WO2017020714A1 - 用于推荐及辅助推荐信息的方法及装置 - Google Patents

用于推荐及辅助推荐信息的方法及装置 Download PDF

Info

Publication number
WO2017020714A1
WO2017020714A1 PCT/CN2016/090814 CN2016090814W WO2017020714A1 WO 2017020714 A1 WO2017020714 A1 WO 2017020714A1 CN 2016090814 W CN2016090814 W CN 2016090814W WO 2017020714 A1 WO2017020714 A1 WO 2017020714A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
user
label
leaf
tag
Prior art date
Application number
PCT/CN2016/090814
Other languages
English (en)
French (fr)
Inventor
刘通
Original Assignee
阿里巴巴集团控股有限公司
刘通
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 阿里巴巴集团控股有限公司, 刘通 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2017020714A1 publication Critical patent/WO2017020714A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Definitions

  • the present application relates to the field of computer technologies, and in particular, to a method and apparatus for recommending and assisting recommendation information.
  • Information recommendation techniques have been applied to various platforms. For example, the recommendation of products in the e-commerce platform, the recommendation of information in the information platform, and so on.
  • Existing information recommendation techniques include techniques for information recommendation based on user preferences. Specifically, the leaf category of the user preference is obtained, and then the information included in the leaf category is recommended for the user based on the leaf category of the user preference. For example, if the obtained user's preferred leaf category is a fishing rod, the information recommended for the user is information of different specifications of the fishing rod contained in the leaf category fishing rod.
  • the disadvantage of the above method is that the recommendation is based on the traditional classification of information, and the recommended information is limited to the leaf category preferred by the user, and the personalized recommendation cannot be performed. That is, information related to user preference information that is not of interest to the user cannot be recommended to the user.
  • One of the technical problems solved by the present application is to provide a method and apparatus for recommending and assisting recommendation information, and implementing recommendation information for users based on user preferences.
  • a method for assisting recommendation information including:
  • a method for recommending information including:
  • an apparatus for assisting recommendation information including:
  • a first determining unit configured to determine a leaf category of the user preference based on the user behavior information
  • a second determining unit configured to determine, according to a leaf category of the user preference, an information label of the user preference, where the information label is a label obtained by clustering relationships between leaf categories of the information;
  • An information label providing unit configured to provide the determined information label of the user preference to the client in response to receiving the information label obtaining request of the user sent by the client, so that the client recommends the information Label the user.
  • an apparatus for recommending information including:
  • An information label obtaining unit configured to acquire, according to the information label obtaining request of the user, the information label of the user preference, where the information label is obtained by clustering the leaf category of the user preference;
  • An information label display unit configured to display the acquired information label of the user preference
  • a leaf category obtaining unit configured to acquire, according to the information label selection request of the user, a leaf category corresponding to the selected information label from the server;
  • a leaf category display unit for recommending a leaf category corresponding to the selected information label.
  • a method for generating an information tag includes: generating an information tag by clustering relationships between leaf categories of information.
  • an apparatus for generating an information tag includes: means for generating an information tag by clustering of relationships between leaf categories of information.
  • the information is recommended by the user in the manner of the information label
  • the information label is a label obtained by clustering the relationship between the leaf categories of the information
  • the information label recommended to the user is determined according to the leaf category of the user preference. . Therefore, the user can not only find the desired and preferred information as soon as possible, but also obtain information related to the preferred information.
  • the purpose of extending the recommendation information is achieved, and the information recommended by the extension is a kind of information that can be clustered with the information that the user prefers, that is, the information related to the information that the user prefers, and the extended user attention is not realized. Causes interference to users.
  • FIG. 1 is a flow chart of a method for assisting recommendation information in accordance with one embodiment of the present application.
  • FIG. 2 is a flow chart of a method for recommending information in accordance with one embodiment of the present application.
  • FIG. 3 is a schematic diagram showing an information label display according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of an apparatus for assisting recommendation information according to an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of an apparatus for assisting recommendation information according to another embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of an apparatus for recommending information according to an embodiment of the present application.
  • the computer device includes a user device and a network device.
  • the user equipment includes, but is not limited to, a computer, a smart phone, a PDA, etc.
  • the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud computing based computer Or a cloud composed of a network server, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computers.
  • the computer device can be operated separately to implement the present application, and can also access the network and implement the application through interaction with other computer devices in the network.
  • the network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.
  • the user equipment, the network equipment, the network, and the like are only examples, and other existing or future computer equipment or networks may be applicable to the present application, and should also be included in the scope of the present application. It is included here by reference.
  • the information described in the embodiment of the present application includes, but is not limited to, product information, news information, topics, articles, and the like. Therefore, the method for recommending and assisting recommendation information described in the embodiments of the present application can be applied to each Types of applications, including but not limited to: e-commerce applications, information applications, social applications, and the like.
  • FIG. 1 is a flow diagram of a method for assisting recommendation information, which may be performed by a network side device, in accordance with an embodiment of the present application.
  • the method mainly includes the following steps:
  • the leaf category is the end category in the traditional classification of information, that is, below There are no subcategories of categories.
  • the user behavior information includes: a user history behavior record.
  • the method for determining the leaf category of the user preference based on the user preference information in the user history behavior record, and the method for determining the user preference information in the embodiment of the present application No restrictions. Since the information preferred by the user may include hundreds or more kinds of information, in order to assist the user to recommend information, the user needs to first determine the leaf category preferred by the user based on the information of the user preference, so as to calculate the user's preference for each leaf category. degree.
  • the linear regression algorithm may be applied to implement the leaf type of the user preference based on the user preference information by using a machine learning method. This embodiment does not specifically limit this.
  • the determined leaf category preferred by user A includes: earphones, crystal ornaments.
  • the leaf categories preferred by User B include: portable audio, cleaning supplies.
  • the leaf category of the preference determined by the user may also include hundreds or thousands.
  • the embodiment of the present application may determine the user's classification of each leaf category.
  • the degree of preference that is, through machine learning, can sort the leaf categories preferred by the user, and the order of ranking indicates the degree of preference of the user for each leaf category.
  • a predetermined number of leaf categories ie, the user prefers
  • may be selected as the determined leaf category of the user preference for example, selecting the top 100 leaf categories ranked first as the determined user preference Leaf category.
  • the information tag described in step S11 is a tag obtained by clustering the relationship between the leaf categories of the information.
  • the traditional leaf categories can be: portable audio, earphone, headset, power amplifier information clustered into information label "digital control"; the leaf category is: cleaning supplies, detergent information clustering
  • the information tag "obsessive-compulsive disorder”; clusters crystal pendants, small gold bells, bookmarks into information tags "exotic things” and so on. It can be seen that the traditional information that is not a leaf category can be clustered into the same information label by clustering.
  • the embodiment of the present application recommends information for the user in the form of an information label, which is based on the relationship between the traditional leaf categories.
  • the label obtained by the class so if it is determined to be the information label recommended by the user, the leaf category of the user preference needs to be clustered, thereby obtaining the information label of the user preference. That is, the information label of the user preference is determined according to the leaf category of the user preference described in step S11.
  • the method of signing includes: clustering the leaf categories of the user preference to obtain the information label of the user preference.
  • the leaf category preferred by user A includes: earphones, crystal ornaments; user B preferred leaf categories include: portable audio, cleaning supplies.
  • the information labels preferred by the user A include: digital control, odd objects; the information labels preferred by the user B include: digital control, obsessive-compulsive disorder.
  • the embodiment of the present application may also determine a representative map for the information label that the user prefers, and the representative image may be a picture of the leaf category preferred by the user, that is, the user preference level of the leaf category corresponding to the information label is ranked first.
  • the leaf category represents the picture so that the user can know at a glance the leaf categories that the information tag may contain. For example, the user class A prefers the leaf category in the first row of the earphones, and the portable audio ranks the third place.
  • the digital control can use the earphone (because the earphone Sorting is better than the portable audio sorting) as a representative picture.
  • embodiments of the present application are not limited thereto.
  • the information label of the determined user preference, the representative map corresponding to each information label, and the leaf node of the user preference are stored in association with the user information, so as to subsequently receive the relevant information about the user's information label.
  • relevant information such as the information tag of the user preference determined by the user may be provided to the client to implement the auxiliary recommendation information.
  • step S12 in response to receiving the information tag acquisition request of the user sent by the client, the determined information tag of the user preference is provided to the client, so that the client recommends the information tag to the client. User.
  • Providing the determined information label of the user preference to the client may provide all the determined information labels of the user preference to the client at one time, or may be provided in batches, for example, each Receiving an information tag acquisition request provides a predetermined number of information tags of the user preference to the client.
  • the order of the information labels providing the user preferences to the clients may be determined according to the degree of user preference.
  • the method further includes:
  • the order of the degree of user preference provides the leaf category corresponding to the selected information tag. That is, the order in which the leaf categories are provided to the client is determined according to the degree of user preference.
  • the information label selection request is a information label selection request sent by the client when the user selects a information label and wants to further view the detailed content in the information label.
  • the method execution entity provides the leaf category (information included) corresponding to the selected information label to the client.
  • One of the embodiments may provide all the leaf categories corresponding to the selected information label.
  • the leaf category corresponding to the selected information label may be provided in the order of the degree of user preference.
