CN111400549B - User portrait processing method and system - Google Patents
User portrait processing method and system Download PDFInfo
- Publication number
- CN111400549B CN111400549B CN202010506109.8A CN202010506109A CN111400549B CN 111400549 B CN111400549 B CN 111400549B CN 202010506109 A CN202010506109 A CN 202010506109A CN 111400549 B CN111400549 B CN 111400549B
- Authority
- CN
- China
- Prior art keywords
- account
- portrait
- processed
- behavior
- behavior data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000012545 processing Methods 0.000 claims description 28
- 238000010276 construction Methods 0.000 claims description 17
- 230000006399 behavior Effects 0.000 abstract description 322
- 238000013507 mapping Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3438—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
Abstract
本发明提供了一种用户画像的处理方法及系统，该方法为：获取预设时间段内待处理设备的第一行为数据和待处理账户的第二行为数据；根据第一行为数据确定待处理设备对应的账户登录行为，以及根据第二行为数据确定待处理账户对应的设备使用行为；利用账户登录行为和第一行为数据，构建待处理设备对应的第一用户画像；利用设备使用行为和第二行为数据，构建待处理账户对应的第二用户画像。本方案中，分别根据待处理设备和待处理账户在预设时间段内的行为数据，确定待处理设备的账户登录行为和确定待处理账户的设备使用行为。分别利用账户登录行为和设备使用行为构建相应的用户画像，使构建的用户画像在多用户多设备的使用场景下更准确的描述用户行为。
The present invention provides a user portrait processing method and system. The method includes: acquiring first behavior data of a device to be processed and second behavior data of an account to be processed within a preset time period; determining the pending behavior data according to the first behavior data The account login behavior corresponding to the device, and the device usage behavior corresponding to the account to be processed is determined according to the second behavior data; the account login behavior and the first behavior data are used to construct the first user portrait corresponding to the device to be processed; The second behavior data is to construct the second user portrait corresponding to the account to be processed. In this solution, the account login behavior of the device to be processed and the device usage behavior of the account to be processed are determined according to the behavior data of the device to be processed and the account to be processed within a preset time period, respectively. Use account login behavior and device usage behavior to construct corresponding user portraits respectively, so that the constructed user portraits can more accurately describe user behaviors in multi-user and multi-device usage scenarios.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a user portrait processing method and system.
Background
With the development of the times, one user may hold a plurality of terminal devices (devices such as a mobile phone and a tablet computer), or a plurality of users may share one terminal device.
When a user logs in an account on a plurality of terminal devices, behavior data of the user is dispersed to different terminal devices, and a user image composed of an account image (image corresponding to the account) and a device image (image corresponding to the terminal devices) cannot accurately describe the user behavior of the user. When a plurality of users log in an account on the same terminal device, behavior data of the plurality of users are concentrated in the terminal device, and dirty data is generated by user portrait.
Therefore, in the usage scenario of the multi-user multi-device, the accuracy of describing the user behavior by the user portrait is low.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and a system for processing a user portrait, so as to solve the problems of low accuracy of describing a user behavior by a user portrait in a multi-user and multi-device usage scenario.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the first aspect of the embodiments of the present invention discloses a method for processing a user portrait, where the method includes:
acquiring first behavior data of a device to be processed and second behavior data of an account to be processed within a preset time period;
determining account login behaviors corresponding to the to-be-processed equipment according to the first behavior data, and determining equipment use behaviors corresponding to the to-be-processed account according to the second behavior data;
constructing a first user portrait corresponding to the equipment to be processed by using the account login behavior and the first behavior data;
and constructing a second user portrait corresponding to the account to be processed by utilizing the equipment using behavior and the second behavior data.
Preferably, the constructing a first user representation corresponding to the device to be processed by using the account login behavior and the first behavior data includes:
determining an account login state corresponding to the equipment to be processed according to the account login behavior;
if the account login state indicates that no account is logged in the equipment to be processed, constructing a first user portrait corresponding to the equipment ID by using behavior data corresponding to the equipment ID of the equipment to be processed in the first behavior data;
if the account login state indicates that a first account is logged in the equipment to be processed, constructing a first user portrait corresponding to the first account by using behavior data corresponding to the first account in the first behavior data;
if the account login state indicates that an account switching behavior occurs in the to-be-processed device, constructing a device portrait corresponding to the device ID by using behavior data corresponding to the device ID in the first behavior data, and constructing an account portrait corresponding to a second account which is logged in the to-be-processed device before the account switching behavior occurs in the first behavior data;
merging the device representation and the account representation to obtain a first user representation;
and if the account login state indicates that an account exit behavior exists in the equipment to be processed, constructing a first user portrait corresponding to the equipment ID by using behavior data corresponding to the equipment ID in the first behavior data.
