the target user based on the typesetting method.
  • the content push module to be pushed includes: a first reference user acquisition submodule, a reference conversion rate acquisition submodule, and a push mode determination submodule, wherein:
  • the first reference user acquisition sub-module is configured to acquire a user who matches the user portrait of the target user as a reference user based on the user portrait of the target user.
  • the reference conversion rate obtaining sub-module is configured to obtain the conversion rate of the reference user for the content to be pushed as a reference conversion rate.
  • the push method determination submodule is configured to determine the method of pushing the content to be pushed to the target user based on the reference conversion rate.
  • the pushing method determining submodule includes: a content pushing unit to be pushed, wherein:
  • the content to be pushed pushing unit is configured to push the content to be pushed to the target user when the reference conversion rate is greater than a specified conversion rate.
  • the content push module to be pushed includes: a second reference user acquisition submodule, a reference score acquisition submodule, and a fourth content push submodule to be pushed, wherein:
  • the second reference user acquisition sub-module is configured to acquire a user who matches the user portrait of the target user as a reference user based on the user portrait of the target user.
  • the reference score obtaining submodule is used to obtain the score of the reference user for the content to be pushed as a reference score.
  • the fourth content-to-be-pushing submodule is configured to determine a manner of pushing the content-to-be-push to the target user based on the reference score.
  • the coupling between the modules may be electrical, mechanical or other forms of coupling.
  • the functional modules in the various embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software functional modules.
  • FIG. 18 shows a structural block diagram of a server 100 provided by an embodiment of the present application.
  • the server 100 may be a server capable of running application programs, such as a smart phone, a tablet computer, or an e-book.
  • the server 100 in this application may include one or more of the following components: a processor 110, a memory 120, and one or more application programs, where one or more application programs may be stored in the memory 120 and configured to be operated by one or Multiple processors 110 execute, and one or more programs are configured to execute the method described in the foregoing method embodiment.
  • the processor 110 may include one or more processing cores.
  • the processor 110 uses various interfaces and lines to connect various parts of the entire server 100, and executes the server by running or executing instructions, programs, code sets, or instruction sets stored in the memory 120, and calling data stored in the memory 120. 100's various functions and processing data.
  • the processor 110 may adopt at least one of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA).
  • DSP Digital Signal Processing
  • FPGA Field-Programmable Gate Array
  • PDA Programmable Logic Array
  • the processor 110 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), a modem, and the like.
  • the CPU mainly processes the operating system, user interface, and application programs; the GPU is used for rendering and drawing the content to be displayed; the modem is used for processing wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 110, but may be implemented by a communication chip alone.
  • the memory 120 may include random access memory (RAM) or read-only memory (Read-Only Memory).
  • the memory 120 may be used to store instructions, programs, codes, code sets or instruction sets.
  • the memory 120 may include a program storage area and a data storage area, where the program storage area may store instructions for implementing an operating system and instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.) , Instructions used to implement the following various method embodiments, etc.
  • the storage data area can also store data (such as phone book, audio and video data, chat record data) created by the server 100 during use.
  • FIG. 19 shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application.
  • the computer-readable medium 400 stores program code, and the program code can be invoked by a processor to execute the method described in the foregoing method embodiment.
  • the computer-readable storage medium 400 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the computer-readable storage medium 400 includes a non-transitory computer-readable storage medium.
  • the computer-readable storage medium 400 has a storage space for the program code 410 for executing any method steps in the above-mentioned methods. These program codes can be read from or written into one or more computer program products.
  • the program code 410 may be compressed in a suitable form, for example.
  • the user portrait list construction method, device, server, and storage medium collect user data of each of multiple users in the current construction cycle, and the user data of each user Perform aggregation to obtain the user portrait of each user in the current construction cycle, and update the user portrait of each user in the current construction cycle to the distributed storage system, where the distributed storage system includes each user in the historical construction cycle Based on the user portrait of each user in the current construction period and the user portrait of each user in the historical construction period, build a user portrait list of each user, so as to collect each user in a certain construction period
  • the user data of the user profile is aggregated to obtain user portraits, and updated to the distributed storage system in real time to participate in the construction of the user portrait list, so as to improve the update efficiency and accuracy of the user portrait list.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本申请公开了一种用户画像列表构建方法、装置、服务器以及存储介质,涉及信息推送技术领域。在当前构建周期内,收集多个用户中的每个用户的用户数据,对每个用户的用户数据进行聚合,获得每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表。本申请通过在一定构建周期内收集每个用户的用户数据聚合获得用户画像,并实时更新到分布式存储系统中参与用户画像列表的构建,以提高用户画像列表的更新效率和准确率。