  • Another embodiment may only provide the leaf category preferred by the user in the leaf category corresponding to the selected new tag.
  • the information label selected by the user is “digital control”, and the corresponding leaf category in the digital control is many, for example, including: portable audio, earphone, headset, power amplifier, etc., but in the information label, the user prefers the leaf.
  • portable audio and headphones you can only recommend portable audio and headphones, and you can also recommend portable audio and headphones, and then recommend other leaf categories in the information tag, amplifiers, and so on.
  • the embodiment of the present application implements an information tag for determining a preference for the user, so as to provide the information tag preferred by the user to the client when receiving the information tag acquisition request sent by the client, to assist the user to recommend the information tag to the user.
  • the embodiment of the present application further provides a method for recommending information, as shown in FIG. 2 is a flowchart of a method for recommending information according to an embodiment of the present application, which may be performed by a client device.
  • the method mainly includes the following steps:
  • the information label obtaining request of the user in the step S20 may be a login request of the user in the actual operation, that is, when the user logs in to the application, that is, the information label of the user is considered to be received.
  • the user needs to recommend the information label to the user, and then send the information label obtaining request of the user to the server, so as to obtain the information label of the user preference from the server, and the information label is collected by the user's preferred leaf category.
  • Step S21 After obtaining the information label preferred by the user, displaying the information label preferred by the user.
  • the name of the information tag may be displayed when the information tag is displayed; or the name and representative image of the information tag are displayed.
  • the information tag of the user preference may include multiple, the information tag of the user preference may be displayed in multiple pages.
  • One of the embodiments may display the information tag according to the order of the user's preference level, that is, the priority display with a high degree of user preference.
  • Specific methods for displaying information labels recommended by users in multiple pages include:
  • the user's handover request includes, but is not limited to, receiving a handover request sent by the user by changing the location of the client with a certain acceleration. For example, the user sends a handover request by shaking the mobile phone, and the mobile phone perceives the shake through the built-in acceleration sensor. An indication of shaking, thereby determining to receive the switching request; or receiving a switching request issued by the user through the set switching button.
  • the information tag is presented in a manner distributed around a center of the circle, indicating the user's preference for the respective information tag near the center of the circle.
  • This kind of presentation can visually reflect the relevant attributes of the information tag.
  • the user displays five information labels on the first display page.
  • the five information labels can be close to the center of the circle. Indicates the user's preference for the five information tags. For example, the closer to the center of the circle, the more the user prefers the leaf category corresponding to the information tag.
  • the user shakes the mobile phone switch to display the next 5 information labels, and then shake to display the other 5 information labels.
  • the number of information tags displayed on each page can also vary.
  • the advantages of recommending information to the user in the form of information tags include that the user can find the information preferred by the user as soon as possible, and at the same time, can also recommend information related to the information preferred by the user for the user. Because the embodiment of the present application can classify leaf categories of different classes in the process of generating information labels by clustering. Clustering into the same tag, for example, clustering crystal pendants, small gold bells, and bookmarks into odd objects.
  • the information label recommended by the user is a singular object, and when the user is recommended for the singular object, the information in the other leaf categories included in the information label (the singular object) is also recommended, including The small gold bells, bookmarks, etc., achieve the purpose of expanding the recommendation information, and the information recommended by the extension is a kind of information that can be clustered with the information that the user prefers, that is, the information related to the information preferred by the user, and the extension is implemented. The user's attention will not cause interference to the user.
  • step S22 in response to receiving the information label selection request of the user, the leaf category corresponding to the selected information label is obtained from the server. That is, when the user selects an information tag, the leaf category corresponding to the selected information tag needs to be further displayed. Therefore, the information label selection request is sent to the server side, and the leaf category corresponding to the selected information label provided by the server is received.
  • the leaf category corresponding to the server providing the selected information label may include the following two situations:
  • All leaf categories corresponding to the selected information label can be provided, and the leaf categories corresponding to the information label are provided in order of user preference.
  • the client can know the preference of the user for each leaf category in the leaf category corresponding to the selected information label. Therefore, when the leaf category corresponding to the selected information label is recommended in the step S23, the leaf category corresponding to the selected information label may be recommended in the order of the user preference level, that is, the leaf category corresponding to the selected information label is preferentially displayed.
  • the embodiment of the present application implements different leaf categories for different users when different users select the same information label. For example, if it is determined that the information labels preferred by User A and User B both include digital control, and the leaf category corresponding to the information label, the leaf category preferred by User A is a headset, and the leaf category preferred by User B is a portable audio. Or, in the leaf category preferred by user A, the earphones belonging to the same category of information labels (digital control) are ranked first in the leaf category; the leaf category preferred by user B belongs to the same information label (digital control). The order of portable audio in the leaf category is the highest.
  • the embodiment of the present application implements different preferences for different users, and displays different information in different recommended display orders when the user selects the same information label.
  • the information in the leaf category preferred by the user in the leaf category corresponding to the selected information label is preferentially displayed, that is, the information in the leaf category of the user preference is displayed, and the information label is also displayed.
  • the information in the other leaf categories is only the information in the leaf category preferred by the user. This is more conducive to users quickly find the information they need, preferred.
  • the embodiment of the present application further provides an apparatus corresponding to the foregoing method for assisting recommendation information.
  • the apparatus mainly includes:
  • the first determining unit 40 is configured to determine a leaf category of the user preference based on the user behavior information.
  • the second determining unit 41 is configured to determine, according to the leaf category of the user preference, the information label of the user preference, where the information label is a label obtained by clustering the relationship between the leaf categories of the information.
  • the information label providing unit 42 is configured to provide the determined information label of the user preference to the client in response to receiving the information label obtaining request of the user sent by the client, so that the client recommends the The information tag is given to the user.
  • the second determining unit 41 is configured to:
  • Clustering the leaf categories preferred by the user results in an information tag of the user preference.
  • the apparatus may further include:
  • the leaf category providing unit 43 is configured to provide the leaf category corresponding to the selected information label in the order of the user preference level in response to receiving the information label selection request of the user sent by the client.
  • the embodiment of the present application further provides an apparatus corresponding to the foregoing method for recommending information.
  • the apparatus mainly includes:
  • the information label obtaining unit 60 is configured to obtain, according to the information label obtaining request of the user, the information label of the user preference, where the information label is obtained by clustering the leaf category of the user preference;
  • An information label display unit 61 configured to display the acquired information label of the user preference
  • a leaf category obtaining unit 62 configured to acquire, according to the information label selection request of the user, a leaf category corresponding to the selected information label from the server;
  • the leaf category display unit 63 is configured to recommend a leaf category corresponding to the selected information label.
  • the information label display unit 61 is configured to:
  • the information label display unit 61 can be configured to:
  • a predetermined number of the user-applied information tags are displayed on each of the display pages, and in response to receiving the user's switching request, the display page and the displayed user-applied information tags are switched.
  • the information tag display unit 61 can be configured to:
  • the user-applied information tags are displayed in a manner distributed around a center of the circle, and the degree of preference of the user for each information tag is indicated by the proximity of each information tag to the center of the circle.
  • the leaf category obtaining unit 62 is configured to: acquire, from the server, a preference level of the user for each leaf category in the leaf category corresponding to the selected information label;
  • the corresponding leaf category display unit 63 is configured to:
  • the leaf category corresponding to the selected information tag is recommended in the order of the degree of user preference.
  • the embodiment of the present application further provides a method for generating an information label, including: generating an information label by clustering relationships between leaf categories of information. Clustering can be used to cluster traditional information that is not a leaf class into the same information tag.
  • An embodiment of the present application further provides an apparatus for generating an information label, including: means for generating an information label by clustering relationships between leaf categories of information.
  • the embodiment of the present application recommends information for the user in the form of an information label
  • the information label is a label obtained by clustering the relationship between the leaf categories of the information, and the information label recommended to the user is based on the user preference.
  • the leaf category is determined. Therefore, the user can not only find the desired and preferred information as soon as possible, but also obtain information related to the preferred information.
  • the purpose of extending the recommendation information is achieved, and the information recommended by the extension is information that can be clustered with the information that the user prefers, that is, information related to the information preferred by the user, and the extension is implemented. The user's attention will not cause interference to the user.
  • the present application can be implemented in software and/or a combination of software and hardware, for example, using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device.
  • the software program of the present application can be executed by a processor to implement the steps or functions described above.
  • the software programs (including related data structures) of the present application can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like.
  • some of the steps or functions of the present application may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.
  • a portion of the present application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or technical solution in accordance with the present application.
  • the program instructions for invoking the method of the present application may be stored in a fixed or removable recording medium, and/or transmitted by a data stream in a broadcast or other signal bearing medium, and/or stored in a The working memory of the computer device in which the program instructions are run.
  • an embodiment in accordance with the present application includes a device including a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, triggering
  • the apparatus operates based on the aforementioned methods and/or technical solutions in accordance with various embodiments of the present application.