Preferably, the constructing a second user representation corresponding to the account to be processed by using the device usage behavior and the second behavior data includes:
determining the number of the devices logged in by the account to be processed according to the device using behaviors;
if the number of the devices logged in by the account to be processed is larger than 1, constructing an account image of the account to be processed corresponding to each device according to the behavior data of the account to be processed corresponding to each device in the second behavior data;
and merging the account portrait of the account to be processed corresponding to each device to obtain a second user portrait corresponding to the account to be processed.
Preferably, before the acquiring the first behavior data of the device to be processed and the second behavior data of the account to be processed within the preset time period, the method further includes:
when an account to be processed logs in a device to be processed, determining whether a historical account image corresponding to the account to be processed and a historical device image corresponding to the device to be processed exist in a preset database;
if the historical account portrait and the historical equipment portrait do not exist in the database, copying the historical account portrait, and using the copied historical account portrait as the historical equipment portrait;
and if the historical account portrait and the historical equipment portrait do not exist in the database, copying the historical equipment portrait, and using the copied historical equipment portrait as the historical account portrait.
Preferably, after determining whether the historical account representation corresponding to the account to be processed and the historical device representation corresponding to the device to be processed exist in the preset database, the method further includes:
when the account to be processed generates a viewing behavior and an exposure behavior in the equipment to be processed, determining whether a real-time account image corresponding to the account to be processed and a real-time equipment image corresponding to the equipment to be processed exist in the database, wherein the real-time account image is obtained by updating the historical account image according to behavior data of the viewing behavior and the exposure behavior, and the real-time equipment image is obtained by updating the historical equipment image according to the behavior data of the viewing behavior and the exposure behavior;
if the real-time account image exists in the database and the real-time equipment image does not exist in the database, copying the real-time account image, and taking the copied real-time account image as the real-time equipment image;
and if the real-time account portrait does not exist in the database and the real-time equipment portrait exists in the database, copying the real-time equipment portrait, and taking the copied real-time equipment portrait as the real-time account portrait.
The second aspect of the embodiments of the present invention discloses a system for processing a user portrait, the system comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring first behavior data of equipment to be processed and second behavior data of an account to be processed within a preset time period;
the determining unit is used for determining account login behaviors corresponding to the to-be-processed equipment according to the first behavior data and determining equipment using behaviors corresponding to the to-be-processed account according to the second behavior data;
the first construction unit is used for constructing a first user portrait corresponding to the equipment to be processed by using the account login behavior and the first behavior data;
and the second construction unit is used for constructing a second user portrait corresponding to the account to be processed by utilizing the equipment using behavior and the second behavior data.
Preferably, the first building unit comprises:
the determining module is used for determining the account login state corresponding to the equipment to be processed according to the account login behavior;
the first construction module is used for constructing a first user portrait corresponding to the equipment ID by utilizing the behavior data corresponding to the equipment ID of the equipment to be processed in the first behavior data if the account login state indicates that no account is logged in the equipment to be processed;
the second construction module is used for constructing a first user portrait corresponding to a first account by utilizing behavior data corresponding to the first account in the first behavior data if the account login state indicates that the first account is logged in the device to be processed;
a third construction module, configured to, if the account login status indicates that an account switching behavior occurs in the device to be processed, construct, by using behavior data corresponding to the device ID in the first behavior data, a device representation corresponding to the device ID, and construct, by using behavior data corresponding to a second account, which is logged in the device to be processed before the account switching behavior occurs, an account representation corresponding to the second account in the first behavior data, and execute a merge module;
the merging module is used for merging the equipment portrait and the account portrait to obtain a first user portrait;
and if the account login state indicates that an account quitting behavior exists in the to-be-processed equipment, constructing a first user portrait corresponding to the equipment ID by using the behavior data corresponding to the equipment ID in the first behavior data.
Preferably, the second building element comprises:
the determining module is used for determining the number of the devices logged in by the account to be processed according to the device using behaviors;
the construction module is used for constructing an account image of the account to be processed corresponding to each device according to the behavior data of the account to be processed corresponding to each device in the second behavior data if the number of the devices logged in by the account to be processed is larger than 1;
and the merging module is used for merging the account representation of the account to be processed corresponding to each device to obtain a second user representation corresponding to the account to be processed.
Preferably, the system further comprises:
the image processing device comprises a first image processing unit and a second image processing unit, wherein the first image processing unit is used for determining whether a historical account image corresponding to an account to be processed and a historical device image corresponding to the device to be processed exist in a preset database when the account to be processed is registered in the device to be processed, copying the historical account image if the historical account image exists in the database and the historical device image does not exist in the database, using the copied historical account image as the historical device image, copying the historical device image if the historical account image does not exist in the database and the historical device image exists in the database, and using the copied historical device image as the historical account image.
