WO2020000207A1 - 用户兴趣采集方法、装置、计算机装置及计算机可读存储介质 - Google Patents

用户兴趣采集方法、装置、计算机装置及计算机可读存储介质 Download PDF

Info

Publication number
WO2020000207A1
WO2020000207A1 PCT/CN2018/092936 CN2018092936W WO2020000207A1 WO 2020000207 A1 WO2020000207 A1 WO 2020000207A1 CN 2018092936 W CN2018092936 W CN 2018092936W WO 2020000207 A1 WO2020000207 A1 WO 2020000207A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
interest information
behavior data
interest
information
Prior art date
Application number
PCT/CN2018/092936
Other languages
English (en)
French (fr)
Inventor
范春林
赵福均
邓仁坚
Original Assignee
深圳市爱的网络科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市爱的网络科技有限公司 filed Critical 深圳市爱的网络科技有限公司
Priority to PCT/CN2018/092936 priority Critical patent/WO2020000207A1/zh
Publication of WO2020000207A1 publication Critical patent/WO2020000207A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/40Data acquisition and logging

Definitions

  • the present invention belongs to the technical field of data processing, and in particular, to a user interest collection method, device, computer device, and computer-readable storage medium.
  • An embodiment of the present invention provides a user interest collection method, which aims to solve the problems of inaccurate user interest determination and low recommendation efficiency.
  • An embodiment of the present invention provides a user interest collection method, including the following steps:
  • [0009] determine at least one user interest information corresponding to the user behavior data according to the user behavior data, and score the user interest information according to a correspondence relationship between a preset scoring rule and the user behavior data;
  • An embodiment of the present invention provides a user interest collection device, including:
  • a user behavior data collection unit configured to collect user behavior data
  • a scoring unit configured to determine at least one user interest information corresponding to the user behavior data according to user behavior data, and perform user interest information according to a correspondence relationship between a preset scoring rule and the user behavior data Score
  • the user's actual interest information determination unit is configured to perform statistics on the score of the user's interest information, obtain a score value corresponding to the user's interest information, and determine the user's actual interest information according to the score value.
  • An embodiment of the present invention further provides a computer device, where the computer device includes: a processor configured to implement the steps of the user interest collection method described above when executing a computer program stored in a memory.
  • An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the steps of the user interest collection method described above.
  • the behavior data of the user is collected; according to the behavior data of the user, at least user interest information corresponding to the behavior data of the user is determined, and a relationship between the preset scoring rule and the behavior data of the user is determined according to the behavior data of the user.
  • scoring the user's interest information statistics the scoring of the user's interest information, obtain the score value corresponding to the user's interest information, and determine the user's actual interest information according to the score value.
  • the user's actual interest information is determined, referring to the user's attention, likes, and browsing time, etc., the user's interest is determined more accurately, so that the content can be more effectively recommended to the user based on the user's interest in the future, and the effectiveness of the recommendation technology is improved.
  • FIG. 1 is a schematic flowchart of a user interest collection method according to a first embodiment of the present invention
  • FIG. 2 is an implementation flowchart of a method for determining actual user interest information provided in Embodiment 2 of the present invention
  • FIG. 3 is a schematic structural diagram collected by a user interest collection device provided in Embodiment 3 of the present invention.
  • FIG. 4 is a schematic structural diagram of a user actual interest information determining unit provided in Embodiment 4 of the present invention.
  • the actual interest information of the user is determined by collecting the user's behavior data, and by using the user's behavior data and a preset scoring rule.
  • the user's actual interest information is determined, referring to the user's attention, likes, and browsing time, and other factors, the user's interest determination is more accurate, so that the subsequent content can be more effectively recommended for the user based on the user's interest, which improves the effectiveness of the recommendation technology.
  • a first embodiment of the present invention provides a schematic flowchart of a user interest collection method, which is described in detail as follows.
  • the user interest collection method includes, but is not limited to, the following steps:
  • S101 Collect behavior data of a user.
  • the behavior data of the user may include behavior data such as the user paying attention, liking, or unfollowing a web page, or browsing the web page when browsing a social networking page (such as Weibo), or when the user watches a video, Behavior data such as frequency and duration of watching a certain program;
  • the behavior data of the user may also include behavior data such as the usage time, duration, or frequency of the user using an application in the terminal.
  • user behavior data may be collected through a cloud server or a client running on a terminal of Android operating system, iOS operating system, Windows operating system, or other operating systems.
  • the terminal It may include, for example, a mobile phone, a mobile computer, a tablet computer, a Personal Digital Assistant (PDA), and the like.
  • the user when the user behavior data is collected by the client running on the terminal, the user can browse information such as news, videos, etc. posted on the client.
  • the client can collect behavior data such as the user's attention, like, or unfollowing, or the time spent browsing the webpage when browsing the webpage; or, the client can also collect behavior data such as the frequency and duration when the user watches the video.
  • S102 Determine at least one user interest information corresponding to the user behavior data according to user behavior data, and perform the user interest information on the user interest information according to a correspondence relationship between a preset scoring rule and the user behavior data. score.
  • the preset scoring rule is that different behavior data corresponds to different scores. For example, when the user's behavior data is likes, one point can be added. When the user's behavior data is When following, you can The score is 2 points. When the user's behavior data is unfollowing, the score can be reduced by 2 points.
  • the article browsed by the user, the video watched, etc. can be divided into different types, such as entertainment, life, sports, etc., according to the behavior of the user on different types of articles or videos (Such as follow, like, unfollow or browse, etc.) can determine the user's interest information.
  • the interest information of the user may be information such as entertainment, sports, and news.
  • the behavior data of the user may be the length of time that the user browses articles or videos on different webpages, and the user interest information may be scored according to a correspondence between a preset score and the length of time the user browses.
  • the web pages Al, A2, and A3 belong to the entertainment section
  • the web pages Bl, B2, and B3 belong to the technology section
  • the web pages Cl and C2 belong to the game section.
  • the preset correspondence between the ratings and the user browsing time is:
  • the browsing time is Omin- A score of 1 Omin corresponds to 1 point
  • a browsing time of 10min-20min corresponds to 2 points.
  • the behavior data of the user may be a follow, like, or unfollow webpage
  • the user interest collecting device may set a relationship between the above behavior and a score to score the user interest information.
  • a relationship between behaviors and scores shown in Table 1 users can add 1 point to webpages that they follow, 2 points for like pages, and 1 point for canceling followers.
  • the user interest collecting device collects the user's following web page A1, following web page B1, like web page B2, like web page C1, following the above, the web page A1 belongs to the entertainment section, and the web pages Bl, B2 belong to the technology section,