Description

用户画像列表构建方法、装置、服务器以及存储介质 技术领域
本申请涉及信息推送技术领域,更具体地,涉及一种用户画像列表构建方法、装置、服务器以及存储介质。
背景技术
随着科学技术的发展,电子设备的使用越来越广泛,功能越来越多,已经成为人们日常生活中的必备之一。目前,服务器一般会向电子设备推送内容,以在电子设备进行展示。
发明内容
鉴于上述问题,本申请提出了一种用户画像列表构建方法、装置、服务器以及存储介质,以解决上述问题。
第一方面,本申请实施例提供了一种用户画像列表构建方法,所述方法包括:在当前构建周期内,收集多个用户中的每个用户的用户数据;对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像;将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像;基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
第二方面,本申请实施例提供了一种用户画像列表构建装置,所述装置包括:用户数据收集模块,用于在当前构建周期内,收集多个用户中的每个用户的用户数据;用户画像获得模块,用于对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像;用户画像更新模块,用于将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像;用户画像列表构建模块,用于基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
第三方面,本申请实施例提供了一种服务器,包括存储器和处理器,所述存储器耦接到所述处理器,所述存储器存储指令,当所述指令由所述处理器执行时所述处理器执行上述方法。
第四方面,本申请实施例提供了一种计算机可读取存储介质,所述计算机可读取存储介质中存储有程序代码,所述程序代码可被处理器调用执行上述方法。
本申请实施例提供的用户画像列表构建方法、装置、服务器以及存储介质,在当前构建周期内,收集多个用户中的每个用户的用户数据,对每个用户的用户数据进行聚合,获得每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表,从而通过在一定构建周期内收集每个用户的用户数据聚合获得用户画像,并实时更新到分布式存储系统中参与用户画像列表的构建,以提高用户画像列表的更新效率和准确率。
附图说明
为了更清楚地说明本申请实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其它的附图。
图1示出了可用于本申请实施例提供的用户画像列表构建方法的应用环境示意图;
图2示出了本申请一个实施例提供的用户画像列表构建方法的流程示意图;
图3示出了本申请又一个实施例提供的用户画像列表构建方法的流程示意图;
图4示出了本申请的图3所示的用户画像列表构建方法的步骤S250的一个实施例的流程示意图;
图5示出了本申请的图3所示的用户画像列表构建方法的步骤S250的又一个实施例的流程示意图;
图6示出了本申请的图3所示的用户画像列表构建方法的步骤S250的再一个实施例的流程示意图;
图7示出了本申请再一个实施例提供的用户画像列表构建方法的流程示意图;
图8示出了本申请另一个实施例提供的用户画像列表构建方法的流程示意图;
图9示出了本申请又再一个实施例提供的用户画像列表构建方法的流程示意图;
图10示出了本申请的图9所示的用户画像列表构建方法的步骤S550的一个实施例的流程示意 图;
图11示出了本申请的图9所示的用户画像列表构建方法的步骤S550的又一个实施例的流程示意图;
图12示出了本申请的图9所示的用户画像列表构建方法的步骤S570的一个实施例的流程示意图;
图13示出了本申请的图9所示的用户画像列表构建方法的步骤S570的又一个实施例的流程示意图;
图14示出了本申请的图9所示的用户画像列表构建方法的步骤S570的再一个实施例的流程示意图;
图15示出了本申请的图9所示的用户画像列表构建方法的步骤S570的另一个实施例的流程示意图;
图16示出了本申请的图9所示的用户画像列表构建方法的步骤S570的又再一个实施例的流程示意图;
图17示出了本申请实施例提供的用户画像列表构建装置的模块框图;
图18示出了本申请实施例用于执行根据本申请实施例的用户画像列表构建方法的服务器的框图;
图19示出了本申请实施例的用于保存或者携带实现根据本申请实施例的用户画像列表构建方法的程序代码的存储单元。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案,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。
运营方一般会通过向电子设备推送内容以达到运营目的。通常,运营方在推送前会获取用户画像(用户特征),其中,用户画像又称用户角色,是一种勾画目标用户、联系用户诉求及设计方向的有效工具,用户画像在各领域得到了广泛的应用。用户画像通常包含多个维度的画像特征来表征用户的样子,对于促销活动,每个活动都需要对应一些用户画像特征,活动针对的所有用户画像特征即可形成活动画像,通过活动画像与用户画像进行对比,将包含活动画像的画像特征的用户画像圈进活动人群,即可生成促销活动的活动人群,以针对该活动人群进行活动投放,以实现目标用户的精准圈取,再进行统一、批量的推送,以提升推送内容的点击率与资源利用率,同时最小化无用推送信息对用户体验的负面影响。
目前,用户画像通过离线方式加工生产出来存储在离线的存储系统中,对于线上业务服务,用户画像的更新获取不够及时。另外,目前的大多数系统,是以优化展示的素材及内容为主要优化点,没有考虑到用户的爱好不同,如中老年可能更喜爱淡雅一些的色彩,年轻人更喜爱绚丽一些的色彩,男性更喜爱运动相关的内容,女性更喜爱美妆相关的内容等,因此,目前的业务服务只能做到用户千人一面的内容推送。
针对上述问题,发明人经过长期的研究发现,并提出了本申请实施例提供的用户画像列表构建方法、装置、服务器以及存储介质,通过在一定构建周期内收集每个用户的用户数据聚合获得用户画像,并实时更新到分布式存储系统中参与用户画像列表的构建,以提高用户画像列表的更新效率和准确率。其中,具体的用户画像列表构建方法在后续的实施例中进行详细的说明。
下面将针对可用于本申请实施例提供的用户画像列表构建方法的环境示意图进行描述。
请参阅图1,图1示出了可用于本申请实施例提供的内容推送方法的应用环境示意图。其包括服务器100和电子设备200,电子设备200和服务器100通信连接以实现数据交互,例如,服务器100可以发送推送内容至电子设备200。其中,电子设备200和服务器100可以通过数据网络或无线网络连接,当电子设备200和服务器100通过数据网络连接时,电子设备200和服务器100可以通过2G网络、3G网络、4G网络、5G网络等连接,当电子设备200和服务器100通过无线网络连接时,电子设备200和服务器100可以通过无线保真WiFi网络连接,在此不做限定。其中,电子设备200可以为智能手机、平板电脑、穿戴式电子设备等,服务器100可以为传统服务器,云服务器等,在此不做限定。
请参阅图2,图2示出了本申请一个实施例提供的用户画像列表构建方法的流程示意图。所述用户画像列表构建方法用于通过在一定构建周期内收集每个用户的用户数据聚合获得用户画像,并实时更新到分布式存储系统中参与用户画像列表的构建,以提高用户画像列表的更新效率和准确率。其中,在具体的实施例中,所述用户画像列表构建方法应用于如图17所示的用户画像列表构建装置300以及配置有用户画像列表构建装置300的服务器100(图18)。下面将以服务器为例,说明本实施例的具体流程,其中,本实施例所应用的服务器可以为云服务器,也可以为传统服务器,在此不 做限定。下面将针对图2所示的流程进行详细的阐述,所述用户画像列表构建方法具体可以包括以下步骤:
步骤S110:在当前构建周期内,收集多个用户中的每个用户的用户数据。
在本实施例中,可以预先设置构建周期。例如,可以预先设置每天的不同时间段为一个构建周期,可以预先设置一天为一个构建周期,也可以设置一周为一个构建周期等,在此不做限定。其中,当预先设置的构建周期为每天的不同时间段时,可以将每天的8:00~12:00设置为一个构建周期,12:00~16:00设置为一个构建周期,12:00~20:00设置为一个构建周期,20:00~24:00设置为一个构建周期以及24:00~8:00设置为一个构建周期。
在一些实施方式中,可以获取当前时间,将当前时间所在的构建周期确定为当前构建周期,并收集多个用户中的每个用户的用户数据。例如,若预先设置的构建周期为每天不同的时间段,且当前时间为9:00时,可以将8:00~12:00作为当前构建周期,并在8:00~12:00的构建周期内收集多个用户中的每个用户的用户数据。
在一些实施方式中,可以在当前构建周期内,收集多个用户中的每个用户在不同应用程序、不同业务、不同系统等的用户数据。以应用程序为例,可以收集多个用户中的每个用户在聊天类应用程序中的用户数据、收集多个用户中的每个用户在游戏类应用程序中的用户数据、收集多个用户中的每个用户在视频类应用程序中的用户数据、收集多个用户中的每个用户在搜索类应用程序中的用户数据等,在此不做限定。
在一些实施方式中,所收集的多个用户中的每个用户的用户数据可以包括:每个用户的年龄、每个用户的性别、每个用户的职业、每个用户的收入、每个用户的爱好、每个用户所下载的应用、每个用户对应用的评分等,在此不做限定。
步骤S120:对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像。
在本实施例中,在收集到每个用户的用户数据后,可以将每个用户的用户数据进行聚合,以获得每个用户在当前构建周期内的用户画像。在一些实施方式中,在从不同的应用程序、业务、系统等收集到用户的用户数据后,可以将从不同应用程序、业务、系统等收集到的用户数据进行聚合,以获得用户在当前构建周期内的用户画像。
在一些实施方式中,在从不同的应用程序、业务、系统等收集到用户的用户数据后,可以基于规则及算法分析、构建用户的基础画像、业务画像、行为画像等全局维度的用户画像并聚合,以获得用户在当前构建周期内的用户画像。其中,可以基于从不同应用程序、业务、系统等收集到的用户的年龄、性别、收入等构建用户的基础画像,基于从不同应用程序、业务、系统等收集到的用户喜好构建用户的业务画像,基于从不同应用程序、业务、系统等收集到的用户下载安装的应用构建用户的行为画像等,在此不做限定。
步骤S130:将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像。
在本实施例中,在获取每个用户在当前构建周期内的用户画像后,可以将每个用户在当前构建周期内的用户画像更新到分布式存储系统,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像。具体地,由于所获取的多个用户的用户画像有上千维度,且每个维度特征的用户量可能超过亿级,并且不同用户画像的更新周期及时间点不一致,因此,在获取每个用户在当前构建周期内的用户画像后,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,可以提升用户画像的更新和获取的性能和吞吐量,并且,由于分布式存储系统还包括每个用户在历史构建周期内的用户画像,因此,将每个用户在当前构建周期内的用户画像更新到分布式存储系统,可以提升每个用户的用户画像的更新实时性。