Preferably, the system further comprises:
the second portrait processing unit is used for determining whether a real-time account portrait corresponding to the account to be processed and a real-time equipment portrait corresponding to the equipment to be processed exist in the database when the account to be processed generates a film watching behavior and an exposure behavior in the equipment to be processed, copying the real-time account portrait if the real-time account portrait exists in the database and the real-time equipment portrait does not exist in the database, and copying the real-time equipment portrait if the real-time account portrait does not exist in the database and the real-time equipment portrait exists in the database and taking the copied real-time equipment portrait as the real-time account portrait;
the real-time account image is obtained by updating the historical account image according to the behavior data of the viewing behavior and the exposure behavior, and the real-time equipment image is obtained by updating the historical equipment image according to the behavior data of the viewing behavior and the exposure behavior.
Based on the above method and system for processing a user portrait provided by the embodiments of the present invention, the method includes: acquiring first behavior data of a device to be processed and second behavior data of an account to be processed within a preset time period; determining account login behaviors corresponding to the to-be-processed equipment according to the first behavior data, and determining equipment use behaviors corresponding to the to-be-processed account according to the second behavior data; constructing a first user portrait corresponding to the equipment to be processed by using the account login behavior and the first behavior data; and constructing a second user portrait corresponding to the account to be processed by using the equipment using behavior and the second behavior data. In the scheme, the account login behavior of the device to be processed and the device use behavior of the account to be processed are determined according to the behavior data of the device to be processed and the account to be processed in the preset time period. Corresponding user portrait is constructed by respectively utilizing account login behaviors and device using behaviors, so that the constructed user portrait can describe user behaviors more accurately in a multi-user multi-device using scene.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flowchart illustrating a method for processing a user representation according to an embodiment of the present invention;
FIG. 2 is a flow diagram of constructing a first user representation according to an embodiment of the present invention;
FIG. 3 is a flow diagram for constructing a second user representation according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a mapping process of a real-time user image according to an embodiment of the present invention;
FIG. 5 is a block diagram of a system for processing a user representation according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
As known from the background art, when a user logs in an account on a plurality of terminal devices, behavior data of the user may be dispersed to different terminal devices, and a user portrait may not accurately describe the user behavior of the user. When an account is logged in on a terminal device, behavior data of a plurality of users can be concentrated in the terminal device, and user portrayal cannot accurately describe user behaviors of the users. Therefore, in the use scene of the multi-user multi-device, the accuracy of describing the user behavior by the user portrait is low.
Therefore, the embodiment of the invention provides a method and a system for processing a user portrait, which respectively determine an account login behavior of a device to be processed and an equipment use behavior of an account to be processed according to behavior data of the device to be processed and the account to be processed within a preset time period. And corresponding user pictures are constructed by respectively utilizing the account login behaviors and the device using behaviors, so that the constructed user pictures can describe the user behaviors more accurately in the use scene of multiple users and multiple devices.
Referring to fig. 1, a flowchart of a processing method for a user portrait according to an embodiment of the present invention is shown, where the processing method includes the following steps:
step S101: the method comprises the steps of obtaining first behavior data of a device to be processed and second behavior data of an account to be processed in a preset time period.
It should be noted that the viewing behavior and the exposure behavior are logs for generating a user portrait, and the exposure behavior is generated when the video is displayed on the screen of the user's device, and the viewing behavior is generated when the duration of the video played by the user is greater than the viewing time threshold.
It is understood that the user records first behavior data corresponding to a device ID (referred to as UID) and second behavior data corresponding to an account identification ID (referred to as passport) when generating the exposure behavior and the viewing behavior.
In the process of implementing step S101 specifically, first behavior data corresponding to the UID of the device to be processed in a preset time period is acquired, and second behavior data corresponding to the account identifier ID of the account to be processed is acquired.
Such as: first behavior data of a device to be processed within one month (within one month before the current time) and second behavior data of an account to be processed are acquired.
Step S102: and determining account login behaviors corresponding to the to-be-processed equipment according to the first behavior data, and determining equipment use behaviors corresponding to the to-be-processed account according to the second behavior data.
In the process of implementing step S102 specifically, according to the first behavior data, account login behaviors in the device to be processed are determined, that is, whether an account is logged in the device to be processed is determined, and how many accounts are logged in the device to be processed is determined.
And determining the device use behavior corresponding to the account to be processed according to the second behavior data, namely determining which device the account to be processed logs in, and determining how many devices the account to be processed logs in.
Step S103: and constructing a first user portrait corresponding to the equipment to be processed by using the account login behavior and the first behavior data.
It can be understood that after the first user portrait is constructed according to the account login behavior and the first behavior data corresponding to the device to be processed, the first user portrait is used for determining recommendation information and displaying the recommendation information to the user.
Such as: a video that needs to be recommended to the user is determined using the first user representation, and the determined video is presented to the user.
Step S104: and constructing a second user portrait corresponding to the account to be processed by using the equipment using behavior and the second behavior data.
It can be understood that after the second user portrait is constructed according to the device usage behavior corresponding to the account to be processed and the second behavior data, the recommendation information is determined by using the second user portrait and is displayed to the user.