  • the webpage Cl belongs to the game section, the user interest collecting device can determine that the user's interest information is entertainment, technology, and games, and the user's interest information is entertainment rating statistics.
  • the score is 1 point corresponding to the following webpage A1.
  • the user interest information may also be determined according to the content browsed by the user.
  • keywords of browsing content information may be extracted according to content information browsed by the user, and user interest information corresponding to user behavior data may be determined according to the keywords.
  • the user's interest information can be directly determined based on the tag. For example, if the tag of the content browsed by the user is entertainment, the user's interest information can be directly determined as entertainment; If the content information browsed by the user does not have tags, the keywords in the browsed content can be extracted to determine the user's interest information. For example, if the content browsed by the user has "movie premiere", it can be determined that the user's interest information is entertainment. Wait.
  • S103 Perform statistics on the scores of the user interest information, obtain a score value corresponding to the user interest information, and determine actual user interest information according to the score value.
  • the user interest information with a score higher than a preset threshold is the user ’s actual interest information; or, the user interest information with the highest score may be determined as the user ’s actual interest information, etc. I will not repeat them here.
  • FIG. 2 shows an implementation flow of a method for determining actual interest information of a user provided in Embodiment 2 of the present invention, which is similar to Embodiment 1, except that the statistics on the scores of the user's interest information are counted.
  • Obtaining a score value corresponding to the user interest information, and determining actual user interest information according to the score value includes:
  • step S210 statistics are performed on the scores of the user interest information to obtain score values corresponding to the user interest information.
  • step S220 user interest information with a score value higher than a preset threshold is obtained.
  • the preset threshold may be a specific score value, for example, 80 points, 90 points, etc., and may be specifically set according to actual conditions, which is not limited in the embodiment of the present invention.
  • the score corresponding to the user's interest information is counted, and user interest information whose score value is higher than a preset threshold is obtained.
  • the user's interest information is entertainment, 80 points, and sports 60 points.
  • the preset threshold is 70 points, and the user's interest information is entertainment.
  • a score of the user's interest information within a preset time can be counted, for example, within one month, within six months, within three months, etc., specifically, It is set according to actual conditions, and the present invention is not limited.
  • step S230 the actual interest information of the user is determined according to the user interest information whose score value is higher than a preset threshold.
  • the user interest collecting device may determine that the user interest information with a score higher than a preset threshold is the user's actual interest information.
  • the behavior data of the user may further include behavior data such as a usage time, a usage duration, or a usage frequency of the user using an application in the terminal
  • the user interest collecting device is a terminal.
  • the terminal collects behavior data such as the usage time of a user's use of an application, and from all the applications used (which can be understood as the user's interest information), determines that the usage time is relatively short, the usage time is long, or the usage frequency is relatively Large applications serve as users' actual interest information.
  • the terminal may also place the determined actual interest information of the user, that is, the icon of the corresponding application, at a specific position on the main interface of the terminal, for example, on the bottom tray of the main interface of the terminal, or
  • the specific folder set by the user is medium to make it easier for the user to find the icon next time.
  • a user uses applications A, B, and C, where the frequencies of using applications A, B, and C are 10 times / day, 6 times / day, and 2 times / day, and the preset use frequency threshold is 5 times / day.
  • the terminal can determine applications A and B that are used more frequently than the preset usage frequency as the user's actual interest information, and can also place applications A and B in the bottom tray of the terminal's main interface.
  • an embodiment of the present invention further provides a user interest collection device, which can be applied to the foregoing method embodiments.
  • FIG. 3 it is a schematic structural diagram of a user interest collection device 300 provided in Embodiment 3 of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown.
  • the user interest collecting device 300 includes: a user behavior data collecting unit 31, a scoring unit 32, and a user actual interest information determining unit 33.
  • a user behavior data collection unit 31 configured to collect user behavior data
  • the behavior data of the user may include behavior data such as the user paying attention, liking, or unfollowing a certain webpage, or browsing the webpage when browsing a social networking page (such as Weibo), or when the user watches a video, Behavior data such as frequency and duration of watching a certain program;
  • the behavior data of the user may also include behavior data such as the usage time, duration, or frequency of the user using an application in the terminal.
  • user behavior data may be collected through a cloud server or a client running on a terminal of Android operating system, iOS operating system, Windows operating system, or other operating systems.
  • the terminal It may include, for example, a mobile phone, a mobile computer, a tablet computer, a Personal Digital Assistant (PDA), and the like.
  • PDA Personal Digital Assistant
  • the user may browse information such as news, videos, etc. posted on the client.
  • the client can collect behavior data such as the user's attention, like, or unfollowing, or the time spent browsing the webpage when browsing the webpage; or, the client can also collect behavior data such as the frequency and duration when the user watches the video.
  • a scoring unit 32 configured to determine at least one user interest information corresponding to the user behavior data according to the user's behavior data, and according to a correspondence relationship between a preset scoring rule and the user's behavior data, to the user interest information Scoring.
  • the preset scoring rule is that different behavior data correspond to different score values, such as When the user's behavior data is like, you can add 1 point, when the user's behavior data is attention, you can add 2 points, and when the user's behavior data is unfollow, you can reduce 2 points.
  • articles browsed by a user, videos watched by the user and the like can be divided into different types, such as entertainment, life, sports, and other types, according to the behavior of the user on different types of articles or videos ( (Such as follow, like, unfollow or browse, etc.) can determine the user's interest information.
  • the user's interest information may be information such as entertainment, sports, and news.
  • the scoring unit is further configured to score user interest information according to a preset correspondence between a predetermined score and a browsing duration of the user.
  • the user's behavior data may be the length of time that the user browses articles or videos on different webpages
  • the user interest information may be scored according to the correspondence between the preset score and the length of time the user browses.
  • the web pages Al, A2, and A3 belong to the entertainment section
  • the web pages Bl, B 2, and B3 belong to the technology section
  • the web pages Cl and C2 belong to the game section.
  • the preset correspondence between the rating and the user's browsing time is:
  • the browsing time is Omin
  • the score corresponding to -lOmin is 1 point
  • the browsing duration is 10mi.
  • the score corresponding to 20min is 2 points. If the user interest acquisition device browses the web pages Al, B1, and B2, and the browsing durations are Omin-lOmin, Omin-lOmin, and 10min-20min, respectively, the webpage A1 belongs to the entertainment section, and the webpages B1 and B2 belong to the technology section.