在一些实施方式中,当历史构建周期为当前构建周期之前的所有构建周期时,则每个用户在历史构建周期内的用户画像可以为每个用户在当前构建周期之前的所有构建周期内的用户画像;当历史构建周期为当前构建周期之前的指定时间内的构建周期时,则每个用户在历史构建周期内的用户画像可以为每个用户在当前构建周期之前的指定时间内的构建周期内的用户画像。
步骤S140:基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
在本实施例中,在获取每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像后,可以基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表。
在一些实施方式中,构建的用户画像列表可以包括多个用户和多个用户中的每个用户对应的用户画像,例如,可以包括多个用户中的每个用户的用户标识和多个用户中的每个用户的用户标识对应的用户画像。
在一些实施方式中,构建的用户画像列表可以包括多个用户和多个用户中的每个用户对应的多个用户画像,例如,可以包括多个用户中的每个用户的用户标识和多个用户中的每个用户的用户标 识对应的多个用户画像,其中,多个用户画像可以包括基础画像、业务画像、行为画像等,在此不做限定。
本申请一个实施例提供的用户画像列表构建方法,在当前构建周期内,收集多个用户中的每个用户的用户数据,对每个用户的用户数据进行聚合,获得每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表,从而通过在一定构建周期内收集每个用户的用户数据聚合获得用户画像,并实时更新到分布式存储系统中参与用户画像列表的构建,以提高用户画像列表的更新效率和准确率。
请参阅图3,图3示出了本申请又一个实施例提供的用户画像列表构建方法的流程示意图。下面将针对图3所示的流程进行详细的阐述,所述用户画像里列表构建方法具体可以包括以下步骤:
步骤S210:在当前构建周期内,收集多个用户中的每个用户的用户数据。
步骤S220:对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像。
步骤S230:将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像。
其中,步骤S210-步骤S230的具体描述请参阅步骤S110-步骤S130,在此不再赘述。
步骤S240:基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,获得所述每个用户的当前用户画像。
在一些实施方式中,在获取每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像后,可以基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,分析获得获取每个用户的当前用户画像。
在一些实施方式中,可以预先设置每个用户在当前构建周期内的用户画像的权重值作为第一权重值,设置每个用户在历史构建周期内的用户画像的权重值作为第二权重值,则在获取每个用户在当前构建周期内的用户画像和每个用户在历史构建周期时,可以基于每个用户在当前构建周期内的用户画像和第一权重值,以及每个用户在历史构建周期内的用户画像和第二权重值,获得每个用户的当前用户画像。其中,于本实施例中,第一权重值可以大于第二权重值。例如,用户在历史构建周期内的用户画像表征用户更倾向于在晚上8点点外卖,用户在当前构建周期内的用户画像表征用户更倾向于在晚上7点点外卖,则基于用户在历史构建周期内的用户画像和用户在当前构建周期内的用户画像获得的当前用户画像可以为在晚上7点点外卖。
步骤S250:基于所述每个用户的当前用户画像,构建所述每个用户的用户画像列表。
在本实施例中,在获取每个用户的当前用户画像后,可以基于每个用户的当前用户画像,构建每个用户的用户画像列表。在一些实施方式中,在获取每个用户的当前用户画像后,可以将每个用户的当前用户画像作为整体,构建每个用户的用户画像列表,以提升每个用户对应的用户画像列表的全面性。在一些实施方式中,在获取每个用户的当前用户画像后,可以按当前用户画像的不同类型,将每个用户的当前用户画像划分为不同类型的多个当前用户画像,并基于不同类型的多放个当前用户画像,分别构建每个用户的用户画像列表,即构建获得每个用户的多个用户画像列表。
请参阅图4,图4示出了本申请的图3所示的用户画像列表构建方法的步骤S250的一个实施例的流程示意图。下面将针对图4所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S251A:基于所述每个用户的当前用户画像,获取所述每个用户的当前基础画像。
在一些实施方式中,每个用户的当前用户画像可以包括多个不同类型的用户画像,例如,每个用户的当前用户画像可以包括当前基础画像、当前业务画像、当前行为画像等,以实现由于不同业务、不同场景需要使用的用户画像不一致时的业务隔离限流,不同业务访问流量相互不影响,并根据业务配置化自动获取对应类型的用户画像。在一些实施方式中,通过设置当前用户画像包括多个不同类型的用户画像的方式,可以满足QPS达到20W+并可不断扩展,服务平均响应时间2ms,P99响应时间10ms,满足业务访问量需求的同时基本不会阻塞业务系统本身的访问延迟,不影响用户体验。
在本实施例中,在获取每个用户的当前用户画像后,可以基于每个用户的当前用户画像,获取每个用户的当前基础画像。在一些实施方式中,在获取每个用户的当前用户画像后,可以对每个用户的当前用户画像进行用户画像过滤或者用户画像提取,以从当前用户画像中获取当前基础画像。其中,该当前基础画像可以包括:年龄、性别、职业等,在此不做限定。
步骤S252A:基于所述每个用户的当前基础画像,构建所述每个用户的第一用户画像列表。
在本实施例中,在获取每个用户的当前基础画像后,可以基于每个用户的当前基础画像,构建每个用户的第一用户画像列表。其中,由于第一用户画像列表是基于当前基础画像构建的,因此,若某用户在访 问某些业务时需要使用的用户画像仅与基础画像相关,则可以直接从第一用户列表中获取该用户的当前基础画像,以实现业务隔离限流,加快当前基础画像的获取速度。
请参阅图5,图5示出了本申请的图3所示的用户画像列表构建方法的步骤S250的又一个实施例的流程示意图。下面将针对图5所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S251B:基于所述每个用户的当前用户画像,获取所述每个用户的当前业务画像。
在本实施例中,在获取每个用户的当前用户画像后,可以基于每个用户的当前用户画像,获取每个用户的当前业务画像。在一些实施方式中,在获取每个用户的当前用户画像后,可以对每个用户的当前用户画像进行用户画像过滤或者用户画像提取,以从当前用户画像中获取当前业务画像。其中,该当前业务画像可以包括:用户爱好,用户习惯等,例如可以包括用户对游戏角色的爱好、对游戏类型的爱好、对游戏画面的爱好等,在此不做限定。
步骤S252B:基于所述每个用户的当前业务画像,构建所述每个用户的第二用户画像列表。
在本实施例中,在获取每个用户的当前业务画像后,可以基于每个用户的当前业务画像,构建每个用户的第二用户画像列表。其中,由于第二用户画像列表是基于当前业务画像构建的,因此,若某用户在访问某些业务时需要使用的用户画像仅与业务画像相关,则可以直接从第二用户列表中获取该用户的当前业务画像,以实现业务隔离限流,加快当前业务画像的获取速度。
请参阅图6,图6示出了本申请的图3所示的用户画像列表构建方法的步骤S250的再一个实施例的流程示意图。下面将针对图6所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S251C:基于所述每个用户的当前用户画像,获取所述每个用户的当前行为画像。
在本实施例中,在获取每个用户的当前用户画像后,可以基于每个用户的当前用户画像,获取每个用户的当前行为画像。在一些实施方式中,在获取每个用户的当前用户画像后,可以对每个用户的当前用户画像进行用户画像过滤或者用户画像提取,以从当前用户画像中获取当前行为画像。其中,该当前行为画像可以包括:用户对应用程序的下载情况、用户对应用程序的安装情况、用户对应用程序的评分等,在此不做限定。
步骤S252C:基于所述每个用户的当前行为画像,构建所述每个用户的第三用户画像列表。
在本实施例中,在获取每个用户的当前行为画像后,可以基于每个用户的当前行为画像,构建每个用户的第三用户画像列表。其中,由于第三用户画像列表是基于当前行为画像构建的,因此,若某用户在访问某些业务时需要使用的用户画像仅与行为画像相关,则可以直接从第三用户列表中获取该用户的当前行为画像,以实现业务隔离限流,加快当前行为画像的获取速度。
本申请又一个实施例提供的用户画像列表构建方法,在当前构建周期内,收集多个用户中的每个用户的用户数据,对每个用户的用户数据进行聚合,获得每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,获得每个用户的当前用户画像,基于每个用户的当前用户画像,构建每个用户的用户画像列表。相较于图2所示的用户画像列表构建方法,本实施例还基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,获取每个用户的当前用户画像参与用户画像列表的构建,以提升构建的用户画像列表的效率和准确性。
请参阅图7,图7示出了本申请再一个实施例提供的用户画像列表构建方法的流程示意图。下面将针对图7所示的流程进行详细的阐述,所述用户画像列表构建方法具体可以包括以下步骤:
步骤S310:在当前构建周期内,收集多个用户中的每个用户的用户数据。
步骤S320:对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像。
步骤S330:将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像。
其中,步骤S310-步骤S330的具体描述请参阅步骤S110-步骤S130,在此不再赘述。
步骤S340:获取所述每个用户的用户标识。
在本实施例中,可以获取每个用户的用户标识,其中,用户标识可以包括用户身份标识号码ID,即可以获取每个用户的用户ID。在一些实施方式中,可以从每个用户的登录信息中获取每个用户的用户标识,可以从每个用户的输入信息中获取每个用户的用户标识,也可以从每个用户的验证信息中获取每个用户的用户标识等,在此不做限定。
步骤S350:基于所述每个用户的用户标识、所述每个用户在所述当前构建周期内的用户画像以及所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
在本实施例中,在获取每个用户的用户标识后,可以基于每个用户的用户标识、每个用户在当前构建周期内的用户画像以及每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表。