It should be noted that the steps S101 to S104 are performed periodically, for example: the above steps S101 to S104 are performed at 23 points per day. After each execution of steps S101 through S104 to obtain a first user representation and a second user representation, the first user representation and the second user representation are applied to determine recommendation information, such as: after the first user representation and the second user representation are obtained at 23 points of each day by executing the steps S101 to S104, the first user representation and the second user representation are applied to determine recommendation information on the next day, and the recommendation information is displayed to the user.
In the embodiment of the invention, the account login behavior of the device to be processed and the device use behavior of the account to be processed are determined according to the behavior data of the device to be processed and the account to be processed in the preset time period. And constructing a first user portrait corresponding to the equipment to be processed according to the account login behavior and the first behavior data, and constructing a second user portrait corresponding to the account to be processed according to the equipment use behavior. And determining recommendation information by using the constructed first user portrait and the second user portrait and displaying the recommendation information to the user, so that the constructed user portrait can describe the user behavior more accurately in the use scene of the multi-user and multi-device.
The process of building a first user representation as described above in step S103 of FIG. 1 in accordance with embodiments of the present invention, and referring to FIG. 2, is a flow chart of building a first user representation as provided in accordance with embodiments of the present invention, including the steps of:
step S201: and determining the account login state corresponding to the equipment to be processed according to the account login behavior.
It should be noted that, in the use process of the device to be processed, the user behavior log reports the behavior data identified by the device ID and reports the behavior data identified by the account ID, that is, the first behavior data includes the behavior data identified by the device ID and the behavior data identified by the account ID.
According to the behavior data (first behavior data) reported by the user behavior log, the account login behavior can be determined.
In the process of implementing step S201 specifically, according to the account login behavior, the account login status corresponding to the device to be processed is determined, for example: determining whether an account logs in the device to be processed, determining whether an account switching behavior exists in the device to be processed, and determining whether an account quitting behavior exists in the device to be processed.
It is to be understood that the above examples of the account login status corresponding to the device to be processed are only used for illustration, and other account login statuses are not necessarily illustrated.
Step S202: and if the account login state indicates that no account is logged in the equipment to be processed, constructing a first user portrait corresponding to the equipment ID by using the behavior data corresponding to the equipment ID of the equipment to be processed in the first behavior data.
In the process of implementing step S202 specifically, if it is determined that no account is logged in the device to be processed according to the account login status, that is, the user does not log in the account in the device to be processed, but directly uses the device to be processed to perform a service operation (the behavior data reported in the use process and identified by the account identifier ID is a null value), and obtains the behavior data corresponding to the device ID of the device to be processed from the first behavior data.
Such as: for a video application software in the device to be processed, the user does not log in an account in the video application software, but directly uses the video application software to browse the video, and the behavior data uploaded in the process of browsing the video is the behavior data with the device ID as the identification.
Behavior data corresponding to the device ID of the device to be processed is obtained according to the first behavior data, and a first user portrait corresponding to the device ID is generated by utilizing big data components (such as hive and spark).
Step S203: and if the account login state indicates that a first account is logged in the equipment to be processed, constructing a first user portrait corresponding to the first account by using behavior data corresponding to the first account in the first behavior data.
In the process of implementing step S203 specifically, when the device to be processed is a new device (there is no user portrait corresponding to the device ID of the device to be processed), and it is determined that there is a first account login in the device to be processed according to the account login state, in order to ensure that the generated user portrait can describe the user behavior of the user more accurately (reflect the user' S preference more accurately), behavior data corresponding to the first account (and the account ID of the first account) is obtained from the first behavior data.
And constructing a first user portrait corresponding to the first account by utilizing the big data component according to the behavior data corresponding to the first account, and using the first user portrait as a user portrait of the device to be processed.
Step S204: if the account login state indicates that an account switching behavior occurs in the device to be processed, constructing a device portrait corresponding to the device ID by using behavior data corresponding to the device ID in the first behavior data, and constructing an account portrait corresponding to a second account registered in the device to be processed before the account switching behavior occurs in the first behavior data.
It should be noted that, when a user uses a device to be processed, a situation that multiple accounts are logged in the same device usually occurs, that is, an account switching behavior occurs in the device to be processed.
In the process of implementing step S204 specifically, if it is determined that an account switching behavior occurs in the device to be processed according to the account login status (the second account is switched to the current account), behavior data corresponding to the device ID of the device to be processed is acquired from the first behavior data, and behavior data corresponding to the second account (passport of the second account) is acquired, that is, behavior data corresponding to the account (the second account) that was logged in the device to be processed before the account switching behavior occurred is acquired from the first behavior data.
And constructing an equipment portrait corresponding to the equipment ID by utilizing the big data component according to the acquired behavior data corresponding to the equipment ID of the equipment to be processed.