Abstract

一种用于推荐及辅助推荐信息的方法及装置,其中辅助推荐信息的方法包括:基于用户行为信息确定用户偏好的叶子类目(S10);依据用户偏好的叶子类目确定所述用户偏好的信息标签,所述信息标签为通过信息的叶子类目之间的关系聚类获得的标签(S11);响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户(S12)。该方法实现了扩展推荐信息的目的且不会对用户造成干扰。

Description

用于推荐及辅助推荐信息的方法及装置 技术领域
本申请涉及计算机技术领域,尤其涉及一种用于推荐及辅助推荐信息的方法及装置。
背景技术
信息推荐的目的是令用户快速的找到需要的信息,或对推荐的信息引起关注。目前在各类平台中都已应用信息推荐技术。例如,电子商务平台中对产品的推荐,资讯平台中对资讯的推荐等等。已有的信息推荐技术包括基于用户偏好进行信息推荐的技术。具体为:获取用户偏好的叶子类目,之后基于用户偏好的叶子类目为用户推荐该叶子类目包含的信息。例如,获取到的用户的偏好叶子类目为鱼竿,则为用户推荐的信息为该叶子类目鱼竿中包含的不同规格的鱼竿的信息。
上述方法的弊端在于:该推荐是基于信息的传统分类,其所推荐的信息局限于用户偏好的叶子类目,无法进行个性化推荐。即,对于用户无兴趣表示的与用户偏好信息相关的信息无法推荐给用户。
发明内容
本申请解决的技术问题之一是,提供一种用于推荐及辅助推荐信息的方法及装置,实现基于用户偏好为用户扩展推荐信息。
根据本申请一方面的一个实施例,提供了一种用于辅助推荐信息的方法,包括:
基于用户行为信息确定用户偏好的叶子类目;
依据用户偏好的叶子类目确定所述用户偏好的信息标签,所述信息标签为通过信息的叶子类目之间的关系聚类获得的标签;
响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户。
根据本申请另一方面的一个实施例,提供了一种用于推荐信息的方法,包括:
响应于接收到用户的信息标签获取请求,从服务器端获取所述用户偏好的信息标签,所述信息标签为通过用户偏好的叶子类目聚类得到;
展示获取的所述用户偏好的信息标签;
响应于接收到所述用户的信息标签选择请求,从服务器获取所选择的信息标签对应的叶子类目;
推荐所选择的信息标签对应的叶子类目。
根据本申请又一方面的一个实施例,提供了一种用于辅助推荐信息的装置,包括:
第一确定单元,用于基于用户行为信息确定用户偏好的叶子类目;
第二确定单元,用于依据用户偏好的叶子类目确定所述用户偏好的信息标签,所述信息标签为通过信息的叶子类目之间的关系聚类获得的标签;
信息标签提供单元,用于响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户。
根据本申请再一方面的一个实施例,提供了一种用于推荐信息的装置,包括:
信息标签获取单元,用于响应于接收到用户的信息标签获取请求,从服务器端获取所述用户偏好的信息标签,所述信息标签为通过用户偏好的叶子类目聚类得到;
信息标签展示单元,用于展示获取的所述用户偏好的信息标签;
叶子类目获取单元,用于响应于接收到所述用户的信息标签选择请求,从服务器获取所选择的信息标签对应的叶子类目;
叶子类目展示单元,用于推荐所选择的信息标签对应的叶子类目。
根据本申请还一方面的一个实施例,提供了一种生成信息标签的方法,包括:通过信息的叶子类目之间的关系聚类生成信息标签。
根据本申请又一方面的一个实施例,提供了一种生成信息标签的装置,包括:用于通过信息的叶子类目之间的关系聚类生成信息标签的单元。
本申请实施例以信息标签的方式为用户推荐信息,且信息标签为通过信息的叶子类目之间的关系聚类获得的标签,推荐给用户的信息标签为基于用户偏好的叶子类目确定的。因此,用户不但可以尽快找到需要的、且偏好的信息,而且还可以获得与偏好的信息相关的信息。实现了扩展推荐信息的目的,同时该扩展推荐的信息为与用户偏好的信息能够聚类成为一类的信息,也就是与用户偏好的信息相关的信息,在实现扩展用户关注点的同时不会对用户造成干扰。
本领域普通技术人员将了解,虽然下面的详细说明将参考图示实施例、附图进行,但本申请并不仅限于这些实施例。而是,本申请的范围是广泛的,且意在仅通过后附的权利要求限定本申请的范围。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述,本申请的其它特征、目的和优点将会变得更明显:
图1是根据本申请一个实施例的用于辅助推荐信息的方法的流程图。
图2是根据本申请一个实施例的用于推荐信息的方法的流程图。
图3是根据本申请一个实施例的信息标签展示示意图。
图4是根据本申请一个实施例的用于辅助推荐信息的装置的结构示意图。
图5是根据本申请另一个实施例的用于辅助推荐信息的装置的结构示意图。
图6是根据本申请一个实施例的用于推荐信息的装置的结构示意图。
附图中相同或相似的附图标记代表相同或相似的部件。
具体实施方式
在更加详细地讨论示例性实施例之前应当提到的是,一些示例性实施例被描述成作为流程图描绘的处理或方法。虽然流程图将各项操作描述成顺序的处理,但是其中的许多操作可以被并行地、并发地或者同时实施。此外,各项操作的顺序可以被重新安排。当其操作完成时所述处理可以被 终止,但是还可以具有未包括在附图中的附加步骤。所述处理可以对应于方法、函数、规程、子例程、子程序等等。
所述计算机设备包括用户设备与网络设备。其中,所述用户设备包括但不限于电脑、智能手机、PDA等;所述网络设备包括但不限于单个网络服务器、多个网络服务器组成的服务器组或基于云计算(Cloud Computing)的由大量计算机或网络服务器构成的云,其中,云计算是分布式计算的一种,由一群松散耦合的计算机集组成的一个超级虚拟计算机。其中,所述计算机设备可单独运行来实现本申请,也可接入网络并通过与网络中的其他计算机设备的交互操作来实现本申请。其中,所述计算机设备所处的网络包括但不限于互联网、广域网、城域网、局域网、VPN网络等。