在一些实施方式中,如表1所示,所构建的每个用户的用户画像列表可以包括多个用户标识、多个用户在当前构建周期内的用户画像和多个用户在历史构建周期内的用户画像,其中,多个用户标识、多个用户在当前构建周期内的用户画像以及多个用户在历史构建周期内的用户画像可以一一对应。
用户标识 当前构建周期内的用户画像 历史构建周期内的用户画像
用户标识1 用户画像A1 用户画像B1
用户标识2 用户画像A2 用户画像B2
用户标识3 用户画像A3 用户画像B3
本申请再一个实施例提供的用户画像列表构建方法,在当前构建周期内,收集多个用户中的每个用户的用户数据,对每个用户的用户数据进行聚合,获得每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,获取每个用户的用户标识,基于每个用户的用户标识、每个用户在当前构建周期内的用户画像以及每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表。相较于图2所示的用户画像列表构建方法,本实施例还获取每个用户的用户标识参考用户画像列表的构建,以提升用户画像列表中的用户与用户画像的关联性,提升用户画像的查询速度。
请参阅图8,图8示出了本申请另一个实施例提供的用户画像列表构建方法的流程示意图。下面将针对图8所示的流程进行详细的阐述,所述用户列表构建方法具体可以包括以下步骤:
步骤S410:从预设映射关系表中获取所述当前构建周期对应的当前用户数据,其中,所述预设映射关系表包括多个构建周期和多个用户数据的对应关系。
在一些实施方式中,服务器可以预先获取并记录多个构建周期和多个用户数据,以及多个构建周期和多个用户数据的对应关系。根据多个构建周期和多个用户数据的对应关系建立多个构建周期和多个用户数据的映射关系表作为预设映射关系表。如表2所示,该预设映射关系表可以包括多个构建周期和多个用户数据,其中,多个构建周期和多个数据数据可以一一对应,多个构建周期可以和一个用户数据对应,一个周建周期可以和多个用户数据对应等,在此不做限定。
构建周期 用户数据
构建周期1 用户数据1
构建周期2 用户数据2
构建周期3 用户数据3
在本实施例中,服务器在获取当前构建周期后,可以根据当前构建周期,获取与当前构建周期对应的当前用户数据。作为一种方式,服务器在获取到当前构建周期后,可以将当前构建周期和预先建立的预设映射关系表中的多个构建周期进行对比,以获取与当前构建周期匹配的构建周期,再基于预设映射关系表中与当前构建周期匹配的构建周期对应的用户数据,将与当前构建周期匹配的构建周期对应的用户数据确定为当前用户数据。
步骤S420:在所述当前构建周期内,收集所述多个用户中的每个用户的当前用户数据。
在一些实施方式中,在确定当前构建周期对应的当前用户数据后,可以在当前构建周期内,收集多个用户中的每个用户的当前用户数据,以实现在不同的构建周期收集不同的用户数据,满足数据收集的合理性。例如,若当前构建周期对应的当前用户数据为用户年龄,则可以在当前构建周期内,收集多个用户中的每个用户的用户年龄;若当前构建周期对应的当前用户数据为用户安装的应用程序时,则可以在当前构建周期内,收集多个用户中的每个用户所安装的应用程序。
步骤S430:对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像。
步骤S440:将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像。
步骤S450:基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
其中,步骤S430-步骤S450的具体描述请参阅步骤S120-步骤S140,在此不再赘述。
本申请另一个实施例提供的用户画像列表构建方法,从预设映射关系表中获取当前构建周期对应的当前用户数据,其中,预设映射关系表包括多个构建周期和多个用户户数的对应关系,在当前构建周期内,收集多个用户中的每个用户的当前用户数据,对每个用户的用户数据进行聚合,获取每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,基于每个用户在当 前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表。相较于图2所示的用户画像列表构建方法,本实施例还基于预设映射关系表获取当前构建周期对应的当前用户数据,从而基于不同的构建周期获取不同的用户数据,提升获取的用户数据的精确性和合理性。
请参阅图9,图9示出了本申请又再一个实施例提供的用户画像列表构建方法的流程示意图。下面将针对图9所示的流程进行详细的阐述,所述用户画像列表构建方法具体可以包括以下步骤:
步骤S510:在当前构建周期内,收集多个用户中的每个用户的用户数据。
步骤S520:对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像。
步骤S530:将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像。
步骤S540:基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
其中,步骤S510-步骤S540的具体描述请参阅步骤S110-步骤S140,在此不再赘述。
步骤S550:当接收到目标用户的业务访问时,从所述用户画像列表中获取所述目标用户的用户画像。
在本实施例中,当接收到目标用户的业务访问时,可以从用户画像列表中获取目标用户的用户画像,以提升用户的用户画像的获取速度,其中,目标用户可以是用户画像列表中记录的多个用户中的任意用户。
在一些实施方式中,当目标用户在电子设备触发针对应用程序的访问、针对业务系统的访问等时,可以在电子设备触发业务访问,并发送目标用户的业务访问请求至服务器,当服务器接收到目标用户的业务访问请求时,可以响应该目标用户的业务访问,从用户画像列表中获取目标用户的用户画像。
请参阅图10,图10示出了本申请的图9所示的用户画像列表构建方法的步骤S550的一个实施例的流程示意图。下面将针对图10所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S551A:当接收到所述目标用户的业务访问时,获取所述目标用户的用户标识。
在一些实施方式中,当接收到目标用户的业务访问时,可以获取目标用户的用户标识,其中,目标用户的用户标识可以包括:目标用户的用户ID,目标用户的身份证号码、目标用户的电话号码等,在此不做限定。在一些实施方式中,当接收到目标用户的业务访问时,可以从目标用户的基础信息、登录信息、验证信息等中获取该目标用户的用户标识。
步骤S552A:基于所述目标用户的用户标识,从所述用户画像列表中获取所述目标用户的用户画像。
在一些实施方式中,在获取目标用户的用户标识后,可以基于目标用户的用户标识,从用户画像列表中获取目标用户的用户画像。例如,如表1所示,当目标用户的用户标识为用户标识1时,则当接收到目标用户的业务访问时,可以从用户画像列表中获取用户画像A1和用户画像B1作为目标用户的用户画像;当目标用户的用户标识为用户标识2时,则当接收到目标用户的业务访问时,可以从用户画像列表中获取用户画像A2和用户画像B2作为目标用户的用户画像。
请参阅图11,图11示出了本申请的图9所示的用户画像列表构建方法的步骤S550的又一个实施例的流程示意图。其中,用户画像列表的数量为多个,且每个用户画像列表对应每个用户的不同画像类型,下面将针对图11所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S551B:当接收到所述目标用户的业务访问时,获取所述业务访问的业务类型。
在本实施例中,用户画像列表的数量为多个,且每个用户画像列表对应每个用户的不同画像类型。其中,在一些实施方式中,用户画像列表可以包括第一用户画像列表、第二用户画像列表以及第三用户画像列表,且第一用户画像列表基于用户的基础画像构建,第二用户画像列表基于用户的业务画像构建,第三用户画像列表基于用户的行为画像构建,那么,该第一用户画像列表可以和与基础画像相关的业务类型对应,第二用户画像列表可以和与业务画像相关的业务类型对应,第三用户画像列表可以和与行为画像相关的业务类型对应,在此不做限定。
在一些实施方式中,由于不同访问业务需要使用的用户画像不同,可以通过创建多个用户画像列表的方式,实现业务隔离限流,不同业务访问之间互不影响的效果。因此,在本实施例中,当接收到目标用户的业务访问时,可以获取该业务访问的业务类型。
步骤S552B:从所述多个用户画像列表中获取与所述业务类型对应的目标用户画像列表。
在本实施例中,在获取业务访问的业务类型后,可以从多个用户画像列表中获取与业务类型对应的目标用户画像列表。在一些实施方式中,在获取业务访问的业务类型后,可以从第一用户画像列表、第二用户画像列表以及第三用户画像列表中获取与当前类型对应的目标用户画像列表。其中,当业务访问的业务类型与基础画像相关时,可以从多个用户画像列表中获取第一用户画像列表作为目标用户画像列表;当业务访问的业务类型与业务画像相关时,可以从多个用户画像列表中获取第二用户画像列表作为目标用户画像列表;当业务访问的业务类型与行为画像相关时,可以从多个用户画像列表中获取第三用户画像列表作 为目标用户画像列表。
步骤S553B:从所述目标用户画像列表中获取所述目标用户的用户画像。
在本实施例中,在确定业务类型对应的目标用户画像列表后,可以从从目标用户画像列表中获取目标用户的用户画像,从而可以高效的获取业务访问的业务类型所需求的用户画像,以满足用户画像的获取需求。在一些实施方式中,当目标用户画像列表为第一用户画像列表,则可以从第一用户画像列表中获取目标用户的基础画像,当目标用户画像列表为第二用户画像列表,则可以从第二用户画像列表中获取目标用户的业务画像。
步骤S560:基于所述目标用户的用户画像,获取与所述目标用户的用户画像对应的待推送内容。
在本实施例中,在获取目标用户的用户画像后,可以基于目标用户的用户画像,获取与目标用户的用户画像对应的待推送内容。例如,当目标用户访问某个应用程序时,获取到目标用户的用户画像为:男性、上班族、偏好游戏、晚上八点是使用手机的高峰期,就可以针对目标用户将晚上八点到晚上十点之间的游戏相关内容确定为对应的待推送内容;又例如,当目标用户访问某个应用程序时,获取到目标用户的用户画像为:女性、偏好购物、下午五点是使用手机的高峰期,就可以针对该目标用户将下午四点到下午六点之间的购物相关内容确定为对应的待推送内容。
步骤S570:向所述目标用户推送所述待推送内容。
在一些实施方式中,在获取与目标用户的用户画像对应的待推送内容后,可以将推送内容推送给目标用户,即向目标用户推送待推送内容。如此可以做到不同用户千人千面的内容展示甚至于相同用户不同时间段偏好一人千面的内容展示,可极大提升用户活跃、留存、转化等相关指标,并且这种通用能力可无成本复制到不同业务。
请参阅图12,图12示出了本申请的图9所示的用户画像列表构建方法的步骤S570的一个实施例的流程示意图。下面将针对图12所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S571A:基于所述目标用户的用户画像,获取向所述目标用户推送所述待推送内容的推送时间。