And constructing an account portrait corresponding to the second account by using the big data component according to the acquired behavior data corresponding to passport of the second account.
Step S205: the device representation and the account representation are merged to obtain a first user representation.
In the process of implementing step S205 specifically, if it is determined that an account switching behavior occurs in the device to be processed according to the account login status, in order to ensure consistency of the user portrait, the constructed device portrait and the account portrait are merged to obtain a first user portrait corresponding to the device to be processed.
Step S206: and if the account login state indicates that the equipment to be processed has an account exit behavior, constructing a first user portrait corresponding to the equipment ID by using behavior data corresponding to the equipment ID in the first behavior data.
In the process of implementing step S206 specifically, if it is determined that there is an account logout behavior (account logout) in the device to be processed according to the account login status, behavior data corresponding to the device ID of the device to be processed is acquired from the first behavior data.
And constructing a first user portrait corresponding to the equipment ID by utilizing the big data component according to the behavior data corresponding to the equipment ID of the equipment to be processed.
In the embodiment of the invention, the account login state corresponding to the equipment to be processed is determined according to the account login behavior, and corresponding behavior data is obtained from the first behavior data according to the account login state. And generating a first user portrait corresponding to the equipment to be processed by using the acquired behavior data and big data components. The recommendation information is determined through the first user portrait and displayed to the user, so that the constructed user portrait can describe the user behavior more accurately in the use scene of the multi-user and multi-device.
The process of building a second user representation as described above in step S104 of FIG. 1 in accordance with embodiments of the present invention, and referring to FIG. 3, is a flow chart for building a second user representation as provided in accordance with embodiments of the present invention, including the following steps:
step S301: and determining the number of the devices logged in by the account to be processed according to the device using behaviors.
It should be noted that, when the user uses the account to be processed in each device, the user behavior log may report the behavior data corresponding to the device ID of the device and the behavior data corresponding to the account to be processed, that is, according to all the behavior data (i.e., the second behavior data) reported by the user behavior log, which devices the account to be processed logs in (determine the device usage behavior) may be determined.
In the process of implementing step S301 specifically, the number of devices logged in by the account to be processed is determined by using the device usage behavior.
Step S302: and if the number of the devices logged in by the account to be processed is larger than 1, constructing an account portrait of the account to be processed corresponding to each device according to the behavior data of the account to be processed corresponding to each device in the second behavior data.
In the process of implementing step S302 specifically, if the number of devices logged in by the account to be processed is greater than 1 (one user logs in an account on multiple devices), that is, the behavior data of the account to be processed is dispersed to different devices, the behavior data of the account to be processed corresponding to each device (the device logged in by the account to be processed) is obtained from the second behavior data.
And aiming at each device, constructing an account portrait of the account to be processed corresponding to the device by utilizing the big data component according to the behavior data of the account to be processed corresponding to the device.
Step S303: and combining the account pictures of the accounts to be processed corresponding to each device to obtain a second user picture corresponding to the accounts to be processed.
In the process of implementing step S303, since the behavior data of the account to be processed is distributed to a plurality of different devices, in order to ensure that the generated user representation (second user representation) of the account to be processed describes the user behavior more accurately, the account representations of the account to be processed corresponding to each device are merged to obtain the second user representation corresponding to the account to be processed.
In the embodiment of the invention, if the account to be processed is logged in a plurality of devices, the account image of the account to be processed corresponding to each device is constructed according to the behavior data of the account to be processed corresponding to each device. And combining the account portrait of the account to be processed corresponding to each device to obtain a second user portrait corresponding to the account to be processed, determining recommendation information through the second user portrait and displaying the recommendation information to the user, so that the constructed user portrait can describe user behaviors more accurately in the use scene of multiple users and multiple devices.
Preferably, before step S101 is executed (before the first user image and the second user image are not constructed), recommendation information needs to be determined according to the acquired historical account image corresponding to the account to be processed and/or the historical device image corresponding to the device to be processed, and how to acquire the historical account image and/or the historical device image is described in detail below:
referring to fig. 4, a flowchart of mapping a real-time user image provided by the embodiment of the present invention is shown, including the following steps:
step S401: when the account to be processed logs in the equipment to be processed, whether a historical account image corresponding to the account to be processed and a historical equipment image corresponding to the equipment to be processed exist in a preset database or not is determined.
In the process of implementing step S401 specifically, when the account to be processed logs in the device to be processed, it is determined whether a historical account image corresponding to the account to be processed exists in a preset database (e.g., a redis database), and it is determined whether a historical device image corresponding to the device to be processed exists in the database.
It should be noted that, since the data stored in the redis database has an expiration time (for example, the data in the redis database may expire after 1 day), the historical portraits (the historical account portraits and/or the historical device portraits) are loaded in the redis database in advance from the hbase database.
Step S402: if the historical account representation exists in the database and the historical device representation does not exist in the database, the historical account representation is copied, and the copied historical account representation is used as the historical device representation.