  • the behavior data of the user may be a follow, like, or unfollow webpage
  • the user interest collection device may set a relationship between the above behavior and a score to score the user interest information.
  • a relationship between behaviors and scores shown in Table 1 users can add 1 point to webpages that they follow, 2 points for like pages, and 1 point for canceling followers.
  • the user interest acquisition device collects the user attention page A1, the attention page B1, the like page B2, and the like page C1, following the above, the page A1 belongs to the entertainment section, the pages Bl, B2 belong to the technology section, and the page C1 Belonging to the game section, the user interest collection device can determine that the user's interest information is entertainment, technology, and games, and the user's interest information is entertainment rating statistics.
  • the score is 1 point corresponding to the attention page A1, and the user interest information technology score
  • the scoring unit includes:
  • a browsing content information determining unit configured to determine browsing content information according to user behavior data
  • a keyword extraction unit configured to extract keywords for browsing content information
  • the user interest information determining unit is configured to determine at least one behavior related to the user according to the keyword.
  • the content browsed by the user may be determined, and the user interest information is further determined.
  • keywords of browsing content information may be extracted according to content information browsed by the user, and user interest information corresponding to user behavior data may be determined according to the keywords.
  • the user's interest information can be directly determined according to the tag. For example, if the tag of the content browsed by the user is entertainment, the user's interest information can be directly determined as entertainment; If the content information browsed by the user does not have tags, the keywords in the browsed content can be extracted to determine the user's interest information. For example, if the content browsed by the user has "movie premiere", it can be determined that the user's interest information is entertainment. Wait.
  • the user actual interest information determining unit 33 is configured to perform statistics on the scores of the user interest information, obtain a score value corresponding to the user interest information, and determine the user's actual interest information according to the score value.
  • the user interest collecting device may determine that the user interest information with a score higher than a preset threshold is the user ’s actual interest information; or may determine the user interest information with the highest score as the user The actual interest information, etc., will not be repeated here.
  • FIG. 4 shows a structure of a user actual interest information determining unit 33 according to a fourth embodiment of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown.
  • the user actual interest information determining unit 33 includes:
  • a statistics module 33 configured to perform statistics on the scores of user interest information, and obtain score values corresponding to the user interest information
  • the user interest information acquisition module 332 is configured to acquire user interest information with a score value higher than a preset threshold.
  • the preset threshold may be a specific score value, for example, 80 points, 90 points, etc., and may be specifically set according to actual conditions, which is not limited in the embodiment of the present invention.
  • the scores of the user's interest information are counted, and the user interest information whose score value is higher than a preset threshold is obtained.
  • the user's interest information is entertainment, 80 points, and sports 60 points.
  • the preset threshold is 70 points, and the user's interest information is entertainment.
  • a score of the user's interest information within a preset time can be counted, for example, within one month, within six months, within three months, etc., specifically, It is set according to actual conditions, and the present invention is not limited.
  • the user actual interest information determining module 333 is configured to determine the user's actual interest information according to the user interest information whose score value is higher than a preset threshold.
  • the user interest information with a score higher than a preset threshold is the user ’s actual interest information.
  • An embodiment of the present invention further provides a computer device including a processor.
  • the processor is configured to implement the steps of the user interest information collection method provided by the foregoing method embodiments when executing a computer program stored in a memory.
  • An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program / Instructions, when the computer program / instruction is executed by the processor, implements the steps of the new method for collecting user interests provided by the foregoing method embodiments.
  • the computer program may be divided into one or more modules, and one or more modules are stored in a memory and executed by a processor to complete the present invention.
  • One or more modules may be a series of computer program instruction segments capable of performing a specific function, and the instruction segments are used to describe a computer program execution process in a computer device.
  • the computer program may be divided into steps of a user interest information collection method provided by the foregoing method embodiments.
  • the above description of the computer device is merely an example, and does not constitute a limitation on the computer device, and may include more or less components than the above description, or combine some components, or different
  • the components may include, for example, input / output devices, network access devices, and buses.
  • the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSPs), and application specific integrated circuits (ASICs). ), Ready-made programmable gate array
  • the general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc.
  • the processor is a control center of the computer device and connects various parts of the entire user terminal by using various interfaces and lines.
  • the memory may be configured to store the computer program and / or module, and the processor may implement the computer program and / or module stored in the memory by running or executing, and calling data stored in the memory to implement Various functions of the computer device.
  • the memory may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, at least one application required by a function (such as a sound playback function, an image playback function, etc.), etc .; the storage data area may store Data (such as audio data, phone book, etc.) created based on the use of the phone.
  • the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, an internal memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), and a secure digital (SD) card.
  • a non-volatile memory such as a hard disk, an internal memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), and a secure digital (SD) card.
  • a Flash Card at least one disk storage device, a flash memory device, or other volatile solid-state storage device.
  • the modules / units integrated in the computer device are implemented in the form of software functional units and are independent When a product is sold or used, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the method of the foregoing embodiment, and may also be completed by a computer program instructing related hardware.
  • the computer program may be stored in a computer-readable storage medium.
  • the computer When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented.
  • the computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file, or some intermediate form.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random access memory (RAM, Random Access Memory), electric carrier signals, telecommunication signals, and software distribution media.
  • a recording medium a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random access memory (RAM, Random Access Memory), electric carrier signals, telecommunication signals, and software distribution media.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种用户兴趣采集方法、装置、计算机装置及计算机可读存储介质,适用于数据处理技术领域,所述方法包括采集用户的行为数据(S101);根据所述用户的行为数据,确定至少一个与所述用户行为数据对应的用户兴趣信息,并根据预设的评分规则与所述用户的行为数据之间的对应关系,对所述用户兴趣信息进行评分(S102);对所述用户兴趣信息的评分进行统计,获取所述用户兴趣信息对应的分数值,并根据所述分数值确定用户的实际兴趣信息(S103)。该方法和装置,在用户实际兴趣信息确定时,参考用户关注、点赞、浏览时长等要素,使用户兴趣的确定更加准确,从而后续根据用户兴趣更能有效地为用户推荐内容,提高了推荐技术的有效性。