在一些实施方式中,在获取目标用户的用户画像后,可以基于目标用户的用户画像获取目标用户高频使用电子设备的时间段,将该目标用户高频使用电子设备的时间段确定为向目标用户推送待推送内容的推送时间,以提升待推送内容的触达率和转化率。
步骤S572A:基于所述推送时间,向所述目标用户推送所述待推送内容。
在一些实施方式中,在确定向目标用户推送待推送内容的推送时间后,可以基于该推送时间向目标用户推送该待推送内容,以使待推送内容在向目标用户推送时,是在用户高频使用电子设备的时间段,则用户点击转化该待推送内容的几率更高。
请参阅图13,图13示出了本申请的图9所示的用户画像列表构建方法的步骤S570的又一个实施例的流程示意图。下面将针对图13所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S571B:基于所述目标用户的用户画像,获取向所述目标用户推送所述待推送内容的推送次数。
在一些实施方式中,在获取目标用户的用户画像和待推送内容后,可以基于目标用户的用户画像获取目标用户对多个内容的中的每个内容的转化次数,并将待推送内容与多个内容进行比较,以获取与待推送内容一致或相近的内容,并获取用户对该与待推送内容一致或相近的内容的转化次数,将该转化次数确定为向目标用户推送待推送内容的最少推送次数,以提升待推送内容的转化率。
步骤S572B:基于所述推送次数,向所述目标用户推送所述待推送内容。
在一些实施方式中,在确定向目标用户推送待推送内容的推送次数后,可以基于该推送次数向目标用户推送该待推送内容,以使待推送内容向目标用户的推送次数更加合理,在不频繁打扰目标用户的情况下,提升待推送内容的转化率。
请参阅图14,图14示出了本申请的图9所示的用户画像列表构建方法的步骤S570的再一个实施例的流程示意图。下面将针对图14所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S571C:基于所述目标用户的用户画像,获取向所述目标用户推送的所述待推送内容排版方式。
在一些实施方式中,服务器可以记录目标用户对于电子设备所展示内容的展示偏好,例如,记录目标用户对于电子设备所展示内容的展示位置的偏好、所展示内容的展示大小的偏好、所展示内容的展示颜色的偏好、所展示内容的展示时长的偏好等,在此不做限定,将该展示偏好存储在目标数据库中作为目标用户的用户画像。因此,在本实施例中,在获取目标用户的用户画像后,可以基于该目标用户的用户画像,获取向目标用户推送该待推送内容的排版方式。
步骤S572C:基于所述排版方式,向所述目标用户推送所述待推送内容。
在一些实施方式中,在获取待推送内容的排版方式后,可以基于该排版方式,向目标用户推送待推送内容,以使电子设备在接收并展示待推送内容时,是按照设置的排版方式进行展示,更符合 用户的展示偏好,提升待推送内容的转化率。
请参阅图15,图15示出了本申请的图9所示的用户画像列表构建方法的步骤S570的另一个实施例的流程示意图。下面将针对图15所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S571D:基于所述目标用户的用户画像,获取与所述目标用户的用户画像匹配的用户作为参考用户。
在本实施例中,该目标用户的用户画像可以用于表征目标用户的兴趣偏好、支付行为、推送转化率等,例如,用户画像可以用于表征目标用户偏好的游戏类型、偏好的视频类型、购买力、对推送内容的点击率、对推送内容的下载率等。
在一些实施方式中,服务器可以预先获取并记录多个用户以及多个用户中的每个用户的用户画像,建立多个用户和多个用户画像之间的映射关系,如表3所示,该映射关系可以包括多个用户和多个用户画像,其中多个用户和多个用户画像可以一一对应、多个用户可以和一个用户画像对应、一个用户可以和多个用户画像对应等,在此不做限定。
表3
用户 用户画像
用户1 用户画像1
用户2 用户画像2
用户3 用户画像3
在本实施例中,服务器在获取到目标用户的用户画像后,可以根据目标用户的用户画像,获取与目标用户的用户画像匹配的用户作为参考用户。作为一种方式,在获取到目标用户的用户画像后,可以基于该用户画像从多个用户中确定参考用户。具体地,在一些实施方式中,服务器在获取到目标用户的用户画像时,可以将目标用户的用户画像和预先建立的映射关系中的多个用户画像进行对比,以获取与目标用户的用户画像匹配的用户画像,再基于映射关系获取与目标用户的用户画像匹配的用户画像对应的用户,在确定与目标用户的用户画像匹配的用户画像对应的用户时,可以将该用户确定为参考用户。以用户画像为兴趣偏好为例,服务器可以从多个兴趣偏好中查找与目标用户的兴趣偏好匹配的兴趣偏好,并基于映射关系查找与目标用户的兴趣偏好匹配的兴趣偏好对应的用户,将查找到的用户确定为参考用户。
在一些实施方式中,服务器可以获取目标用户的用户画像和待推送内容,可以先基于待推送内容对多个用户进行筛选,以从多个用户中筛选出接收到过待推送内容的用户,将从多个用户中筛选出的接收到过待推送内容的用户确定为待参考用户,然后可以将目标用户的用户画像和预先建立的映射关系中的多个待参考用户的用户画像进行对比,以获取与目标用户的用户画像匹配的用户画像,再基于映射关系获取与目标用户的用户画像匹配的用户画像对应的待参考用户,在确定与目标用户的用户画像匹配的用户画像对应的待参考用户时,可以将该待参考用户确定为参考用户。
步骤S572D:获取所述参考用户针对所述待推送内容的转化率作为参考转化率。
在一些实施方式中,所确定的参考用户的数量为一个或多个。其中,当所确定的参考用户的数量为一个时,可以获取该一个参考用户针对待推送内容的转化率,并将该一个参考用户针对待推送内容的转化率作为参考转化率。当所确定的参考用户的数量为多个时,可以分别获取该多个参考用户针对待推送内容的转化率,并基于每个参考用户针对待推送内容的转化率计算多个参考用户针对待推送内容的平均转化率,并将平均转化率作为参考转化率。
在一些实施方式中,服务器可以统计并记录待推送内容发送给参考用户的次数和参考用户转化待推送内容的次数,其中,参考用户转化推送内容包括从浏览到待推送内容到点击跳转、从浏览到待推送内容到点击下载,从浏览到待推送内容到点击购买等,在此不做限定。作为一种方式,服务器在确定参考用户后,可以将记录的待推送内容发送给参考用户的次数和参考用户转化待推送内容的次数计算参考用户针对推送内容的转化率作为参考转化率。
步骤S473D:基于所述参考转化率确定向所述目标用户推送所述待推送内容的方式。
在一些实施方式中,服务器在获取到参考用户针对待推送内容的参考转化率后,可以根据参考转化率确定对推送内容的处理方式。可以理解的是,由于参考用户和目标用户的用户画像匹配,因此,基于参考用户针对推送内容的参考转化率确定向目标用户推送待推送内容的方式,可以使得处理方式更符合目标用户的喜好,可以提升推送内容的转化率和目标用户的体验。
在一些实施方式中,可以预先建立参考转化率和处理方式的映射关系,该映射关系可以包括多个参考转化率和多个方式,其中多个参考转化率和多个方式可以一一对应、多个参考转化率可以和一个方式对应、一个参考转化率可以和多个方式对应等。在本实施例中,可以获取参考用户针对推送内容的参考转化率,再将参考用户针对推送内容的参考转化率和预先建立的映射关系中的转化率 进行对比,以获取与参考用户针对推送内容的参考转化率匹配的转化率,再基于映射关系获取与参考用户针对推送内容的参考转化率匹配的转化率对应的方式,将所获取的处理方式确定为电子设备对推送内容的方式。
在本实施例中,该方式可以包括向目标用户推送待推送内容、不向目标用户推送待推送内容、控制向目标用户推送待推送内容的时长、控制向目标用户推送待推送内容的次数、控制向目标用户推送待推送内容的时刻等,在此不做限定。
在一些实施方式中,可以预先设置并存储指定转化率,该指定转化率用于作为参考转化率的判断依据。因此,在获取参考转化率后,可以将参考转化率与指定转化率进行比较,以判断参考转化率是否大于指定转化率,其中,当判断结果表征参考转化率大于指定转化率时,可以向目标用户推送待推送内容,当参考转化率不大于指定转化率时,可以不向目标用户推送待推送内容。
请参阅图16,图16示出了本申请的图9所示的用户画像列表构建方法的步骤S570的又再一个实施例的流程示意图。下面将针对图16所示的流程进行详细的阐述,所述方法具体可以包括以下步骤:
步骤S571E:基于所述目标用户的用户画像,获取与所述目标用户的用户画像匹配的用户作为参考用户。
其中,步骤S571E的具体描述请参阅步骤S571D,在此不再赘述。
步骤S572E:获取所述参考用户针对所述待推送内容的评分作为参考评分。
在一些实施方式中,所确定的参考用户的数量为一个或多个。其中,当所确定的参考用户的数量为一个时,可以获取该一个参考用户针对待推送内容的评分,并将该一个参考用户针对待推送内容的评分作为参考评分。当所确定的参考用户的数量为多个时,可以分别获取该多个参考用户针对待推送内容的评分,并基于每个参考用户针对待推送内容的评分计算多个参考用户针对待推送内容的平均评分,并将平均评分作为参考评分。
步骤S473E:基于所述参考评分确定向所述目标用户推送所述待推送内容的方式。
在一些实施方式中,服务器在获取到参考用户针对待推送内容的参考评分后,可以根据参考评分确定对推送内容的处理方式。可以理解的是,由于参考用户和目标用户的用户画像匹配,因此,基于参考用户针对推送内容的参考评分确定向目标用户推送待推送内容的方式,可以使得处理方式更符合目标用户的喜好,可以提升推送内容的转化率和目标用户的体验。
在一些实施方式中,可以预先建立参考评分和处理方式的映射关系,该映射关系可以包括多个参考评分和多个方式,其中多个参考评分和多个方式可以一一对应、多个参考评分可以和一个方式对应、一个参考评分可以和多个方式对应等。在本实施例中,可以获取参考用户针对推送内容的参考评分,再将参考用户针对推送内容的参考评分和预先建立的映射关系中的评分进行对比,以获取与参考用户针对推送内容的参考评分匹配的评分,再基于映射关系获取与参考用户针对推送内容的参考评分匹配的评分对应的方式,将所获取的处理方式确定为电子设备对推送内容的方式。
在本实施例中,该方式可以包括向目标用户推送待推送内容、不向目标用户推送待推送内容、控制向目标用户推送待推送内容的时长、控制向目标用户推送待推送内容的次数、控制向目标用户推送待推送内容的时刻等,在此不做限定。
在一些实施方式中,可以预先设置并存储指定评分,该指定评分用于作为参考评分的判断依据。因此,在获取参考评分后,可以将参考评分与指定评分进行比较,以判断参考评分是否大于指定评分,其中,当判断结果表征参考评分大于指定评分时,可以向目标用户推送待推送内容,当参考评分不大于指定评分时,可以不向目标用户推送待推送内容。
本申请又再一个实施例提供的用户画像列表构建方法,在当前构建周期内,收集多个用户中的每个用户的用户数据,对每个用户的用户数据进行聚合,获得每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户互相,构建每个用户的用户画像列表,当接收到目标用户的业务访问时,从用户画像列表中获取目标用户的用户画像,基于目标用户的用户画像,获取目标用户的用户画像对应的待推送内容,向目标用户推送待推送内容。相较于图2所示的用户画像列表构建方法,本实施了还在接收到目标用户的业务访问时,根据用户画像列表获取目标用户的用户画像,并基于目标用户的用户画像确定待推送内容,以实现业务服务的千人千面的个性化内容推送。
请参阅图17,图17示出了本申请实施例提供的用户画像列表构建装置300的模块框图。下面将针对图17所示的框图进行阐述,所述用户画像列表构建装置300包括:用户数据收集模块310、用户画像获得模块320、用户画像更新模块330以及用户画像列表构建模块340,其中:
用户数据收集模块310,用于在当前构建周期内,收集多个用户中的每个用户的用户数据。
进一步地,所述用户数据收集模块310包括:当前用户数据获取子模块和当前用户数据收集子模块,其中:
当前用户数据获取子模块,用于从预设映射关系表中获取所述当前构建周期对应的当前用户数据,其中,所述预设映射关系表包括多个构建周期和多个用户数据的对应关系。
当前用户数据收集子模块,用于在所述当前构建周期内,收集所述多个用户中的每个用户的当前用户数据。
用户画像获得模块320,用于对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像。
用户画像更新模块330,用于将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像。
用户画像列表构建模块340,用于基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
进一步地,所述用户画像列表构建模块340包括:当前用户画像获得子模块和第一用户画像列表构建子模块,其中:
当前用户画像获得子模块,用于基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,获得所述每个用户的当前用户画像。
第一用户画像列表构建子模块,用于基于所述每个用户的当前用户画像,构建所述每个用户的用户画像列表。
进一步地,所述第一用户画像列表构建子模块包括:当前基础画像获取单元和第一用户画像列表构建单元,其中:
当前基础画像获取单元,用于基于所述每个用户的当前用户画像,获取所述每个用户的当前基础画像。
第一用户画像列表构建单元,用于基于所述每个用户的当前基础画像,构建所述每个用户的第一用户画像列表。
进一步地,所述第一用户画像列表构建子模块包括:当前业务画像获取单元和第二用户画像列表构建单元,其中:
当前业务画像获取单元,用于基于所述每个用户的当前用户画像,获取所述每个用户的当前业务画像。
第二用户画像列表构建单元,用于基于所述每个用户的当前业务画像,构建所述每个用户的第二用户画像列表。
进一步地,所述第一用户画像列表构建子模块包括:当前行为画像获取单元和第三用户画像列表构建单元,其中:
当前行为画像获取单元,用于基于所述每个用户的当前用户画像,获取所述每个用户的当前行为画像。
第三用户画像列表构建单元,用于基于所述每个用户的当前行为画像,构建所述每个用户的第三用户画像列表。
进一步地,所述用户画像列表构建模块340包括:用户标识获取子模块和第二用户画像列表构建子模块,其中:
用户标识获取子模块,用于获取所述每个用户的用户标识。
第二用户画像列表构建子模块,用于基于所述每个用户的用户标识、所述每个用户在所述当前构建周期内的用户画像以及所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
进一步地,所述用户画像列表构建模块300还包括:目标用户画像获取模块、待推送内容获取模块以及待推送内容推送模块,其中:
目标用户画像获取模块,用于当接收到目标用户的业务访问时,从所述用户画像列表中获取所述目标用户的用户画像。
进一步地,所述目标用户画像获取模块包括:用户标识获取子模块和第一目标用户画像获取子模块,其中:
用户标识获取子模块,用于当接收到所述目标用户的业务访问时,获取所述目标用户的用户标识。
第一目标用户画像获取子模块,用于基于所述目标用户的用户标识,从所述用户画像列表中获取所述目标用户的用户画像。
进一步地,所述用户画像列表的数量为多个,且每个用户画像列表对应所述每个用户的不同画像类型,所述目标用户画像获取模块包括:业务类型获取子模块、目标用户画像列表获取子模块以及目标用户画像获取子模块,其中:
业务类型获取子模块,用于当接收到所述目标用户的业务访问时,获取所述业务访问的业务类型。
目标用户画像列表获取子模块,用于从所述多个用户画像列表中获取与所述业务类型对应的目标用户 画像列表。
目标用户画像获取子模块,用于从所述目标用户画像列表中获取所述目标用户的用户画像。
待推送内容获取模块,用于基于所述目标用户的用户画像,获取与所述目标用户的用户画像对应的待推送内容。
待推送内容推送模块,用于向所述目标用户推送所述待推送内容。
进一步地,所述待推送内容推送模块包括:推送时间获取子模块和第一待推送内容推送子模块,其中:
推送时间获取子模块,用于基于所述目标用户的用户画像,获取向所述目标用户推送所述待推送内容的推送时间。
第一待推送内容推送子模块,用于基于所述推送时间,向所述目标用户推送所述待推送内容。
进一步地,所述待推送内容推送模块包括:推送次数获取子模块和第二待推送内容推送子模块,其中:
推送次数获取子模块,用于基于所述目标用户的用户画像,获取向所述目标用户推送所述待推送内容的推送次数。
第二待推送内容推送子模块,用于基于所述推送次数,向所述目标用户推送所述待推送内容。
进一步地,所述待推送内容推送模块包括:排版方式获取子模块和第三待推送内容推送子模块,其中:
排版方式获取子模块,用于基于所述目标用户的用户画像,获取向所述目标用户推送的所述待推送内容排版方式。
第三待推送内容推送子模块,用于基于所述排版方式,向所述目标用户推送所述待推送内容。
进一步地,所述待推送内容推送模块包括:第一参考用户获取子模块、参考转化率获取子模块以及推送方式确定子模块,其中:
第一参考用户获取子模块,用于基于所述目标用户的用户画像,获取与所述目标用户的用户画像匹配的用户作为参考用户。
参考转化率获取子模块,用于获取所述参考用户针对所述待推送内容的转化率作为参考转化率。
推送方式确定子模块,用于基于所述参考转化率确定向所述目标用户推送所述待推送内容的方式。
进一步地,所述推送方式确定子模块包括:待推送内容推送单元,其中:
待推送内容推送单元,用于当所述参考转化率大于指定转化率时,向所述目标用户推送所述待推送内容。
进一步地,所述待推送内容推送模块包括:第二参考用户获取子模块、参考评分获取子模块以及第四待推送内容推送子模块,其中:
第二参考用户获取子模块,用于基于所述目标用户的用户画像,获取与所述目标用户的用户画像匹配的用户作为参考用户。
参考评分获取子模块,用于获取所述参考用户针对所述待推送内容的评分作为参考评分。
第四待推送内容推送子模块,用于基于所述参考评分确定向所述目标用户推送所述待推送内容的方式。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述装置和模块的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,模块相互之间的耦合可以是电性,机械或其它形式的耦合。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理模块中,也可以是各个模块单独物理存在,也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。
请参阅图18,其示出了本申请实施例提供的一种服务器100的结构框图。该服务器100可以是智能手机、平板电脑、电子书等能够运行应用程序的服务器。本申请中的服务器100可以包括一个或多个如下部件:处理器110、存储器120以及一个或多个应用程序,其中一个或多个应用程序可以被存储在存储器120中并被配置为由一个或多个处理器110执行,一个或多个程序配置用于执行如前述方法实施例所描述的方法。
其中,处理器110可以包括一个或者多个处理核。处理器110利用各种接口和线路连接整个服务器100内的各个部分,通过运行或执行存储在存储器120内的指令、程序、代码集或指令集,以及调用存储在存储器120内的数据,执行服务器100的各种功能和处理数据。可选地,处理器110可以采用数字信号处理(Digital Signal Processing,DSP)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)、可编程逻辑阵列(Programmable Logic Array,PLA)中的至少一种硬件形式来实现。处理器110可集成中央处理器(Central Processing Unit,CPU)、图形处理器(Graphics  Processing Unit,GPU)和调制解调器等中的一种或几种的组合。其中,CPU主要处理操作系统、用户界面和应用程序等;GPU用于负责待显示内容的渲染和绘制;调制解调器用于处理无线通信。可以理解的是,上述调制解调器也可以不集成到处理器110中,单独通过一块通信芯片进行实现。
存储器120可以包括随机存储器(Random Access Memory,RAM),也可以包括只读存储器(Read-Only Memory)。存储器120可用于存储指令、程序、代码、代码集或指令集。存储器120可包括存储程序区和存储数据区,其中,存储程序区可存储用于实现操作系统的指令、用于实现至少一个功能的指令(比如触控功能、声音播放功能、图像播放功能等)、用于实现下述各个方法实施例的指令等。存储数据区还可以存储服务器100在使用中所创建的数据(比如电话本、音视频数据、聊天记录数据)等。
请参阅图19,其示出了本申请实施例提供的一种计算机可读存储介质的结构框图。该计算机可读介质400中存储有程序代码,所述程序代码可被处理器调用执行上述方法实施例中所描述的方法。
计算机可读存储介质400可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。可选地,计算机可读存储介质400包括非易失性计算机可读介质(non-transitory computer-readable storage medium)。计算机可读存储介质400具有执行上述方法中的任何方法步骤的程序代码410的存储空间。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。程序代码410可以例如以适当形式进行压缩。
综上所述,本申请实施例提供的用户画像列表构建方法、装置、服务器以及存储介质,在当前构建周期内,收集多个用户中的每个用户的用户数据,对每个用户的用户数据进行聚合,获得每个用户在当前构建周期内的用户画像,将每个用户在当前构建周期内的用户画像更新到分布式存储系统中,其中,分布式存储系统包括每个用户在历史构建周期内的用户画像,基于每个用户在当前构建周期内的用户画像和每个用户在历史构建周期内的用户画像,构建每个用户的用户画像列表,从而通过在一定构建周期内收集每个用户的用户数据聚合获得用户画像,并实时更新到分布式存储系统中参与用户画像列表的构建,以提高用户画像列表的更新效率和准确率。
最后应说明的是:以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不驱使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (20)

  1. 一种用户画像列表构建方法,其特征在于,所述方法包括:
    在当前构建周期内,收集多个用户中的每个用户的用户数据;
    对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像;
    将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像;
    基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
  2. 根据权利要求1所述的方法,其特征在于,所述基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表,包括:
    基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,获得所述每个用户的当前用户画像;
    基于所述每个用户的当前用户画像,构建所述每个用户的用户画像列表。
  3. 根据权利要求2所述的方法,其特征在于,所述基于所述每个用户的当前用户画像,构建所述每个用户的用户画像列表,包括:
    基于所述每个用户的当前用户画像,获取所述每个用户的当前基础画像;
    基于所述每个用户的当前基础画像,构建所述每个用户的第一用户画像列表。
  4. 根据权利要求2或3所述的方法,其特征在于,所述基于所述每个用户的当前用户画像,构建所述每个用户的用户画像列表,包括:
    基于所述每个用户的当前用户画像,获取所述每个用户的当前业务画像;
    基于所述每个用户的当前业务画像,构建所述每个用户的第二用户画像列表。
  5. 根据权利要求2-4任一项所述的方法,其特征在于,所述基于所述每个用户的当前用户画像,构建所述每个用户的用户画像列表,包括:
    基于所述每个用户的当前用户画像,获取所述每个用户的当前行为画像;
    基于所述每个用户的当前行为画像,构建所述每个用户的第三用户画像列表。
  6. 根据权利要求1-5任一项所述的方法,其特征在于,所述基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表,包括:
    获取所述每个用户的用户标识;
    基于所述每个用户的用户标识、所述每个用户在所述当前构建周期内的用户画像以及所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
  7. 根据权利要求6所述的方法,其特征在于,所述用户标识包括用户身份标识号码ID。
  8. 根据权利要求1-7任一项所述的方法,其特征在于,所述在当前构建周期内,收集多个用户中的每个用户的用户数据,包括:
    从预设映射关系表中获取所述当前构建周期对应的当前用户数据,其中,所述预设映射关系表包括多个构建周期和多个用户数据的对应关系;
    在所述当前构建周期内,收集所述多个用户中的每个用户的当前用户数据。
  9. 根据权利要求1-8任一项所述的方法,其特征在于,所述基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表之后,还包括:
    当接收到目标用户的业务访问时,从所述用户画像列表中获取所述目标用户的用户画像;
    基于所述目标用户的用户画像,获取与所述目标用户的用户画像对应的待推送内容;
    向所述目标用户推送所述待推送内容。
  10. 根据权利要求9所述的方法,其特征在于,所述当接收到目标用户的业务访问时,从所述用户画像列表中获取所述目标用户的用户画像,包括:
    当接收到所述目标用户的业务访问时,获取所述目标用户的用户标识;
    基于所述目标用户的用户标识,从所述用户画像列表中获取所述目标用户的用户画像。
  11. 根据权利要求9或10所述的方法,其特征在于,所述用户画像列表的数量为多个,且每个用户画像列表对应所述每个用户的不同画像类型,所述当接收到目标用户的业务访问时,从所述用户画像列表中获取所述目标用户的用户画像,包括:
    当接收到所述目标用户的业务访问时,获取所述业务访问的业务类型;
    从所述多个用户画像列表中获取与所述业务类型对应的目标用户画像列表;
    从所述目标用户画像列表中获取所述目标用户的用户画像。
  12. 根据权利要求9-11任一项所述的方法,其特征在于,所述向所述目标用户推送所述待推送内容,包括:
    基于所述目标用户的用户画像,获取向所述目标用户推送所述待推送内容的推送时间;
    基于所述推送时间,向所述目标用户推送所述待推送内容。
  13. 根据权利要求9-12任一项所述的方法,其特征在于,所述向所述目标用户推送所述待推送内容,包括:
    基于所述目标用户的用户画像,获取向所述目标用户推送所述待推送内容的推送次数;
    基于所述推送次数,向所述目标用户推送所述待推送内容。
  14. 根据权利要求9-13任一项所述的方法,其特征在于,所述向所述目标用户推送所述待推送内容,包括:
    基于所述目标用户的用户画像,获取向所述目标用户推送的所述待推送内容排版方式;
    基于所述排版方式,向所述目标用户推送所述待推送内容。
  15. 根据权利要求9-14任一项所述的方法,其特征在于,所述向所述目标用户推送所述待推送内容,包括:
    基于所述目标用户的用户画像,获取与所述目标用户的用户画像匹配的用户作为参考用户;
    获取所述参考用户针对所述待推送内容的转化率作为参考转化率;
    基于所述参考转化率确定向所述目标用户推送所述待推送内容的方式。
  16. 根据权利要求15所述的方法,其特征在于,所述基于所述参考转化率确定向所述目标用户推送所述待推送内容的方式,包括:
    当所述参考转化率大于指定转化率时,向所述目标用户推送所述待推送内容。
  17. 根据权利要求9-14任一项所述的方法,其特征在于,所述向所述目标用户推送所述待推送内容,包括:
    基于所述目标用户的用户画像,获取与所述目标用户的用户画像匹配的用户作为参考用户;
    获取所述参考用户针对所述待推送内容的评分作为参考评分;
    基于所述参考评分确定向所述目标用户推送所述待推送内容的方式。
  18. 一种用户画像列表构建装置,其特征在于,所述装置包括:
    用户数据收集模块,用于在当前构建周期内,收集多个用户中的每个用户的用户数据;
    用户画像获得模块,用于对所述每个用户的用户数据进行聚合,获得所述每个用户在所述当前构建周期内的用户画像;
    用户画像更新模块,用于将所述每个用户在所述当前构建周期内的用户画像更新到分布式存储系统中,其中,所述分布式存储系统包括所述每个用户在历史构建周期内的用户画像;
    用户画像列表构建模块,用于基于所述每个用户在所述当前构建周期内的用户画像和所述每个用户在所述历史构建周期内的用户画像,构建所述每个用户的用户画像列表。
  19. 一种服务器,其特征在于,包括存储器和处理器,所述存储器耦接到所述处理器,所述存储器存储指令,当所述指令由所述处理器执行时所述处理器执行如权利要求1-17任一项所述的方法。
  20. 一种计算机可读取存储介质,其特征在于,所述计算机可读取存储介质中存储有程序代码,所述程序代码可被处理器调用执行如权利要求1-17任一项所述的方法。
PCT/CN2020/082842 2020-04-01 2020-04-01 用户画像列表构建方法、装置、服务器以及存储介质 WO2021196097A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/082842 WO2021196097A1 (zh) 2020-04-01 2020-04-01 用户画像列表构建方法、装置、服务器以及存储介质
CN202080094726.XA CN115004210A (zh) 2020-04-01 2020-04-01 用户画像列表构建方法、装置、服务器以及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/082842 WO2021196097A1 (zh) 2020-04-01 2020-04-01 用户画像列表构建方法、装置、服务器以及存储介质

Publications (1)

Publication Number Publication Date
WO2021196097A1 true WO2021196097A1 (zh) 2021-10-07

Family

ID=77927274

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/082842 WO2021196097A1 (zh) 2020-04-01 2020-04-01 用户画像列表构建方法、装置、服务器以及存储介质

Country Status (2)

Country Link
CN (1) CN115004210A (zh)
WO (1) WO2021196097A1 (zh)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113973087A (zh) * 2021-11-24 2022-01-25 中国银联股份有限公司 一种网页访问限流方法、装置及计算机可读存储介质
CN114157916A (zh) * 2021-12-14 2022-03-08 深圳创维-Rgb电子有限公司 智能电视内容推送方法、智能电视及计算机可读存储介质
CN114745444A (zh) * 2022-04-07 2022-07-12 国网电力科学研究院有限公司 基于5g网络流量分析的调控业务访问控制方法及系统
CN114782764A (zh) * 2022-06-22 2022-07-22 每日互动股份有限公司 一种用户画像的生成方法、装置、计算机设备及存储介质
CN115587853A (zh) * 2022-10-24 2023-01-10 广州易海创腾信息科技有限公司 电子商务与大数据结合的业务画像分析方法及系统
CN115801330A (zh) * 2022-10-26 2023-03-14 国网天津市电力公司 一种电力物联网终端的安全属性画像构建方法
CN117596133A (zh) * 2024-01-18 2024-02-23 山东中测信息技术有限公司 基于多维数据的业务画像及异常监测系统及监测方法
CN117876015A (zh) * 2024-03-11 2024-04-12 南京数策信息科技有限公司 一种用户行为数据分析方法、装置及相关设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4889672B2 (ja) * 2008-04-02 2012-03-07 ヤフー株式会社 広告配信装置、システム及び方法
CN108510321A (zh) * 2018-03-23 2018-09-07 北京焦点新干线信息技术有限公司 一种房产用户画像的构建方法及装置
CN109146539A (zh) * 2018-06-28 2019-01-04 深圳市彬讯科技有限公司 用户画像的更新方法及装置
CN109933727A (zh) * 2019-03-22 2019-06-25 北京博明信德科技有限公司 用户画像生成方法及系统、用户画像应用方法及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4889672B2 (ja) * 2008-04-02 2012-03-07 ヤフー株式会社 広告配信装置、システム及び方法
CN108510321A (zh) * 2018-03-23 2018-09-07 北京焦点新干线信息技术有限公司 一种房产用户画像的构建方法及装置
CN109146539A (zh) * 2018-06-28 2019-01-04 深圳市彬讯科技有限公司 用户画像的更新方法及装置
CN109933727A (zh) * 2019-03-22 2019-06-25 北京博明信德科技有限公司 用户画像生成方法及系统、用户画像应用方法及系统

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113973087A (zh) * 2021-11-24 2022-01-25 中国银联股份有限公司 一种网页访问限流方法、装置及计算机可读存储介质
CN113973087B (zh) * 2021-11-24 2024-01-05 中国银联股份有限公司 一种网页访问限流方法、装置及计算机可读存储介质
CN114157916A (zh) * 2021-12-14 2022-03-08 深圳创维-Rgb电子有限公司 智能电视内容推送方法、智能电视及计算机可读存储介质
CN114157916B (zh) * 2021-12-14 2023-10-24 深圳创维-Rgb电子有限公司 智能电视内容推送方法、智能电视及计算机可读存储介质
CN114745444A (zh) * 2022-04-07 2022-07-12 国网电力科学研究院有限公司 基于5g网络流量分析的调控业务访问控制方法及系统
CN114745444B (zh) * 2022-04-07 2024-05-24 国网电力科学研究院有限公司 基于5g网络流量分析的调控业务访问控制方法及系统
CN114782764A (zh) * 2022-06-22 2022-07-22 每日互动股份有限公司 一种用户画像的生成方法、装置、计算机设备及存储介质
CN114782764B (zh) * 2022-06-22 2022-09-30 每日互动股份有限公司 一种用户画像的生成方法、装置、计算机设备及存储介质
CN115587853B (zh) * 2022-10-24 2024-04-05 广州易海创腾信息科技有限公司 电子商务与大数据结合的业务画像分析方法及系统
CN115587853A (zh) * 2022-10-24 2023-01-10 广州易海创腾信息科技有限公司 电子商务与大数据结合的业务画像分析方法及系统
CN115801330A (zh) * 2022-10-26 2023-03-14 国网天津市电力公司 一种电力物联网终端的安全属性画像构建方法
CN117596133B (zh) * 2024-01-18 2024-04-05 山东中测信息技术有限公司 基于多维数据的业务画像及异常监测系统及监测方法
CN117596133A (zh) * 2024-01-18 2024-02-23 山东中测信息技术有限公司 基于多维数据的业务画像及异常监测系统及监测方法
CN117876015A (zh) * 2024-03-11 2024-04-12 南京数策信息科技有限公司 一种用户行为数据分析方法、装置及相关设备
CN117876015B (zh) * 2024-03-11 2024-05-07 南京数策信息科技有限公司 一种用户行为数据分析方法、装置及相关设备

Also Published As

Publication number Publication date
CN115004210A (zh) 2022-09-02

Similar Documents

Publication Publication Date Title
WO2021196097A1 (zh) 用户画像列表构建方法、装置、服务器以及存储介质
CN106357517B (zh) 定向标签生成方法及装置
CN108415952B (zh) 用户数据存储方法、标签计算方法及计算设备
CN108280115B (zh) 识别用户关系的方法及装置
WO2017101240A1 (zh) 一种信息处理方法及服务器、计算机存储介质
CN107798027B (zh) 一种信息热度预测方法、信息推荐方法及装置
US20160307131A1 (en) Method, apparatus, and system for controlling delivery task in social networking platform
WO2017008322A1 (zh) 基于社交网络行为感知的智能家庭能源管理方法
WO2014121086A2 (en) System and method for dynamic criteria, request-lists, event-lists, and playlists
CN110956505B (zh) 一种广告库存的预估方法以及相关装置
WO2013097714A1 (zh) 一种移动终端上网流量统计分析和提醒的方法和系统
US10657559B2 (en) Generating and utilizing a conversational index for marketing campaigns
CN111143697B (zh) 一种内容推荐的方法以及相关装置
WO2019062342A9 (zh) 后台应用清理方法、装置、存储介质及电子设备
WO2013142823A1 (en) Method and system for predicting words in a message
US20160379122A1 (en) Recommendation algorithm optimization method, device and system
WO2019062405A1 (zh) 应用程序的处理方法、装置、存储介质及电子设备
CN112311612A (zh) 一种家庭画像构建方法、装置及存储介质
CN113412607B (zh) 内容推送方法、装置、移动终端及存储介质
CN110991392A (zh) 人群识别方法、装置、终端及存储介质
WO2020258773A1 (zh) 确定推送用户群的方法、装置、设备及存储介质
CN112035717A (zh) 信息处理方法、装置、设备及存储介质
WO2021142719A1 (zh) 画像生成方法、装置、服务器及存储介质
CN104937613A (zh) 量化数据质量的探试
CN110990706B (zh) 语料推荐方法及装置

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: 20928665

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 13.02.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20928665

Country of ref document: EP

Kind code of ref document: A1