In the specific implementation step S402, if the historical account image exists in the database but the historical device image does not exist, that is, the pending account is registered on another device and a corresponding image is generated, the historical account image is copied to the image of the pending device, that is, the copied historical account image is used as the historical device image of the pending device, so as to implement mapping between the historical account image and the historical device image.
Step S403: if the historical account representation and the historical equipment representation do not exist in the database, the historical equipment representation is copied, and the copied historical equipment representation is used as the historical account representation.
In the process of implementing step S403 specifically, if there is no historical account image but there is a historical device image in the database, the historical device image is copied to the image of the account to be processed, that is, the copied historical device image is taken as the historical account image of the account to be processed.
It will be appreciated that if historical account representations and historical device representations are present in the database, the historical account representations and historical device representations may be utilized directly.
After the mapping of the historical account portrait and the historical equipment portrait is completed, when a user generates a viewing behavior and an exposure behavior, the historical account portrait is updated (updated by algorithms such as accumulation and attenuation) according to behavior data of the viewing behavior and the exposure behavior to obtain a real-time portrait, the historical equipment portrait is updated according to the behavior data of the viewing behavior and the exposure behavior to obtain a real-time equipment portrait, and recommendation information is determined by the real-time account portrait and the real-time equipment portrait and displayed to the user.
It can be understood that if no historical account portrait and no historical device portrait exist in the database, a real-time device portrait and a real-time account portrait are generated according to behavior data of the viewing behavior and the exposure behavior, and recommendation information is determined and displayed to a user by using the real-time account portrait and the real-time device portrait.
It is noted that the real-time device representation and the real-time account representation are generated by a distributed real-time computing framework, such as storm.
Preferably, when an abnormality occurs in the network (for example, an abnormal situation such as network interruption and network disconnection), uploading of the real-time account representation or the real-time device representation may fail, that is, the network abnormality may cause the real-time account representation to be absent in the account to be processed or cause the real-time device representation to be absent in the device to be processed.
In order to ensure that the account to be processed has a corresponding real-time account image and the equipment to be processed has a corresponding real-time equipment image, when the account to be processed generates a viewing behavior and an exposure behavior in the equipment to be processed, whether a real-time account image corresponding to the account to be processed and a real-time equipment image corresponding to the equipment to be processed exist in the database or not is determined. The real-time account image is obtained by updating the historical account image according to the behavior data of the viewing behavior and the exposure behavior, and the real-time equipment image is obtained by updating the historical equipment image according to the behavior data of the viewing behavior and the exposure behavior.
If the real-time account image exists in the database and the real-time equipment image does not exist in the database, copying the real-time account image, and taking the copied real-time account image as the real-time equipment image;
and if the real-time account image does not exist in the database and the real-time equipment image exists in the database, copying the real-time equipment image, and taking the copied real-time equipment image as the real-time account image.
If the real-time account image and the real-time equipment image exist in the database, the real-time account image and the real-time equipment image can be directly utilized.
And if the real-time account image and the real-time equipment image do not exist in the database, generating a real-time equipment portrait and a real-time account portrait according to the behavior data of the viewing behavior and the exposure behavior.
In the embodiment of the invention, when the account to be processed logs in the equipment to be processed, the mapping between the historical equipment portrait and the historical account portrait is completed according to the data stored in the database, the historical equipment portrait and the historical account portrait are respectively updated according to the behavior data of the viewing behavior and the exposure behavior, the real-time equipment portrait and the real-time account portrait are obtained, the recommendation information is determined according to the real-time equipment portrait and the real-time account portrait and is displayed to the user, the determined recommendation information is more suitable for the preference of the user, and the use experience of the user is improved. When the account to be processed generates a viewing behavior and an exposure behavior in the equipment to be processed, whether the real-time account portrait and the real-time equipment portrait exist or not is further determined, mapping of the real-time account portrait and the real-time equipment portrait is completed, it is guaranteed that recommendation information can be determined according to the real-time equipment portrait and the real-time account portrait and displayed to a user, and use experience of the user is improved.
Corresponding to the method for processing a user portrait provided by the above embodiment of the present invention, referring to fig. 5, an embodiment of the present invention further provides a block diagram of a system for processing a user portrait, where the system includes: an acquisition unit 501, a determination unit 502, a first construction unit 503, and a second construction unit 504;
the acquiring unit 501 is configured to acquire first behavior data of a device to be processed and second behavior data of an account to be processed within a preset time period.
The determining unit 502 is configured to determine an account login behavior corresponding to the to-be-processed account according to the first behavior data, and determine a device usage behavior corresponding to the to-be-processed account according to the second behavior data.
The first construction unit 503 is configured to construct a first user representation corresponding to the device to be processed, using the account login behavior and the first behavior data.