Description

用户兴趣釆集方法、 装置、 计算机装置及计算机可读存 储介质
技术领域
[0001] 本发明属于数据处理技术领域, 尤其涉及一种用户兴趣采集方法、 装置、 计算 机装置及计算机可读存储介质。
[0002]
背景技术
[0003] 近年来, 随着移动互联网和大数据的爆发性发展, 智能推荐技术在越来越多的 互联网产品上得到广泛应用, 如新闻推荐、 电影和书籍推荐、 视频推荐、 或商 品推荐等。 现有的推荐技术可以基于一些数据挖掘手段, 如挖掘用户点击历史 、 网页浏览历史、 社交网络信息等来确定用户的兴趣, 从而根据用户的兴趣为 用户推荐相应的内容。
[0004] 但是, 实践中发现, 用户在上网时可能会暂时因一个标题的吸引而浏览该网页 、 或者漫无目的随意地去浏览网页, 若仍基于上述数据挖掘手段确定用户的兴 趣, 会导致用户兴趣确定不准确, 从而导致后续不能准确地为用户推荐合适的 内容, 推荐效率较低。
[0005] 发明内容
[0006] 本发明实施例提供一种用户兴趣采集方法, 旨在解决用户兴趣确定不准确、 推 荐效率较低的问题。
[0007] 本发明实施例提供了一种用户兴趣采集方法, 包括如下步骤:
[0008] 采集用户的行为数据;
[0009] 根据用户的行为数据, 确定至少一个与用户行为数据对应的用户兴趣信息, 并 根据预设的评分规则与用户的行为数据之间的对应关系, 对用户兴趣信息进行 评分;
[0010] 对用户兴趣信息的评分进行统计, 获取用户兴趣信息对应的分数值, 并根据分 数值确定用户的实际兴趣信息。 [0011] 本发明实施例提供了一种用户兴趣采集装置, 包括:
[0012] 用户行为数据采集单元, 用于采集用户的行为数据;
[0013] 评分单元, 用于根据用户的行为数据, 确定至少一个与用户行为数据对应的用 户兴趣信息, 并根据预设的评分规则与用户的行为数据之间的对应关系, 对用 户兴趣信息进行评分;
[0014] 用户实际兴趣信息确定单元, 用于对用户兴趣信息的评分进行统计, 获取用户 兴趣信息对应的分数值, 并根据分数值确定用户的实际兴趣信息。
[0015] 本发明实施例还提供了一种计算机装置, 所述计算机装置包括: 处理器, 用于 执行存储器中存储的计算机程序时实现如上述用户兴趣采集方法的步骤。
[0016] 本发明实施例还提供了一种计算机可读存储介质, 其上存储有计算机程序, 所 述计算机程序被处理器执行时实现上述用户兴趣采集方法的步骤。
[0017] 本发明实施例中, 通过采集用户的行为数据; 根据用户的行为数据, 确定至少 个与用户行为数据对应的用户兴趣信息, 并根据预设的评分规则与用户的行 为数据之间的对应关系, 对用户兴趣信息进行评分; 对用户兴趣信息的评分进 行统计, 获取用户兴趣信息对应的分数值, 并根据分数值确定用户的实际兴趣 信息。 在用户实际兴趣信息确定时, 参考用户关注、 点赞、 浏览时长等要素, 使用户兴趣的确定更加准确, 从而后续根据用户兴趣更能有效地为用户推荐内 容, 提高了推荐技术的有效性。
[0018]
发明概述
对附图的简要说明
附图说明
[0019] 图 1是本发明实施例一提供的用户兴趣采集方法的流程示意图;
[0020] 图 2是本发明实施例二提供的确定用户实际兴趣信息的方法的实现流程图; [0021] 图 3是本发明实施例三提供的用户兴趣采集装置采集的结构示意图;
[0022] 图 4是本发明实施例四提供的用户实际兴趣信息确定单元的结构示意图。
[0023] 具体实施方式
[0024] 为了使本发明的目的、 技术方案及优点更加清楚明白, 以下结合附图及实施例 , 对本发明进行进一步详细说明。 应当理解, 此处所描述的具体实施例仅仅用 以解释本发明, 并不用于限定本发明。
[0025] 本发明实施例中, 通过采集用户的行为数据, 并通过用户的行为数据以及预设 的评分规则确定用户的实际兴趣信息。 在用户实际兴趣信息确定时, 参考用户 关注、 点赞、 浏览时长等要素, 使用户兴趣的确定更加准确, 从而后续根据用 户兴趣更能有效地为用户推荐内容, 提高了推荐技术的有效性。
[0026] 实施例一、
[0027] 参见图 1, 本发明实施例一提供了用户兴趣采集方法的流程示意图, 详述如下
[0028] 该用户兴趣采集方法包括但不限于以下步骤:
[0029] S101、 采集用户的行为数据。
[0030] 用户的行为数据可以包括用户在浏览社交类网页 (如微博) 时关注、 点赞、 或 取消关注某一网页、 或浏览该网页的时长等行为数据, 再或者用户观看视频时 , 观看某一节目的频率、 时长等行为数据等; 另外, 用户的行为数据还可以包 括用户使用终端中某一应用的使用时间、 使用时长、 或使用频率等行为数据。
[0031] 本发明实施例中, 用户的行为数据可以通过云端服务器、 也可以包括运行在 An droid操作系统、 iOS操作系统、 Windows操作系统或其他操作系统的终端上的客 户端进行采集, 该终端可以包括例如移动电话、 移动电脑、 平板电脑、 个人数 字助理 (Personal Digital Assistant, PDA) 等。
[0032] 在一种可选的实施例中, 当通过运行在终端上的客户端对用户行为数据采集时 , 用户可以浏览客户端上发布的新闻、 视频等信息。 此时客户端可以采集用户 在浏览网页时关注、 点赞、 或取消关注、 或浏览该网页的时长等行为数据; 或 者, 客户端还可以采集用户观看视频时的频率、 时长等行为数据等。
[0033] S102、 根据用户的行为数据, 确定至少一个与该用户行为数据对应的用户兴趣 信息, 并根据预设的评分规则与该用户的行为数据之间的对应关系, 对该用户 兴趣信息进行评分。
[0034] 在本发明实施例中, 预设的评分规则为不同的行为数据对应不同的分值, 比如 , 当用户的行为数据为点赞时, 则可加 1分, 当用户的行为数据为关注时, 则可 力口 2分, 当用户的行为数据为取消关注时, 则可减 2分。
[0035] 在本发明实施例中, 用户浏览的文章、 观看的视频等可分为不同的类型, 比如 , 娱乐、 生活、 体育等类型, 根据用户对不同类型的文章或视频等信息的行为 (如关注、 点赞、 取消关注或浏览等) 可确定用户的兴趣信息。
[0036] 其中, 用户的兴趣信息可为娱乐、 体育、 新闻等信息。
[0037] 可选的, 用户的行为数据可以为用户浏览不同网页的文章或者视频的时长, 可 以根据预设的评分与用户浏览时长之间的对应关系, 对用户兴趣信息进行评分 。 例如, 网页 Al、 A2、 A3属于娱乐版块, 网页 Bl、 B2、 B3属于科技版块, 网 页 Cl、 C2属于游戏版块, 预设的评分与用户浏览时长之间的对应关系为: 浏览 时长为 Omin- 1 Omin对应的分值为 1分, 浏览时长为 10min-20min对应的分值为 2分 。 如果用户兴趣采集装置浏览网页 Al、 B 1和 B2, 且浏览时长分别为 Omin-lOmin 、 Omin-lOmin和 10min-20min, 网页 A1归属于娱乐版块, 网页 B l、 B2归属于科技 版块, 则用户兴趣采集装置可以确定用户的兴趣信息为娱乐和科技, 且用户的 兴趣信息为娱乐的评分统计为 1分, 用户的兴趣信息为科技的评分统计为浏览 B 1 、 B2的分值之和 1+2=3分。
[0038] 可选的, 用户的行为数据可以为关注、 点赞、 取消关注网页, 用户兴趣采集装 置可以设置上述行为与分值之间的关系, 对用户兴趣信息进行评分。 例如, 表 1 所示行为与分值之间的关系, 用户关注网页可以加 1分, 点赞网页可以加 2分, 取消关注可以减 1分。
[0039] 表 1行为与分值对应关系
[0040] [表 1]
Figure imgf000006_0001
[0041] 如果用户兴趣采集装置采集到用户关注网页 A1, 关注网页 B1、 点赞网页 B2、 点赞网页 C1, 接上述, 网页 A1归属于娱乐版块, 网页 Bl、 B2归属于科技版块, 网页 Cl归属于游戏版块, 则用户兴趣采集装置可以确定用户的兴趣信息为娱乐 、 科技和游戏, 且用户的兴趣信息为娱乐的评分统计为关注网页 A1对应的分值 1 分, 用户兴趣信息科技的评分统计为关注网页 B 1和点赞网页 B2对应的分值之和 , 即 1+2=3分, 用户兴趣信息游戏的评分统计为点赞网页 C1对应的分值 2分。
[0042] 在又一种可选的实施例中, 还可以根据用户浏览的内容, 确定用户兴趣信息。
具体的, 可以根据用户浏览的内容信息, 提取浏览内容信息的关键词, 并根据 关键词, 确定用户行为数据对应的用户兴趣信息。 需要说明的是, 本发明实施 例中, 如果用户浏览内容信息有标签, 可以直接根据标签确定用户的兴趣信息 , 如用户浏览的内容的标签为娱乐, 则直接可以确定用户的兴趣信息为娱乐; 如果用户浏览的内容信息没有标签, 则可以提取浏览内容中的关键词, 即可确 定用户的兴趣信息, 如用户浏览的内容的中有“电影首映”, 则可以确定用户的兴 趣信息为娱乐等。
[0043] S103、 对用户兴趣信息的评分进行统计, 获取用户兴趣信息对应的分数值, 并 根据分数值确定用户的实际兴趣信息。
[0044] 在一种可选的实施例中, 分值高于预设阈值的用户兴趣信息为用户的实际兴趣 信息; 或者, 可以确定分值最高的用户兴趣信息为用户的实际兴趣信息等, 在 此不再赘述。
[0045] 可见, 实施本发明实施例, 在用户实际兴趣信息确定时, 参考用户关注、 点赞 、 浏览时长等要素, 使用户兴趣的确定更加准确, 从而后续根据用户兴趣更能 有效地为用户推荐内容, 提高了推荐技术的有效性。
[0046] 实施例二、
[0047] 图 2示出了本发明实施例二提供的确定用户实际兴趣信息的方法的实现流程, 其与实施例一相似, 不同之处在于, 所述对所述用户兴趣信息的评分进行统计 , 获取所述用户兴趣信息对应的分数值, 并根据所述分数值确定用户的实际兴 趣信息, 包括
[0048] 在步骤 S210, 对所述用户兴趣信息的评分进行统计, 获取所述用户兴趣信息对 应的分数值。
[0049] 在本发明实施例中, 当确定了用户的兴趣信息, 并根据用户的行为数据对该兴 趣信息进行了评分后, 则可对用户兴趣信息的评分进行统计, 比如, 当用户对 于娱乐类型的文章或者视频进行关注了 30次, 点赞了 20次, 则用户的兴趣信息 为娱乐, 且得分为 30+20*2=70分。
[0050] 在步骤 S220中, 获取所述分数值高于预设阈值的用户兴趣信息。
[0051] 在本发明实施例中, 预设阈值可为具体的分数值, 比如, 80分、 90分等, 具体 可以根据实际情况进行设置, 本发明实施例不做限定。
[0052] 在本发明实施例中, 对应用户的兴趣信息的分数进行统计, 并获取分数值高于 预设阈值的用户兴趣信息, 比如, 用户的兴趣信息为娱乐, 80分, 体育 60分, 预设阈值为 70分, 则用户的兴趣信息为娱乐。
[0053] 在本发明实施例中, 由于用户的兴趣信息会发生变化, 因此可统计预设时间内 的用户兴趣信息的分数, 比如, 一个月内、 半年内、 3个月内等, 具体可根据实 际情况进行设置, 本发明不做限定。
[0054] 在步骤 S230中, 根据所述分数值高于预设阈值的用户兴趣信息, 确定用户的实 际兴趣信息。
[0055] 在本发明实施例中, 用户兴趣采集装置可以确定分值高于预设阈值的用户兴趣 信息为用户的实际兴趣信息。
[0056] 可见, 实施本发明实施例, 在用户实际兴趣信息确定时, 参考用户关注、 点赞 、 浏览时长等要素, 使用户兴趣的确定更加准确, 从而后续根据用户兴趣更能 有效地为用户推荐内容, 提高了推荐技术的有效性。
[0057] 实施例三、
[0058] 示例性的, 本发明实施例中, 用户的行为数据还可以包括用户使用终端中某一 应用的使用时间、 使用时长、 或使用频率等行为数据, 用户兴趣采集装置为终 端。 具体的, 终端采集用户使用某一应用的使用时间等行为数据, 从所有使用 的应用 (可以理解为本申请的用户的兴趣信息) 中, 确定使用时间较近、 使用 时长较长或者使用频率较大的应用作为用户的实际兴趣信息。
[0059] 进一步, 终端还可以将确定出的用户的实际兴趣信息, 即上述对应的应用的图 标放置在终端主界面的特定位置, 比如放置在终端主界面最下面托盘一栏, 或 者, 放置在用户设置的特定文件夹中等, 以使用户下次更方便找到该图标。 [0060] 例如, 用户使用应用 A、 B和 C, 其中, 使用应用 A、 B和 C的频率为 10次 /天, 6 次 /天和 2次 /天, 预设使用频率阈值为 5次 /天, 终端可以确定使用频率大于预设使 用频率的应用 A和 B作为用户的实际兴趣信息, 并还可以将应用 A和 B放置在在终 端主界面最下面托盘一栏。
[0061] 基于上述方法实施例相同的技术构思, 本发明实施例还提供了一种用户兴趣采 集装置, 可以应用于上述方法实施例中。
[0062] 实施例三、
[0063] 如图 3所示, 为本发明实施例三提供的用户兴趣采集装置 300的结构示意图, 为 了便于说明, 仅示出了与本发明实施例相关的部分。
[0064] 用户兴趣采集装置 300包括: 用户行为数据采集单元 31、 评分单元 32、 用户实 际兴趣信息确定单元 33。
[0065] 用户行为数据采集单元 31, 用于采集用户的行为数据;
[0066] 用户的行为数据可以包括用户在浏览社交类网页 (如微博) 时关注、 点赞、 或 取消关注某一网页、 或浏览该网页的时长等行为数据, 再或者用户观看视频时 , 观看某一节目的频率、 时长等行为数据等; 另外, 用户的行为数据还可以包 括用户使用终端中某一应用的使用时间、 使用时长、 或使用频率等行为数据。
[0067] 本发明实施例中, 用户的行为数据可以通过云端服务器、 也可以包括运行在 An droid操作系统、 iOS操作系统、 Windows操作系统或其他操作系统的终端上的客 户端进行采集, 该终端可以包括例如移动电话、 移动电脑、 平板电脑、 个人数 字助理 (Personal Digital Assistant, PDA) 等。
[0068] 在一种可选的实施例中, 当通过运行在终端上的客户端对用户行为数据采集时 , 用户可以浏览客户端上发布的新闻、 视频等信息。 此时客户端可以采集用户 在浏览网页时关注、 点赞、 或取消关注、 或浏览该网页的时长等行为数据; 或 者, 客户端还可以采集用户观看视频时的频率、 时长等行为数据等。
[0069] 评分单元 32, 用于根据用户的行为数据, 确定至少一个与用户行为数据对应的 用户兴趣信息, 并根据预设的评分规则与用户的行为数据之间的对应关系, 对 用户兴趣信息进行评分。
[0070] 在本发明实施例中, 预设的评分规则为不同的行为数据对应不同的分值, 比如 , 当用户的行为数据为点赞时, 则可加 1分, 当用户的行为数据为关注时, 则可 力口 2分, 当用户的行为数据为取消关注时, 则可减 2分。
[0071] 在本发明实施例中, 用户浏览的文章、 观看的视频等可分为不同的类型, 比如 , 娱乐、 生活、 体育等类型, 根据用户对不同类型的文章或视频等信息的行为 (如关注、 点赞、 取消关注或浏览等) 可确定用户的兴趣信息。
[0072] 其中, 用户的兴趣信息可为娱乐、 体育、 新闻等信息。
[0073] 可选的, 评分单元还用于根据预设的评分与用户浏览时长之间的对应关系, 对 用户兴趣信息进行评分。 具体的, 用户的行为数据可以为用户浏览不同网页的 文章或者视频的时长, 可以根据预设的评分与用户浏览时长之间的对应关系, 对用户兴趣信息进行评分。 例如, 网页 Al、 A2、 A3属于娱乐版块, 网页 Bl、 B 2、 B3属于科技版块, 网页 Cl、 C2属于游戏版块, 预设的评分与用户浏览时长 之间的对应关系为: 浏览时长为 Omin-lOmin对应的分值为 1分, 浏览时长为 10mi n-20min对应的分值为 2分。 如果用户兴趣采集装置浏览网页 Al、 B1和 B2, 且浏 览时长分别为 Omin-lOmin、 Omin-lOmin和 10min-20min, 网页 A1归属于娱乐版块 , 网页 B l、 B2归属于科技版块, 则用户兴趣采集装置可以确定用户的兴趣信息 为娱乐和科技, 且用户的兴趣信息为娱乐的评分统计为 1分, 用户的兴趣信息为 科技的评分统计为浏览 B 1、 B2的分值之和 1+2=3分。
[0074] 可选的, 用户的行为数据可以为关注、 点赞、 取消关注网页, 用户兴趣采集装 置可以设置上述行为与分值之间的关系, 对用户兴趣信息进行评分。 例如, 表 1 所示行为与分值之间的关系, 用户关注网页可以加 1分, 点赞网页可以加 2分, 取消关注可以减 1分。
[0075] 表 1行为与分值对应关系
[0076] [表 2] [0077] 如果用户兴趣采集装置采集到用户关注网页 Al, 关注网页 B1、 点赞网页 B2、 点赞网页 C1, 接上述, 网页 A1归属于娱乐版块, 网页 Bl、 B2归属于科技版块, 网页 C1归属于游戏版块, 则用户兴趣采集装置可以确定用户的兴趣信息为娱乐 、 科技和游戏, 且用户的兴趣信息为娱乐的评分统计为关注网页 A1对应的分值 1 分, 用户兴趣信息科技的评分统计为关注网页 B 1和点赞网页 B2对应的分值之和 , 即 1+2=3分, 用户兴趣信息游戏的评分统计为点赞网页 C1对应的分值 2分。
[0078] 在又一种可选的实施例中, 评分单元包括:
[0079] 浏览内容信息确定单元, 用于根据用户的行为数据, 确定浏览内容信息;
[0080] 关键词提取单元, 用于提取浏览内容信息的关键词;
[0081] 用户兴趣信息确定单元, 用于根据关键词, 确定至少一个与用户行为。
[0082] 根据就用户的行为数据可以确定用户浏览的内容, 并进一步确定用户兴趣信息 。 具体的, 可以根据用户浏览的内容信息, 提取浏览内容信息的关键词, 并根 据关键词, 确定用户行为数据对应的用户兴趣信息。 需要说明的是, 本发明实 施例中, 如果用户浏览内容信息有标签, 可以直接根据标签确定用户的兴趣信 息, 如用户浏览的内容的标签为娱乐, 则直接可以确定用户的兴趣信息为娱乐 ; 如果用户浏览的内容信息没有标签, 则可以提取浏览内容中的关键词, 即可 确定用户的兴趣信息, 如用户浏览的内容的中有“电影首映”, 则可以确定用户的 兴趣信息为娱乐等。
[0083] 用户实际兴趣信息确定单元 33 , 用于对用户兴趣信息的评分进行统计, 获取用 户兴趣信息对应的分数值, 并根据分数值确定用户的实际兴趣信息。
[0084] 在一种可选的实施例中, 用户兴趣采集装置可以确定分值高于预设阈值的用户 兴趣信息为用户的实际兴趣信息; 或者, 可以确定分值最高的用户兴趣信息为 用户的实际兴趣信息等, 在此不再赘述。
[0085] 可见, 实施本发明实施例, 在用户实际兴趣信息确定时, 参考用户关注、 点赞 、 浏览时长等要素, 使用户兴趣的确定更加准确, 从而后续根据用户兴趣更能 有效地为用户推荐内容, 提高了推荐技术的有效性。
[0086] 实施例四、
[0087] 图 4示出了本发明实施例四提供了用户实际兴趣信息确定单元 33的结构, 为了 便于说明, 仅示出了与本发明实施例相关的部分。
[0088] 用户实际兴趣信息确定单元 33, 包括:
[0089] 统计模块 331, 用于对用户兴趣信息的评分进行统计, 获取用户兴趣信息对应 的分数值;
[0090] 在本发明实施例中, 当确定了用户的兴趣信息, 并根据用户的行为数据对该兴 趣信息进行了评分后, 则可对用户兴趣信息的评分进行统计, 比如, 当用户对 于娱乐类型的文章或者视频关注了 30次, 点赞了 20次, 则用户的兴趣信息为娱 乐, 且得分为 30+20*2=70分。
[0091] 用户兴趣信息获取模块 332, 用于获取分数值高于预设阈值的用户兴趣信息。
[0092] 在本发明实施例中, 预设阈值可为具体的分数值, 比如, 80分、 90分等, 具体 可以根据实际情况进行设置, 本发明实施例不做限定。
[0093] 在本发明实施例中, 对用户的兴趣信息的分数进行统计, 并获取分数值高于预 设阈值的用户兴趣信息, 比如, 用户的兴趣信息为娱乐, 80分, 体育 60分, 预 设阈值为 70分, 则用户的兴趣信息为娱乐。
[0094] 在本发明实施例中, 由于用户的兴趣信息会发生变化, 因此可统计预设时间内 的用户兴趣信息的分数, 比如, 一个月内、 半年内、 3个月内等, 具体可根据实 际情况进行设置, 本发明不做限定。
[0095] 用户实际兴趣信息确定模块 333 , 用于根据分数值高于预设阈值的用户兴趣信 息, 确定用户的实际兴趣信息。
[0096] 在本发明实施例中, 分值高于预设阈值的用户兴趣信息为用户的实际兴趣信息
[0097] 可见, 实施本发明实施例, 在用户实际兴趣信息确定时, 参考用户关注、 点赞 、 浏览时长等要素, 使用户兴趣的确定更加准确, 从而后续根据用户兴趣更能 有效地为用户推荐内容, 提高了推荐技术的有效性。
[0098] 本发明实施例还提供了一种计算机装置, 该计算机装置包括处理器, 处理器用 于执行存储器中存储的计算机程序时实现上述各个方法实施例提供的用户兴趣 信息采集方法的步骤。
[0099] 本发明的实施例还提供了一种计算机可读存储介质, 其上存储有计算机程序 / 指令, 该计算机程序 /指令被上述处理器执行时实现上述各个方法实施例提供的 用户兴趣新采集方法的步骤。
[0100] 示例性的, 计算机程序可以被分割成一个或多个模块, 一个或者多个模块被存 储在存储器中, 并由处理器执行, 以完成本发明。 一个或多个模块可以是能够 完成特定功能的一系列计算机程序指令段, 该指令段用于描述计算机程序在计 算机装置中的执行过程。 例如, 所述计算机程序可以被分割成上述各个方法实 施例提供的用户兴趣信息采集方法的步骤。
[0101] 本领域技术人员可以理解, 上述计算机装置的描述仅仅是示例, 并不构成对计 算机装置的限定, 可以包括比上述描述更多或更少的部件, 或者组合某些部件 , 或者不同的部件, 例如可以包括输入输出设备、 网络接入设备、 总线等。
[0102] 所称处理器可以是中央处理单元 (Central Processing Unit, CPU) , 还可以是其他 通用处理器、 数字信号处理器 (Digital Signal Processor, DSP)、 专用集成电路 (Application Specific Integrated Circuit, ASIC)、 现成可编程门阵列
(Field-Programmable Gate Array, FPGA)或者其他可编程逻辑器件、 分立门或者 晶体管逻辑器件、 分立硬件组件等。 通用处理器可以是微处理器或者该处理器 也可以是任何常规的处理器等, 所述处理器是所述计算机装置的控制中心, 利 用各种接口和线路连接整个用户终端的各个部分。
[0103] 所述存储器可用于存储所述计算机程序和 /或模块, 所述处理器通过运行或执 行存储在所述存储器内的计算机程序和 /或模块, 以及调用存储在存储器内的数 据, 实现所述计算机装置的各种功能。 所述存储器可主要包括存储程序区和存 储数据区, 其中, 存储程序区可存储操作系统、 至少一个功能所需的应用程序 (比如声音播放功能、 图像播放功能等) 等; 存储数据区可存储根据手机的使 用所创建的数据 (比如音频数据、 电话本等) 等。 此外, 存储器可以包括高速 随机存取存储器, 还可以包括非易失性存储器, 例如硬盘、 内存、 插接式硬盘 , 智能存储卡 (Smart Media Card, SMC) , 安全数字 (Secure Digital, SD) 卡, 闪存卡 (Flash Card) 、 至少一个磁盘存储器件、 闪存器件、 或其他易失性固态 存储器件。
[0104] 所述计算机装置集成的模块 /单元如果以软件功能单元的形式实现并作为独立 的产品销售或使用时, 可以存储在一个计算机可读取存储介质中。 基于这样的 理解, 本发明实现上述实施例方法中的全部或部分流程, 也可以通过计算机程 序来指令相关的硬件来完成, 所述的计算机程序可存储于一计算机可读存储介 质中, 该计算机程序在被处理器执行时, 可实现上述各个方法实施例的步骤。 其中, 所述计算机程序包括计算机程序代码, 所述计算机程序代码可以为源代 码形式、 对象代码形式、 可执行文件或某些中间形式等。 所述计算机可读介质 可以包括: 能够携带所述计算机程序代码的任何实体或装置、 记录介质、 U盘、 移动硬盘、 磁碟、 光盘、 计算机存储器、 只读存储器 (ROM, Read-Only Memory) 、 随机存取存储器 (RAM, Random Access Memory) 、 电载波信号、 电信信号以及软件分发介质等。
[0105] 以上所述仅为本发明的较佳实施例而已, 并不用以限制本发明, 凡在本发明的 精神和原则之内所作的任何修改、 等同替换和改进等, 均应包含在本发明的保 护范围之内。