需要说明的是,所述用户设备、网络设备和网络等仅为举例,其他现有的或今后可能出现的计算机设备或网络如可适用于本申请,也应包含在本申请保护范围以内,并以引用方式包含于此。
后面所讨论的方法(其中一些通过流程图示出)可以通过硬件、软件、固件、中间件、微代码、硬件描述语言或者其任意组合来实施。当用软件、固件、中间件或微代码来实施时,用以实施必要任务的程序代码或代码段可以被存储在机器或计算机可读介质(比如存储介质)中。(一个或多个)处理器可以实施必要的任务。
这里所公开的具体结构和功能细节仅仅是代表性的,并且是用于描述本申请的示例性实施例的目的。但是本申请可以通过许多替换形式来具体实现,并且不应当被解释成仅仅受限于这里所阐述的实施例。
应当理解的是,虽然在这里可能使用了术语“第一”、“第二”等等来描述各个单元,但是这些单元不应当受这些术语限制。使用这些术语仅仅是为了将一个单元与另一个单元进行区分。举例来说,在不背离示例性实施例的范围的情况下,第一单元可以被称为第二单元,并且类似地第二单元可以被称为第一单元。这里所使用的术语“和/或”包括其中一个或更多所列出的相关联项目的任意和所有组合。
应当理解的是,当一个单元被称为“连接”或“耦合”到另一单元时,其可以直接连接或耦合到所述另一单元,或者可以存在中间单元。与此相对, 当一个单元被称为“直接连接”或“直接耦合”到另一单元时,则不存在中间单元。应当按照类似的方式来解释被用于描述单元之间的关系的其他词语(例如“处于...之间”相比于“直接处于...之间”,“与...邻近”相比于“与...直接邻近”等等)。
这里所使用的术语仅仅是为了描述具体实施例而不意图限制示例性实施例。除非上下文明确地另有所指,否则这里所使用的单数形式“一个”、“一项”还意图包括复数。还应当理解的是,这里所使用的术语“包括”和/或“包含”规定所陈述的特征、整数、步骤、操作、单元和/或组件的存在,而不排除存在或添加一个或更多其他特征、整数、步骤、操作、单元、组件和/或其组合。
还应当提到的是,在一些替换实现方式中,所提到的功能/动作可以按照不同于附图中标示的顺序发生。举例来说,取决于所涉及的功能/动作,相继示出的两幅图实际上可以基本上同时执行或者有时可以按照相反的顺序来执行。
本申请实施例中所述的信息包括但不限于:产品信息,新闻资讯、话题或文章等等各类信息,因此,本申请实施例中所述的推荐及辅助推荐信息的方法可适用于各类型的应用,包括但不限于:电子商务类应用、资讯类应用、社交类应用等等。
下面结合附图对本申请的技术方案作进一步详细描述。
图1是根据本申请一个实施例的用于辅助推荐信息的方法的流程图,该方法可以由网络侧设备执行。该方法主要包括如下步骤:
S10、基于用户行为信息确定用户偏好的叶子类目;
S11、依据用户偏好的叶子类目确定所述用户偏好的信息标签,所述信息标签为通过信息的叶子类目之间的关系聚类获得的标签;
S12、响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户。
下面对上述各步骤做进一步详细介绍。
所述叶子类目为信息的传统分类中处于最末端的类目,也就是其下面 没有子类目的类目。
所述用户行为信息包括:用户历史行为记录。
步骤S10中所述的基于用户行为信息确定用户偏好的叶子类目,可以基于用户历史行为记录中用户偏好的信息来确定用户偏好的叶子类目,本申请实施例对确定用户偏好的信息的方法不做限制。由于用户偏好的信息可能包括成百上千种或更多,为实现辅助向用户推荐信息,需首先基于用户偏好的信息确定用户偏好的叶子类目,以统计出用户对各叶子类目的偏好程度。其中,可以应用线性回归算法采用机器学习的方法实现基于用户偏好的信息确定用户偏好的叶子类目,本实施例对此不做具体限制。例如,所确定的用户A偏好的叶子类目包括:耳机、水晶摆件。用户B偏好的叶子类目包括:便携音响、清洁用品。
可以理解的是,由于用户偏好的信息可能包括成百上千种,因此为该用户确定的偏好的叶子类目也可能包括成百上千种,本申请实施例可确定用户对各叶子类目的偏好程度,也就是通过机器学习可以为用户偏好的叶子类目排序,通过排序的先后来表示用户对各叶子类目的偏好程度。其中可选择排序靠前的(即用户较偏好的)指定数量的叶子类目作为所确定的用户偏好的叶子类目,例如,选择排序靠前的前100个叶子类目作为确定的用户偏好的叶子类目。
步骤S11中所述的信息标签为通过信息的叶子类目之间的关系聚类获得的标签。例如,通过聚类可将传统的叶子类目为:便携音响、耳机、耳麦、功放的信息聚类为信息标签“数码控”;将叶子类目为:清洁用品、清洁剂的信息聚类为信息标签“强迫症”;将水晶挂件、黄金小铃铛、书签聚类为信息标签“奇葩物”等等。可见,通过聚类可将传统的不是一个叶子类目的信息聚类为同一个信息标签中。
由于步骤S10中确定的用户偏好的叶子类目为传统的叶子类目,而本申请实施例是以信息标签的形式为用户推荐信息,该信息标签是基于传统的叶子类目之间的关系聚类获得的标签,因此若要确定为用户推荐的信息标签,需对用户偏好的叶子类目聚类,从而得到用户偏好的信息标签。也就是步骤S11所述的依据用户偏好的叶子类目确定所述用户偏好的信息标 签的方法包括:对用户偏好的叶子类目聚类得到用户偏好的信息标签。
例如,若用户A偏好的叶子类目包括:耳机、水晶摆件;用户B偏好的叶子类目包括:便携音响、清洁用品。则通过对偏好的叶子类目聚类,可得到用户A偏好的信息标签包括:数码控、奇葩物;用户B偏好的信息标签包括:数码控、强迫症。通过聚类可能为用户确定出多个为用户偏好推荐的信息标签,可从中选择用户偏好的前N(N为正整数)个叶子类目对应的信息标签作为确定的用户偏好的为用户推荐的信息标签。
另外,本申请实施例还可为用户偏好的信息标签确定代表图,所述代表图片可以为用户偏好的叶子类目的图片,也就是信息标签所对应的叶子类目中用户偏好程度排序靠前的叶子类目的代表图片,这样用户通过该图片能够一目了然的知道该信息标签可能包含的叶子类目。例如,用户A偏好的叶子类目排序中耳机排第一位,便携式音响排第三位,聚类后确定的为用户A推荐的信息标签包括数码控,则该数码控可以使用耳机(因为耳机排序比便携式音响排序靠前)作为代表图片。当然本申请实施例并不局限于此。本申请实施例可将该确定的用户偏好的信息标签、各信息标签对应的代表图以及用户偏好的叶子节点等信息与该用户信息关联存储,以便后续在接收到关于该用户的信息标签的相关请求的情况下,即可将为该用户确定的该用户偏好的信息标签等相关信息提供给客户端以实现辅助推荐信息。
步骤S12即为响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户。
其中,提供所确定的所述用户偏好的信息标签给所述客户端可以一次性提供所有的所确定的所述用户偏好的信息标签给所述客户端,也可以分批次提供,例如,每接收到一次信息标签获取请求则提供预定数量的该用户偏好的信息标签给所述客户端。可按照用户偏好程度来确定提供该用户偏好的信息标签给所述客户端的先后顺序。
另外,所述方法还包括:
响应于接收到所述客户端发送的所述用户的信息标签选择请求,按照 用户偏好程度的顺序提供所选择的信息标签对应的叶子类目。也就是按照用户偏好程度来确定提供叶子类目给所述客户端的先后顺序。其中,信息标签选择请求,即在用户选择一信息标签,想进一步查看该信息标签中的详细内容情况下,所述客户端发送的信息标签选择请求。则本方法执行主体提供所选择的信息标签对应的叶子类目(所包含的信息)给所述客户端。其中一种实施例可提供所选择的信息标签对应的所有叶子类目,可选地,可按照用户偏好程度的顺序提供所选择的信息标签对应的叶子类目。另一种实施例可仅提供所选择的新标签对应的叶子类目中用户偏好的叶子类目。例如,用户选择的信息标签为“数码控”,该数码控中对应的叶子类目很多,例如,包括:便携音响、耳机、耳麦、功放等等,但在该信息标签中,用户偏好的叶子类目只有便携音响和耳机,则可只推荐便携音响和耳机,也可优先推荐便携音响和耳机,之后推荐该信息标签中的其他叶子类目耳麦、功放等等。
本申请实施例实现了为用户确定偏好的信息标签,以便在接收到客户端发送的信息标签获取请求情况下将该用户偏好的信息标签提供给客户端,实现辅助将该信息标签推荐给用户。
本申请实施例还提供一种用于推荐信息的方法,如图2中所示是根据本申请一个实施例的用于推荐信息的方法的流程图,该方法可以由客户端设备执行。该方法主要包括如下步骤:
S20、响应于接收到用户的信息标签获取请求,从服务器端获取所述用户偏好的信息标签,所述信息标签为通过用户偏好的叶子类目聚类得到;
S21、展示获取的所述用户偏好的信息标签;
S22、响应于接收到所述用户的信息标签选择请求,从服务器获取所选择的信息标签对应的叶子类目;
S23、推荐所选择的信息标签对应的叶子类目。
下面对上述各步骤做进一步详细介绍。
步骤S20中所述的用户的信息标签获取请求在实际操作中可以为用户的登录请求,也就是在用户登录应用情况下,即认为接收到用户的信息标 签获取请求,需要向用户推荐信息标签,则向服务器端发送该用户的信息标签获取请求,以便从服务器端获取所述用户偏好的信息标签,所述信息标签为通过用户偏好的叶子类目聚类得到,具体的服务器端生成用户偏好的信息标签的方法参照上面实施例中所述,此处不再赘述。
步骤S21为获取用户偏好的信息标签后,展示该用户偏好的信息标签。其中,展示所述信息标签时可以展示该信息标签的名称;或展示信息标签的名称和代表图片。
另外,由于所述用户偏好的信息标签可能包括多个,则可以分多个页面来展示该用户偏好的信息标签。其中一种实施例可按照用户偏好程度的排序来展示该信息标签,也就是用户偏好程度高的优先展示。具体的分多个页面展示为用户推荐的信息标签的方法包括:
在客户端的每一展示页面展示预定数量的信息标签;响应于接收到用户的切换请求,切换展示页面以及所展示的所述用户偏好的信息标签。所述用户的切换请求包括但不限于:接收到用户通过以一定的加速度改变客户的位置发出的切换请求,例如,用户通过摇一摇手机发出切换请求,手机通过内置的加速度传感器感知的该摇一摇的指示,由此确定接收到切换请求;或通过设置的切换按钮接收用户发出的切换请求。
根据本申请的一个实施例,以围绕一个圆心分布的方式来展示所述信息标签,靠近圆心的远近来表示所述用户对该各个信息标签的偏好程度。这种展示方式可以直观地体现信息标签的相关属性。
其中一种展示实例如图3中所示,在用户登录应用后,在第一展示页面为用户展示5个信息标签,如图3中所示,可通过该5个信息标签靠近圆心的远近来表示用户对该5个信息标签的偏好程度,例如,越靠近圆心则表示用户对该信息标签对应的叶子类目越偏好。在用户摇一摇手机后,切换展示下5个信息标签,再摇一摇可展示另外5个信息标签。当然,每个页面所展示的信息标签的数目也可以不等。
以信息标签的方式为用户推荐信息的优点包括:用户可以尽快找到用户偏好的信息,同时,还可以为用户推荐与用户偏好的信息相关的信息。因为本申请实施例在聚类生成信息标签过程中可将不同类目的叶子类目 聚类为同一标签中,例如,将水晶挂件、黄金小铃铛、书签聚类为奇葩物。在用户偏好水晶挂件情况下,会确定为用户推荐的信息标签为奇葩物,当为用户推荐奇葩物时会同时推荐该信息标签(奇葩物)中所包含的其他叶子类目中的信息,包括黄金小铃铛、书签等,实现了扩展推荐信息的目的,同时该扩展推荐的信息为与用户偏好的信息能够聚类成为一类的信息,也就是与用户偏好的信息相关的信息,在实现扩展用户关注点的同时不会对用户造成干扰。
步骤S22为响应于接收到所述用户的信息标签选择请求,从服务器获取所选择的信息标签对应的叶子类目。也就是,当用户选择一信息标签时,则需要进一步展示所选择的信息标签对应的叶子类目。因此向服务器侧发送所述信息标签选择请求,并接收所述服务器提供的所选择的信息标签对应的叶子类目。其中服务器提供所选择的信息标签对应的叶子类目可包括如下两种情况:
一:可提供所选择的信息标签对应的所有叶子类目,并按照用户偏好程度顺序提供该信息标签对应的叶子类目。
二:只提供所选择的信息标签对应的叶子类目中用户偏好的叶子类目。
上述两种情况客户端均可获知所选择的信息标签对应的叶子类目中用户对各叶子类目的偏好程度。因此,步骤S23推荐所选择的信息标签对应的叶子类目时,可按照用户偏好程度的顺序推荐所选择的信息标签对应的叶子类目,即,优先展示所选择的信息标签对应的叶子类目中所述用户偏好的叶子类目(所包含的信息)。
本申请实施例实现了不同用户选择同一信息标签时,为不同用户推荐不同的叶子类目。例如,若确定用户A和用户B偏好的信息标签均包括数码控,而该信息标签对应的叶子类目中,用户A偏好的叶子类目为耳机,而用户B偏好的叶子类目为便携式音响,或者说,用户A偏好的叶子类目中同属于一个信息标签(数码控)的叶子类目中耳机的排序最靠前;用户B偏好的叶子类目中同属于一个信息标签(数码控)的叶子类目中便携式音响的排序最靠前。则在用户A和用户B都选择信息标签数码控时,为用户A优先推荐耳机相关的信息,而为用户B优先推荐便携式音响相 关的信息。因此,本申请实施例实现了区别不同用户的不同偏好,在用户选择同一信息标签情况下以不同的推荐展示顺序展示不同的信息。
所述的优先展示所选择的信息标签对应的叶子类目中所述用户偏好的叶子类目中的信息,也就是在展示用户偏好的叶子类目中的信息的同时也会展示该信息标签中的其他叶子类目中的信息,只是用户偏好的叶子类目中的信息优先展示。这样更有利于用户快速找到需要的、偏好的信息。
本申请实施例还提供一种与上述用于辅助推荐信息的方法对应的装置,如图4中所示,该装置主要包括:
第一确定单元40,用于基于用户行为信息确定用户偏好的叶子类目。
第二确定单元41,用于依据用户偏好的叶子类目确定所述用户偏好的信息标签,所述信息标签为通过信息的叶子类目之间的关系聚类获得的标签。
信息标签提供单元42,用于响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户。
其中,所述第二确定单元41被配置为:
对用户偏好的叶子类目聚类得到所述用户偏好的信息标签。
如图5中所示,所述装置还可包括:
叶子类目提供单元43,用于响应于接收到所述客户端发送的所述用户的信息标签选择请求,按照用户偏好程度的顺序提供所选择的信息标签对应的叶子类目。
本申请实施例还提供一种与上述用于推荐信息的方法对应的装置,如图6中所示,该装置主要包括:
信息标签获取单元60,用于响应于接收到用户的信息标签获取请求,从服务器端获取所述用户偏好的信息标签,所述信息标签为通过用户偏好的叶子类目聚类得到;
信息标签展示单元61,用于展示获取的所述用户偏好的信息标签;
叶子类目获取单元62,用于响应于接收到所述用户的信息标签选择请求,从服务器获取所选择的信息标签对应的叶子类目;
叶子类目展示单元63,用于推荐所选择的信息标签对应的叶子类目。
其中,所述信息标签展示单元61被配置为:
展示获取的所述用户偏好的信息标签的名称;或
展示获取的所述用户偏好的信息标签的名称和代表图片。
所述信息标签展示单元61可被配置为:
在每一展示页面展示预定数量的所述用户偏好的信息标签,响应于接收到用户的切换请求,切换展示页面以及所展示的所述用户偏好的信息标签。
另外,该信息标签展示单元61可被配置为:
以围绕一个圆心分布的方式来展示所述用户偏好的信息标签,通过各信息标签靠近圆心的远近来表示所述用户对各个信息标签的偏好程度。
其中,所述叶子类目获取单元62被配置为:从服务器获取所选择的信息标签对应的叶子类目中所述用户对各叶子类目的偏好程度;
对应的所述叶子类目展示单元63被配置为:
按照用户偏好程度的顺序推荐所选择的信息标签对应的叶子类目。
本申请实施例还提供一种生成信息标签的方法,包括:通过信息的叶子类目之间的关系聚类生成信息标签。通过聚类可将传统的不是一个叶子类目的信息聚类为同一个信息标签中。
本申请实施例还提供一种生成信息标签的装置,包括:用于通过信息的叶子类目之间的关系聚类生成信息标签的单元。
综上所述,本申请实施例以信息标签的方式为用户推荐信息,且信息标签为通过信息的叶子类目之间的关系聚类获得的标签,推荐给用户的信息标签为基于用户偏好的叶子类目确定的。因此,用户不但可以尽快找到需要的、且偏好的信息,而且还可以获得与偏好的信息相关的信息。实现了扩展推荐信息的目的,同时该扩展推荐的信息为与用户偏好的信息能够聚类成为一类的信息,也就是与用户偏好的信息相关的信息,在实现扩展 用户关注点的同时不会对用户造成干扰。
需要注意的是,本申请可在软件和/或软件与硬件的组合体中被实施,例如,可采用专用集成电路(ASIC)、通用目的计算机或任何其他类似硬件设备来实现。在一个实施例中,本申请的软件程序可以通过处理器执行以实现上文所述步骤或功能。同样地,本申请的软件程序(包括相关的数据结构)可以被存储到计算机可读记录介质中,例如,RAM存储器,磁或光驱动器或软磁盘及类似设备。另外,本申请的一些步骤或功能可采用硬件来实现,例如,作为与处理器配合从而执行各个步骤或功能的电路。
另外,本申请的一部分可被应用为计算机程序产品,例如计算机程序指令,当其被计算机执行时,通过该计算机的操作,可以调用或提供根据本申请的方法和/或技术方案。而调用本申请的方法的程序指令,可能被存储在固定的或可移动的记录介质中,和/或通过广播或其他信号承载媒体中的数据流而被传输,和/或被存储在根据所述程序指令运行的计算机设备的工作存储器中。在此,根据本申请的一个实施例包括一个装置,该装置包括用于存储计算机程序指令的存储器和用于执行程序指令的处理器,其中,当该计算机程序指令被该处理器执行时,触发该装置运行基于前述根据本申请的多个实施例的方法和/或技术方案。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第一,第二等词语用来表示名称,而并不表示任何特定的顺序。

Claims (18)

  1. 一种用于辅助推荐信息的方法,其特征在于,包括:
    基于用户行为信息确定用户偏好的叶子类目;
    依据用户偏好的叶子类目确定所述用户偏好的信息标签,所述信息标签为通过信息的叶子类目之间的关系聚类获得的标签;
    响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户。
  2. 如权利要求1所述的方法,其特征在于,依据用户偏好的叶子类目确定所述用户偏好的信息标签包括:
    对用户偏好的叶子类目聚类得到所述用户偏好的信息标签。
  3. 如权利要求1或2所述的方法,其特征在于,所述方法还包括:
    响应于接收到所述客户端发送的所述用户的信息标签选择请求,按照用户偏好程度的顺序提供所选择的信息标签对应的叶子类目。
  4. 一种用于推荐信息的方法,其特征在于,包括:
    响应于接收到用户的信息标签获取请求,从服务器端获取所述用户偏好的信息标签,所述信息标签为通过用户偏好的叶子类目聚类得到;
    展示获取的所述用户偏好的信息标签;
    响应于接收到所述用户的信息标签选择请求,从服务器获取所选择的信息标签对应的叶子类目;
    推荐所选择的信息标签对应的叶子类目。
  5. 如权利要求4所述的方法,其特征在于,所述展示获取的所述用户偏好的信息标签包括:
    展示获取的所述用户偏好的信息标签的名称;或
    展示获取的所述用户偏好的信息标签的名称和代表图片。
  6. 如权利要求4或5所述的方法,其特征在于,所述展示获取的所述用户偏好的信息标签包括:
    在每一展示页面展示预定数量的所述用户偏好的信息标签,响应于接收到用户的切换请求,切换展示页面以及所展示的所述用户偏好的信息标签。
  7. 如权利要求4或5所述的方法,其特征在于,所述展示获取的所述用户偏好的信息标签包括:
    以围绕一个圆心分布的方式来展示所述用户偏好的信息标签,通过各信息标签靠近圆心的远近来表示所述用户对各个信息标签的偏好程度。
  8. 如权利要求4所述的方法,其特征在于,从服务器获取所选择的信息标签对应的叶子类目包括:从服务器获取所选择的信息标签对应的叶子类目中所述用户对各叶子类目的偏好程度;
    其中,推荐所选择的信息标签对应的叶子类目包括:
    按照用户偏好程度的顺序推荐所选择的信息标签对应的叶子类目。
  9. 一种用于辅助推荐信息的装置,其特征在于,包括:
    第一确定单元,用于基于用户行为信息确定用户偏好的叶子类目;
    第二确定单元,用于依据用户偏好的叶子类目确定所述用户偏好的信息标签,所述信息标签为通过信息的叶子类目之间的关系聚类获得的标签;
    信息标签提供单元,用于响应于接收到客户端发送的所述用户的信息标签获取请求,提供所确定的所述用户偏好的信息标签给所述客户端,以便所述客户端推荐所述信息标签给所述用户。
  10. 如权利要求9所述的装置,其特征在于,所述第二确定单元被配置为:
    对用户偏好的叶子类目聚类得到所述用户偏好的信息标签。
  11. 如权利要求9或10所述的装置,其特征在于,所述装置还包括:
    叶子类目提供单元,用于响应于接收到所述客户端发送的所述用户的信息标签选择请求,按照用户偏好程度的顺序提供所选择的信息标签对应的叶子类目。
  12. 一种用于推荐信息的装置,其特征在于,包括:
    信息标签获取单元,用于响应于接收到用户的信息标签获取请求,从服务器端获取所述用户偏好的信息标签,所述信息标签为通过用户偏好的 叶子类目聚类得到;
    信息标签展示单元,用于展示获取的所述用户偏好的信息标签;
    叶子类目获取单元,用于响应于接收到所述用户的信息标签选择请求,从服务器获取所选择的信息标签对应的叶子类目;
    叶子类目展示单元,用于推荐所选择的信息标签对应的叶子类目。
  13. 如权利要求12所述的装置,其特征在于,所述信息标签展示单元被配置为:
    展示获取的所述用户偏好的信息标签的名称;或
    展示获取的所述用户偏好的信息标签的名称和代表图片。
  14. 如权利要求12或13所述的装置,其特征在于,所述信息标签展示单元被配置为:
    在每一展示页面展示预定数量的所述用户偏好的信息标签,响应于接收到用户的切换请求,切换展示页面以及所展示的所述用户偏好的信息标签。
  15. 如权利要求12或13所述的装置,其特征在于,所述信息标签展示单元被配置为:
    以围绕一个圆心分布的方式来展示所述用户偏好的信息标签,通过各信息标签靠近圆心的远近来表示所述用户对各个信息标签的偏好程度。
  16. 如权利要求12所述的装置,其特征在于,所述叶子类目获取单元被配置为:从服务器获取所选择的信息标签对应的叶子类目中所述用户对各叶子类目的偏好程度;
    所述叶子类目展示单元被配置为:
    按照用户偏好程度的顺序推荐所选择的信息标签对应的叶子类目。
  17. 一种生成信息标签的方法,其特征在于,包括:通过信息的叶子类目之间的关系聚类生成信息标签。
  18. 一种生成信息标签的装置,其特征在于,包括:用于通过信息的叶子类目之间的关系聚类生成信息标签的单元。
PCT/CN2016/090814 2015-08-03 2016-07-21 用于推荐及辅助推荐信息的方法及装置 WO2017020714A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510484633.9 2015-08-03
CN201510484633.9A CN106407239A (zh) 2015-08-03 2015-08-03 用于推荐及辅助推荐信息的方法及装置

Publications (1)

Publication Number Publication Date
WO2017020714A1 true WO2017020714A1 (zh) 2017-02-09

Family

ID=57943806

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/090814 WO2017020714A1 (zh) 2015-08-03 2016-07-21 用于推荐及辅助推荐信息的方法及装置

Country Status (2)

Country Link
CN (1) CN106407239A (zh)
WO (1) WO2017020714A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108055387A (zh) * 2017-11-02 2018-05-18 北京金山安全软件有限公司 一种推荐信息显示方法、装置、电子设备及可读存储介质
CN110874432A (zh) * 2018-08-30 2020-03-10 阿里巴巴集团控股有限公司 排序方法、信息推荐方法、系统及装置
CN111125499A (zh) * 2018-10-30 2020-05-08 阿里巴巴集团控股有限公司 数据查询方法及装置
CN113468426A (zh) * 2021-07-01 2021-10-01 北京明略软件系统有限公司 一种信息的推荐方法、装置、电子设备及可读存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107590205A (zh) * 2017-08-23 2018-01-16 阿里巴巴集团控股有限公司 一种业务展示方法、装置及设备
CN107748801B (zh) * 2017-11-16 2022-04-29 北京百度网讯科技有限公司 新闻推荐方法、装置、终端设备及计算机可读存储介质
CN109033180A (zh) * 2018-06-26 2018-12-18 深圳市爱的网络科技有限公司 一种信息推送方法、装置、计算机装置及计算机可读存储介质
CN110059256B (zh) * 2019-04-26 2023-11-07 北京沃东天骏信息技术有限公司 用于展示信息的系统、方法及装置
CN112464075B (zh) * 2019-09-06 2023-11-03 百度在线网络技术(北京)有限公司 智能音箱的应用推荐方法、装置及电子设备
CN115168740B (zh) * 2022-09-06 2022-11-15 网娱互动科技(北京)股份有限公司 一种基于大数据分析生成营销任务的方法和系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102882936A (zh) * 2012-09-06 2013-01-16 百度在线网络技术(北京)有限公司 云推送的方法、系统和装置
CN102902753A (zh) * 2012-09-20 2013-01-30 北京奇虎科技有限公司 用于补全搜索词及建立个体兴趣模型的方法及装置
CN103810192A (zh) * 2012-11-09 2014-05-21 腾讯科技(深圳)有限公司 一种用户的兴趣推荐方法和装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102007037963A1 (de) * 2007-08-11 2009-02-12 Sikora Aktiengesellschaft Verfahren zur Visualisierung der Exzentrizität von Kabeln bei der Exzentrizitätsmessung der Kabel
CN101430708A (zh) * 2008-11-21 2009-05-13 哈尔滨工业大学深圳研究生院 一种基于标签聚类的博客层次分类树构建方法
US20140280178A1 (en) * 2013-03-15 2014-09-18 Citizennet Inc. Systems and Methods for Labeling Sets of Objects
CN104216881A (zh) * 2013-05-29 2014-12-17 腾讯科技(深圳)有限公司 一种个性化标签的推荐方法及装置
CN103577549B (zh) * 2013-10-16 2017-02-15 复旦大学 一种基于微博标签的人群画像系统和方法
CN104090886B (zh) * 2013-12-09 2015-09-09 深圳市腾讯计算机系统有限公司 构建用户实时画像的方法及装置
CN103970858A (zh) * 2014-05-07 2014-08-06 百度在线网络技术(北京)有限公司 推荐内容确定系统和方法
CN104281699B (zh) * 2014-10-15 2017-11-17 百度在线网络技术(北京)有限公司 搜索推荐方法及装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102882936A (zh) * 2012-09-06 2013-01-16 百度在线网络技术(北京)有限公司 云推送的方法、系统和装置
CN102902753A (zh) * 2012-09-20 2013-01-30 北京奇虎科技有限公司 用于补全搜索词及建立个体兴趣模型的方法及装置
CN103810192A (zh) * 2012-11-09 2014-05-21 腾讯科技(深圳)有限公司 一种用户的兴趣推荐方法和装置

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108055387A (zh) * 2017-11-02 2018-05-18 北京金山安全软件有限公司 一种推荐信息显示方法、装置、电子设备及可读存储介质
CN110874432A (zh) * 2018-08-30 2020-03-10 阿里巴巴集团控股有限公司 排序方法、信息推荐方法、系统及装置
CN110874432B (zh) * 2018-08-30 2023-04-18 阿里巴巴集团控股有限公司 排序方法、信息推荐方法、系统及装置
CN111125499A (zh) * 2018-10-30 2020-05-08 阿里巴巴集团控股有限公司 数据查询方法及装置
CN113468426A (zh) * 2021-07-01 2021-10-01 北京明略软件系统有限公司 一种信息的推荐方法、装置、电子设备及可读存储介质
CN113468426B (zh) * 2021-07-01 2024-01-30 北京明略软件系统有限公司 一种信息的推荐方法、装置、电子设备及可读存储介质

Also Published As

Publication number Publication date
CN106407239A (zh) 2017-02-15

Similar Documents

Publication Publication Date Title
WO2017020714A1 (zh) 用于推荐及辅助推荐信息的方法及装置
CA2996876C (en) Suggesting object identifiers to include in a communication
AU2017245374B2 (en) Index configuration for searchable data in network
CN105205089B (zh) 账户推荐
EP3022639B1 (en) Object based contextual menu controls
US9013426B2 (en) Providing a sense of touch in a mobile device using vibration
US11334642B2 (en) Self-learning webpage layout based on history data
US20230156075A1 (en) Real-time content integration based on machine learned selections
CN113348650B (zh) 交互信息界面的显示方法、系统及机器可读存储介质
US20160292288A1 (en) Comments analyzer
US11070887B2 (en) Video content deep diving
US10372222B1 (en) System and method for filtering content based on gestures
US10230775B2 (en) Message pipeline for suggesting audiences of third-party published articles
US11019379B2 (en) Stage-based content item selection and transmission
JP2016012337A (ja) 検索結果表示方法および装置
WO2017100010A1 (en) Organization and discovery of communication based on crowd sourcing
US10645191B1 (en) User controlled composition of content
TW200841194A (en) Using structured data for online research
JP6213660B2 (ja) 情報管理装置、情報共有システム、制御方法、及びコンピュータ読み取り可能な記録媒体
US20180121510A1 (en) Suggesting object identifiers and recipients for communication
US20170048341A1 (en) Application usage monitoring and presentation
WO2022199494A1 (zh) 一种基于用户兴趣的内容推荐方法与终端设备
US20220138799A1 (en) Streamless content aware ad insertion
US10489026B2 (en) Accessible user interface for application with moving items
JP5420983B2 (ja) プラットフォームシステム

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: 16832202

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: 16832202

Country of ref document: EP

Kind code of ref document: A1