A second constructing unit 504, configured to construct a second user representation corresponding to the account to be processed by using the device usage behavior and the second behavior data.
In the embodiment of the invention, the account login behavior of the device to be processed and the device use behavior of the account to be processed are determined according to the behavior data of the device to be processed and the account to be processed in the preset time period. And constructing a first user portrait corresponding to the equipment to be processed according to the account login behavior and the first behavior data, and constructing a second user portrait corresponding to the account to be processed according to the equipment use behavior. And determining recommendation information by using the constructed first user portrait and the second user portrait and displaying the recommendation information to the user, so that the constructed user portrait can describe the user behavior more accurately in the use scene of the multi-user and multi-device.
Preferably, in conjunction with what is shown in fig. 5, the first building unit 503 includes: the system comprises a determining module, a first constructing module, a second constructing module, a third constructing module, a merging module and a fourth constructing module, wherein the execution principle of each module is as follows:
and the determining module is used for determining the account login state corresponding to the equipment to be processed according to the account login behavior.
And the first construction module is used for constructing a first user portrait corresponding to the equipment ID by utilizing the behavior data corresponding to the equipment ID of the equipment to be processed in the first behavior data if the account login state indicates that no account is logged in the equipment to be processed.
And the second construction module is used for constructing a first user portrait corresponding to the first account by utilizing the behavior data corresponding to the first account in the first behavior data if the account login state indicates that the first account is logged in the equipment to be processed.
And the third construction module is used for constructing an equipment portrait corresponding to the equipment ID by utilizing the behavior data corresponding to the equipment ID in the first behavior data and constructing an account portrait corresponding to a second account registered in the equipment to be processed before the account switching behavior occurs in the first behavior data if the account registration state indicates that the account switching behavior occurs in the equipment to be processed, and executing the merging module.
And the merging module is used for merging the equipment portrait and the account portrait to obtain a first user portrait.
And the fourth construction module is used for constructing the first user portrait corresponding to the equipment ID by utilizing the behavior data corresponding to the equipment ID in the first behavior data if the account login state indicates that the equipment to be processed has an account exit behavior.
In the embodiment of the invention, the account login state corresponding to the equipment to be processed is determined according to the account login behavior, and corresponding behavior data is obtained from the first behavior data according to the account login state. And generating a first user portrait corresponding to the equipment to be processed by using the acquired behavior data and big data components. The recommendation information is determined through the first user portrait and displayed to the user, so that the constructed user portrait can describe the user behavior more accurately in the use scene of the multi-user and multi-device.
Preferably, in conjunction with what is shown in fig. 5, the second building unit 504 includes: the method comprises a determining module, a constructing module and a combining module, wherein the execution principle of each module is as follows:
and the determining module is used for determining the number of the devices logged in by the account to be processed according to the device using behaviors.
And the construction module is used for constructing an account portrait of the account to be processed corresponding to each device according to the behavior data of the account to be processed corresponding to each device in the second behavior data if the number of the devices logged in by the account to be processed is larger than 1.
And the merging module is used for merging the account portrait of the account to be processed corresponding to each device to obtain a second user portrait corresponding to the account to be processed.
In the embodiment of the invention, if the account to be processed is logged in a plurality of devices, the account image of the account to be processed corresponding to each device is constructed according to the behavior data of the account to be processed corresponding to each device. And combining the account portrait of the account to be processed corresponding to each device to obtain a second user portrait corresponding to the account to be processed, determining recommendation information through the second user portrait and displaying the recommendation information to the user, so that the constructed user portrait can describe user behaviors more accurately in the use scene of multiple users and multiple devices.
Preferably, in conjunction with the content shown in fig. 5, the processing system further comprises:
the image processing device comprises a first image processing unit and a second image processing unit, wherein the first image processing unit is used for determining whether a historical account image corresponding to an account to be processed and a historical device image corresponding to a device to be processed exist in a preset database when the account to be processed is registered in the device to be processed, copying the historical account image if the historical account image and the historical device image exist in the database, using the copied historical account image as the historical device image, and copying the historical device image if the historical account image and the historical device image do not exist in the database, and using the copied historical device image as the historical account image.
Preferably, in conjunction with the content shown in fig. 5, the processing system further comprises:
the second portrait processing unit is used for determining whether a real-time account portrait corresponding to the account to be processed and a real-time equipment portrait corresponding to the equipment to be processed exist in the database or not when the account to be processed generates a film watching behavior and an exposure behavior in the equipment to be processed, copying the real-time account portrait if the real-time account portrait exists in the database and the real-time equipment portrait does not exist in the database, copying the real-time equipment portrait if the real-time account portrait does not exist in the database and the real-time equipment portrait exists in the database, and using the copied real-time equipment portrait as the real-time account portrait;
the real-time account image is obtained by updating the historical account image according to the behavior data of the viewing behavior and the exposure behavior, and the real-time equipment image is obtained by updating the historical equipment image according to the behavior data of the viewing behavior and the exposure behavior.