Claims

权利要求书
[权利要求 1] 一种用户兴趣采集方法, 其特征在于, 所述方法包括:
采集用户的行为数据;
根据所述用户的行为数据, 确定至少一个与所述用户行为数据对应的 用户兴趣信息, 并根据预设的评分规则与所述用户的行为数据之间的 对应关系, 对所述用户兴趣信息进行评分;
对所述用户兴趣信息的评分进行统计, 获取所述用户兴趣信息对应的 分数值, 并根据所述分数值确定用户的实际兴趣信息。
[权利要求 2] 如权利要求 1所述的用户兴趣采集方法, 其特征在于, 所述对所述用 户兴趣信息的评分进行统计, 获取所述用户兴趣信息对应的分数值, 并根据所述分数值确定用户的实际兴趣信息, 包括:
对所述用户兴趣信息的评分进行统计, 获取所述用户兴趣信息对应的 分数值;
获取所述分数值高于预设阈值的用户兴趣信息; 根据所述分数值高于预设阈值的用户兴趣信息, 确定用户的实际兴趣 信息。
[权利要求 3] 如权利要求 1所述的用户兴趣采集方法, 其特征在于, 所述用户行为 数据包括用户浏览时长, 所述根据预设的评分与所述用户的行为数据 之间的对应关系, 对所述用户兴趣信息进行评分, 包括
根据预设的评分与所述用户浏览时长之间的对应关系, 对所述用户兴 趣信息进行评分。
[权利要求 4] 如权利要求 1所述的用户兴趣采集方法, 其特征在于, 所述根据所述 用户的行为数据, 确定至少一个与所述用户行为数据对应的用户兴趣 信息, 包括:
根据所述用户的行为数据, 确定浏览内容信息; 提取所述浏览内容信息的关键词;
根据所述关键词, 确定至少一个与所述用户行为数据对应的用户兴趣 信息。
[权利要求 5] 如权利要求 1所述的用户兴趣采集方法, 其特征在于, 所述用户行为 数据包括但不限于关注、 点赞、 取消关注、 浏览时长。
[权利要求 6] 一种用户兴趣采集装置, 其特征在于, 所述装置包括:
用户行为数据采集单元, 用于采集用户的行为数据;
评分单元, 用于根据所述用户的行为数据, 确定至少一个与所述用户 行为数据对应的用户兴趣信息, 并根据预设的评分规则与所述用户的 行为数据之间的对应关系, 对所述用户兴趣信息进行评分; 用户实际兴趣信息确定单元, 用于对所述用户兴趣信息的评分进行统 计, 获取所述用户兴趣信息对应的分数值, 并根据所述分数值确定用 户的实际兴趣信息。
[权利要求 7] 如权利要求 6所述的用户兴趣采集装置, 其特征在于, 所述用户实际 兴趣信息确定单元, 包括:
统计模块, 用于对所述用户兴趣信息的评分进行统计, 获取所述用户 兴趣信息对应的分数值;
用户兴趣信息获取模块, 用于获取所述分数值高于预设阈值的用户兴 趣信息;
用户实际兴趣信息确定模块, 用于根据所述分数值高于预设阈值的用 户兴趣信息, 确定用户的实际兴趣信息。
[权利要求 8] 如权利要求 6所述的用户兴趣采集装置, 其特征在于, 所述评分单元 还用于根据预设的评分与所述用户浏览时长之间的对应关系, 对所述 用户兴趣信息进行评分。
[权利要求 9] 如权利要求 6所述的用户兴趣采集装置, 其特征在于, 所述评分单元 包括:
浏览内容信息确定单元, 用于根据所述用户的行为数据, 确定浏览内 容信息;
关键词提取单元, 用于提取所述浏览内容信息的关键词;
用户兴趣信息确定单元, 用于根据所述关键词, 确定至少一个与所述 用户行为。
[权利要求 10] 如权利要求 1所述的用户兴趣采集方法, 其特征在于, 所述用户行为 数据包括但不限于关注、 点赞、 取消关注、 浏览时长。
[权利要求 11] 一种计算机装置, 其特征在于, 所述计算机装置包括: 处理器, 用于 执行存储器中存储的计算机程序时实现如权利要求 1~5中任意一项所 述方法的步骤。
[权利要求 12] 一种计算机可读存储介质, 其上存储有计算机程序, 其特征在于, 所 述计算机程序被处理器执行时实现如权利要求 1~5中任意一项所述方 法的步骤。
PCT/CN2018/092936 2018-06-26 2018-06-26 用户兴趣采集方法、装置、计算机装置及计算机可读存储介质 WO2020000207A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/092936 WO2020000207A1 (zh) 2018-06-26 2018-06-26 用户兴趣采集方法、装置、计算机装置及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/092936 WO2020000207A1 (zh) 2018-06-26 2018-06-26 用户兴趣采集方法、装置、计算机装置及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2020000207A1 true WO2020000207A1 (zh) 2020-01-02

Family

ID=68985693

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/092936 WO2020000207A1 (zh) 2018-06-26 2018-06-26 用户兴趣采集方法、装置、计算机装置及计算机可读存储介质

Country Status (1)

Country Link
WO (1) WO2020000207A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11388124B2 (en) * 2020-03-19 2022-07-12 Kakao Corp. Method, user device and contents provision server for recommending contents related to contents

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104102648A (zh) * 2013-04-07 2014-10-15 腾讯科技(深圳)有限公司 基于用户行为数据的兴趣推荐方法及装置
CN104281718A (zh) * 2014-11-04 2015-01-14 深圳市英威诺科技有限公司 一种基于用户群体行为数据挖掘智能推荐的方法
CN106503014A (zh) * 2015-09-08 2017-03-15 腾讯科技(深圳)有限公司 一种实时信息的推荐方法、装置和系统
CN106777367A (zh) * 2017-01-24 2017-05-31 深圳企管加企业服务有限公司 一种基于大数据挖掘的用户行为分析方法及系统
CN107704575A (zh) * 2017-09-30 2018-02-16 郑州轻工业学院 基于数据挖掘的用户行为分析方法及用户行为分析装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104102648A (zh) * 2013-04-07 2014-10-15 腾讯科技(深圳)有限公司 基于用户行为数据的兴趣推荐方法及装置
CN104281718A (zh) * 2014-11-04 2015-01-14 深圳市英威诺科技有限公司 一种基于用户群体行为数据挖掘智能推荐的方法
CN106503014A (zh) * 2015-09-08 2017-03-15 腾讯科技(深圳)有限公司 一种实时信息的推荐方法、装置和系统
CN106777367A (zh) * 2017-01-24 2017-05-31 深圳企管加企业服务有限公司 一种基于大数据挖掘的用户行为分析方法及系统
CN107704575A (zh) * 2017-09-30 2018-02-16 郑州轻工业学院 基于数据挖掘的用户行为分析方法及用户行为分析装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11388124B2 (en) * 2020-03-19 2022-07-12 Kakao Corp. Method, user device and contents provision server for recommending contents related to contents

Similar Documents

Publication Publication Date Title
US8713003B2 (en) System and method for ranking content and applications through human assistance
US10043199B2 (en) Method, device and system for publishing merchandise information
WO2019085355A1 (zh) 互联网新闻的舆情聚类分析方法、应用服务器及计算机可读存储介质
US11176142B2 (en) Method of data query based on evaluation and device
CN107463641B (zh) 用于改进对搜索结果的访问的系统和方法
WO2016197774A1 (zh) 一种多媒体数据推送方法、装置以及存储介质
WO2017005054A1 (zh) 视频推荐方法、服务器和存储介质
US9509643B1 (en) Network-based content discovery using messages of a messaging platform
US20150334068A1 (en) Message processing method and apparatus
US11816172B2 (en) Data processing method, server, and computer storage medium
US9660947B1 (en) Method and apparatus for filtering undesirable content based on anti-tags
WO2017107569A1 (zh) 一种基于应用内容的安卓应用组装方法
CN111259271A (zh) 评论信息的展示方法、装置、电子设备及计算机可读介质
CN110781372B (zh) 一种优化网站的方法、装置、计算机设备及存储介质
WO2017219524A1 (zh) 一种页面保存的方法及电子设备
US20140250116A1 (en) Identifying time sensitive ambiguous queries
US9471669B2 (en) Presenting previously selected search results
WO2023040530A1 (zh) 网页内容溯源方法、知识图谱构建方法以及相关设备
CN110347900B (zh) 一种关键词的重要度计算方法、装置、服务器及介质
WO2020000207A1 (zh) 用户兴趣采集方法、装置、计算机装置及计算机可读存储介质
CN103986606B (zh) 一种基于MapReduce算法的并行识别、统计网页URL的方法
WO2018205642A1 (zh) 视频收益计算建模装置、方法和视频推荐装置、方法和服务器及存储介质
CN110674386B (zh) 资源推荐方法、装置及存储介质
US8949228B2 (en) Identification of new sources for topics
CN109074365B (zh) 使网络通信路径参数化

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: 18923920

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18923920

Country of ref document: EP

Kind code of ref document: A1