In the embodiment of the invention, when the account to be processed logs in the equipment to be processed, the mapping between the historical equipment portrait and the historical account portrait is completed according to the data stored in the database, the historical equipment portrait and the historical account portrait are respectively updated according to the behavior data of the viewing behavior and the exposure behavior, the real-time equipment portrait and the real-time account portrait are obtained, the recommendation information is determined according to the real-time equipment portrait and the real-time account portrait and is displayed to the user, the determined recommendation information is more suitable for the preference of the user, and the use experience of the user is improved. When the account to be processed generates a viewing behavior and an exposure behavior in the equipment to be processed, whether the real-time account portrait and the real-time equipment portrait exist or not is further determined, mapping of the real-time account portrait and the real-time equipment portrait is completed, it is guaranteed that recommendation information can be determined according to the real-time equipment portrait and the real-time account portrait and displayed to a user, and use experience of the user is improved.
In summary, embodiments of the present invention provide a method and a system for processing a user portrait, which respectively determine an account login behavior of a device to be processed and an apparatus use behavior of an account to be processed according to behavior data of the device to be processed and the account to be processed within a preset time period. Corresponding user portrait is constructed by respectively utilizing account login behaviors and device using behaviors, so that the constructed user portrait can describe user behaviors more accurately in a multi-user multi-device using scene.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506109.8A CN111400549B (en) | 2020-06-05 | 2020-06-05 | User portrait processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010506109.8A CN111400549B (en) | 2020-06-05 | 2020-06-05 | User portrait processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111400549A CN111400549A (en) | 2020-07-10 |
| CN111400549B true CN111400549B (en) | 2021-02-02 |
Family
ID=71435779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010506109.8A Active CN111400549B (en) | 2020-06-05 | 2020-06-05 | User portrait processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111400549B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580005B (en) * | 2020-12-23 | 2024-05-24 | 北京通付盾人工智能技术有限公司 | Mobile terminal user behavior acquisition method and system based on biological probe technology |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10057227B1 (en) * | 2015-03-27 | 2018-08-21 | Amazon Technologies, Inc. | Determination of authentication mechanism |
| CN105224623B (en) * | 2015-09-22 | 2019-06-18 | 北京百度网讯科技有限公司 | The training method and device of data model |
| CN108876434B (en) * | 2018-05-24 | 2022-08-16 | 北京五八信息技术有限公司 | User portrait construction method and device, computing device and readable storage medium |
| CN109658129A (en) * | 2018-11-22 | 2019-04-19 | 北京奇虎科技有限公司 | A kind of generation method and device of user's portrait |
| CN109670112A (en) * | 2018-12-20 | 2019-04-23 | 北京城市网邻信息技术有限公司 | A kind of generation method, device, storage medium and the terminal of user's portrait ID |
-
2020
- 2020-06-05 CN CN202010506109.8A patent/CN111400549B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111400549A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9172918B2 (en) | Systems and methods for managing live video data | |
| CN105025189B (en) | The control method of communication system, image processing apparatus and image processing apparatus | |
| US11930499B2 (en) | Network monitoring in service enabler architecture layer (SEAL) | |
| US9979880B2 (en) | Systems and methods for gesture-based control of equipment in video communication | |
| KR20170063793A (en) | Session history horizon control | |
| CN114422460A (en) | Method and system for establishing same-screen communication sharing in instant messaging application | |
| CN114817698B (en) | Information push method and device, information display method and device, equipment and medium | |
| CN111105521A (en) | Data reading method and device | |
| CN111400549B (en) | User portrait processing method and system | |
| JP2017527904A (en) | System and method for receiving image processing | |
| CN109299048A (en) | The method for handling data and issuing data | |
| CN110149219B (en) | Shooting equipment configuration method and device | |
| CN105898596B (en) | Direct broadcasting room display control method and device | |
| KR101403783B1 (en) | Virtual space providing system for distinct step of application execution | |
| CN115412682B (en) | Video carousel method, device, computer equipment and storage medium | |
| CN112804098B (en) | Domain name fault line switching method and device, terminal equipment and storage medium | |
| CN103873890A (en) | Flow control method and system for shooting software | |
| KR102271571B1 (en) | MEDIA SERVER FOR PROVIDING webRTC-BASED VIDEO CHATTING SERVICE AND SYSTEM THEREOF | |
| JP6667146B2 (en) | Server and calling method | |
| CN105337778A (en) | Internet of Things event-driven service management system | |
| US20200053426A1 (en) | Method and system for managing content distribution | |
| JP5854562B2 (en) | Server and server login method | |
| KR101344062B1 (en) | The system and method access ip camera using internet messenger and mobile messenger | |
| CN116419036A (en) | Method and device for realizing Android TV background application receiving event | |
| CN107133291A (en) | A kind of method and apparatus of content of pages displaying |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |