WO2020087386A1 - 内容推荐方法、装置、移动终端及服务器 - Google Patents

内容推荐方法、装置、移动终端及服务器 Download PDF

Info

Publication number
WO2020087386A1
WO2020087386A1 PCT/CN2018/113166 CN2018113166W WO2020087386A1 WO 2020087386 A1 WO2020087386 A1 WO 2020087386A1 CN 2018113166 W CN2018113166 W CN 2018113166W WO 2020087386 A1 WO2020087386 A1 WO 2020087386A1
Authority
WO
WIPO (PCT)
Prior art keywords
label
list
user
tag list
tag
Prior art date
Application number
PCT/CN2018/113166
Other languages
English (en)
French (fr)
Inventor
陈崇勇
Original Assignee
深圳市欢太科技有限公司
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to CN201880099091.5A priority Critical patent/CN112930669B/zh
Priority to PCT/CN2018/113166 priority patent/WO2020087386A1/zh
Priority to EP18938863.0A priority patent/EP3873065B1/en
Publication of WO2020087386A1 publication Critical patent/WO2020087386A1/zh
Priority to US17/242,186 priority patent/US20210248198A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/535—Tracking the activity of the user
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/55—Push-based network services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G06Q30/0256—User search

Definitions

  • This application relates to the field of Internet technology, and more specifically, to a content recommendation method, device, mobile terminal, and server.
  • this application proposes a content recommendation method, device, mobile terminal, and server to improve the above problems.
  • an embodiment of the present application provides a content recommendation method.
  • the method includes: acquiring a first tag list, the first tag list is generated according to a tag corresponding to content viewed by a user within a target time period; acquiring a second A tag list, the second tag list is jointly generated based on the first tag list and the stored recommended tag list; acquiring a tag selected by the user from the second tag list to generate a new recommended tag list; pushing to a mobile terminal The content corresponding to the tag in the new recommended tag list.
  • an embodiment of the present application provides a content recommendation method.
  • the method includes: acquiring and displaying a second tag list from a server, the second tag list is generated according to the first tag list and the stored recommended tag list , The first tag list is generated based on the tags corresponding to the content browsed by the user in the target time period; receiving the user's selection of the tags in the second tag list, and returning the selection result to the server, for instructing the server to select according to the selection As a result, a new recommended tag list is generated; the content recommended by the receiving server according to the new recommended tag list.
  • an embodiment of the present application provides a content recommendation apparatus.
  • the apparatus includes: a first tag list acquisition module, configured to acquire a first tag list, the first tag list according to a user's browsing within a target time period Generate tags corresponding to content; a second tag list acquisition module, used to acquire a second tag list, which is generated based on the first tag list and the stored recommended tag list; a recommended tag list acquisition module, used To obtain a label selected by the user from the second label list to generate a new recommended label list; a push module is used to push the content corresponding to the label in the new recommended label list to the mobile terminal.
  • an embodiment of the present application provides a content recommendation apparatus.
  • the apparatus includes: a second tag list acquisition module configured to acquire and display a second tag list from a server, and the second tag list is based on the first tag The list and the stored recommended tag list are generated together, the first tag list is generated according to the tags corresponding to the content browsed by the user in the target time period; the selection module is used to receive the user's selection of tags in the second tag list, and The selection result is returned to the server for instructing the server to generate a new recommended tag list according to the selection result; the content receiving module is used for receiving content recommended by the server according to the new recommended tag list.
  • an embodiment of the present application provides a server, including: one or more processors; a memory; and one or more programs. Wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to perform the method corresponding to the above server.
  • an embodiment of the present application provides a mobile terminal, including: one or more processors; a memory; and one or more programs.
  • the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to perform the method corresponding to the above mobile terminal.
  • an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored, and the program code can be called by a processor to execute the method corresponding to the foregoing mobile terminal.
  • the content recommendation method, device, mobile terminal, and server provided by the embodiments of the present application generate a first tag list according to tags of content browsed by a user, and generate a second tag list based on the first tag list and the existing recommended tag list.
  • the user can select the tag of interest from the second tag list to generate a new recommended tag list for content recommendation. Therefore, when content is pushed to the mobile terminal according to the new recommended tag list, relative to the previously stored recommended tag list, it not only pushes the content that is of interest to the user, but also removes the content that is not of interest to the user, improving the push effect.
  • FIG. 1 shows an interactive schematic diagram of a content recommendation system provided by an embodiment of the present application.
  • FIG. 2 shows a flowchart of a content recommendation method provided by an embodiment of the present application.
  • FIG. 3 shows a flowchart of a content recommendation method provided by another embodiment of the present application.
  • FIG. 4 shows a flowchart of a content recommendation method provided by another embodiment of the present application.
  • FIG. 5 shows a schematic display diagram of the label provided by the embodiment of the present application.
  • FIG. 6 shows another schematic view of the label provided by the embodiment of the present application.
  • FIG. 7 shows another schematic diagram of displaying a label provided by an embodiment of the present application.
  • FIG. 8 shows another schematic diagram of displaying a label provided by an embodiment of the present application.
  • FIG. 9 is a schematic diagram of still another display of the label provided by the embodiment of the present application.
  • FIG. 10 shows a flowchart of a content recommendation method provided by still another embodiment of the present application.
  • FIG. 11 shows a signaling interaction diagram of a content recommendation method provided by still another embodiment of the present application.
  • FIG. 12 shows a functional block diagram of a content recommendation device provided by an embodiment of the present application.
  • FIG. 13 shows a functional block diagram of a content recommendation device provided by another embodiment of the present application.
  • FIG. 14 shows a structural block diagram of a mobile terminal provided by an embodiment of the present application.
  • FIG. 15 shows a structural block diagram of a server provided by an embodiment of the present application.
  • 16 is a storage unit for storing or carrying program code for implementing a content recommendation method according to an embodiment of the present application.
  • FIG. 17 is another storage unit for storing or carrying program code for implementing the content recommendation method according to the embodiment of the present application.
  • mobile terminals As the functions of mobile terminals become more and more perfect, there are more and more applications that meet the various needs of users, and users can browse more and more information through mobile terminals, such as various news web pages, comment articles, Q & A content, and videos Wait. Specific users can browse information through various applications, such as news application (Application, APP), browser, Q & A APP, video APP, etc.
  • applications such as news application (Application, APP), browser, Q & A APP, video APP, etc.
  • users are not interested in all information, and different users may be interested in different information. For example, some users may be interested in sports-related content, some users may be interested in shopping content, and some users may be interested in star entertainment. Interested in related content. If all content is pushed to each mobile terminal indiscriminately, the user needs to find interesting content from the large amount of information received by the mobile terminal, which wastes the user's time and reduces the user's experience. Therefore, when pushing content to a mobile terminal, content that is of interest to the user corresponding to the mobile terminal can be pushed.
  • each content can be classified, such as technology, education, star, sports, constellation, history, etc.
  • the specific classification method and the classified category are not limited in the embodiments of the present application. Then push according to the category that the user is interested in.
  • each category can be represented by a label, to which category a piece of content belongs, it means that there is a label corresponding to the category.
  • the content corresponding to each label indicates that it belongs to the category corresponding to the label.
  • each piece of content can be divided into one or more categories, corresponding to one or more different tags.
  • a piece of news can belong to three categories of education, sports, and history at the same time, corresponding to three labels of education, sports, and history.
  • the label is just a way to describe the category, and any form that classifies the content can be considered as a label used to represent the category.
  • tags can be provided for the user to select, and the tag selected by the user is used as the user's interest tag, that is, the tag that the user is interested in.
  • the content corresponding to the user's interest tag is mainly pushed.
  • a label selection interface may be set in the application, and the user may select a label of interest from the label selection interface at any time.
  • the content corresponding to the selected interest tag is pushed.
  • the tags that the user is interested in are determined according to the user's browsing of various contents within a period of time. For example, according to the content browsed by the user, an interest tag value is generated by weighting. For example, a tag with a high browsing frequency and a tag with a long browsing time are used as the user's interest tag. Push the content corresponding to the user's interest tag to the mobile terminal.
  • the content displayed on the mobile terminal may be provided with an uninteresting setting interface. If the user is not interested in setting the interface, the related content will no longer be pushed to the user or the push of related content will be reduced. For example, under the news website of the browser, each news item is set with an uninteresting button. If the user clicks the button, it means that the user is not interested in the news or the news, and no longer pushes to the mobile terminal.
  • the user may no longer be interested in some initially selected interest tags, but will still use the tag as the user's interest tag and push it to the user related information.
  • the user may not be able to determine whether the tag corresponds to only the category name corresponding to the tag in the tag selection interface
  • the content is of interest, and the content of interest to the user may not be accurately selected by the label.
  • the content pushed to the user is not necessarily of interest to the user.
  • the content of interest to the user is pushed according to the content browsed by the user, if the user has not searched and browsed some content that the user will be interested in, the relevant content will not be pushed to the user. Content, so as to miss the content of interest to some users. Or the user has unintentionally clicked on some uninteresting content, and will continue to push the content that is not of interest to the user, resulting in inaccurate push and affecting the user's browsing experience.
  • the user can directly set the uninteresting under the uninteresting content item, it can only be set for a single content item or category, and other uninteresting content will still be pushed to the user.
  • the embodiments of the present application provide a content recommendation method, device, mobile terminal, and server, which provide the user with a list of tags based on the content viewed by the user and the tags previously selected by the user, so that the user can select the previous tag As well as recently viewed content, select the tags of interest. Then push the content according to the label selected by the user, so that the pushed content is more accurate, and the content that the user may be interested in is less missed.
  • the content recommendation method, device, mobile terminal and server provided in the embodiments of the present application can be implemented through the interaction between the server and the mobile terminal.
  • the server generates a tag list for the user to select and send based on the user's browsing and the tag generated by the previous selection
  • To the mobile terminal the mobile terminal displays the tag list to allow the user to perform a selection operation.
  • the mobile terminal returns the user's selection result to the server, so that the server can push according to the user's selection.
  • FIG. 1 shows a schematic diagram of an interaction between the server 100 and the mobile terminal 200 in the embodiment of the present application.
  • the mobile terminal 200 and the server 100 perform data interaction through a network, which may be a wireless network or a wired network.
  • the mobile terminal 200 may be a smart device such as a mobile phone, a tablet computer, a computer, an e-reader, a wearable electronic device, an in-vehicle device, etc., which is not specifically limited herein.
  • the mobile terminal 200 can run a client, and the server 100 can run a server.
  • the mobile terminal 200 runs a browser or various APPs that can browse content, and the user can browse the content through the client.
  • the server 100 corresponds to a server corresponding to the client.
  • the client running in the mobile terminal may execute the method corresponding to the mobile terminal in the embodiment of the present application, and the corresponding server in the server may be used to execute the method corresponding to the server in the embodiment of the present application.
  • the client can perform data interaction with the server 100 through the network, thereby implementing data interaction with the server running on the server 100.
  • a content recommendation method provided by an embodiment of the present application can be applied to a server.
  • the method is not limited to be applied to a server, but can also be applied to mobile terminals, etc.
  • the present application mainly uses a server as an example for description. Please refer to Figure 2, the method includes:
  • Step S110 Acquire a first tag list, which is generated according to the tags corresponding to the content browsed by the user within the target time period.
  • the user browses the content through the mobile terminal, and the browsed content corresponds to tags respectively, so that the tag corresponding to the content browsed by the user within the target time period can be obtained.
  • a first tag list may be generated.
  • the first tag list includes one or more tags, and each tag represents a category of content.
  • Step S120 Acquire a second tag list, which is jointly generated according to the first tag list and the stored recommended tag list.
  • a recommended tag list may be stored, and the recommended tag list is a basis for the server to push content to the mobile terminal.
  • the recommended tag list includes one or more tags, and the server pushes the content corresponding to the tag in the recommended tag list to the mobile terminal.
  • the server generates the second tag list according to the tags combined with the first tag list and the stored recommended tag list. That is, the second tag list includes the tags in the first tag list and the recommended tag list.
  • Step S130 Acquire a label selected by the user from the second label list, and generate a new recommended label list.
  • the second tag list is a list of tags provided to the user for selection, that is, the user can select the tag of interest from the second tag list.
  • the tag selected by the user from the second tag list indicates that the user is interested in the content corresponding to the tag, and may push the content corresponding to the tag to the user. Therefore, the server may acquire the tag selected by the user from the second tag list, generate a new recommended tag list, and replace the previously stored recommended tag list as a basis for pushing content to the mobile terminal.
  • Step S140 Push the content corresponding to the tag in the new recommended tag list to the mobile terminal.
  • the server pushes the content to the mobile terminal, the content corresponding to the tag in the new recommended tag list is pushed. That is to say, when pushing content to the mobile terminal, the content of the related category of the interest tag newly selected by the user is pushed.
  • the execution time of step S140 may have a certain interval from the execution time of step S130, and the interval is not limited.
  • the content corresponding to the new recommended tag list is pushed until the recommended tag list is regenerated.
  • the mobile terminal may store a recommended tag list, and acquire the first tag list from the server. Then, the second label list is jointly generated according to the first label list and the stored recommended label list. After the user selects a tag in the second tag list, a new recommended tag list is generated according to the user's selection. The mobile terminal can obtain the corresponding content from the server according to the new recommended tag list for display and pushing.
  • the second tag list is jointly generated and used as the basis for the user to select the tag.
  • the second tag list includes not only the user ’s previously selected interesting tags, but also the tags that the user has recently viewed that may be of interest, so as to minimize the omission of tags that may be of interest to the user, and allow the user to select the previously selected tags Interest tag deletion, improve the accuracy and completeness of the tags in the recommended tag list, and improve the push effect.
  • FIG. 3 shows a content recommendation method provided by an embodiment of the present application, which is applied to a mobile terminal. Please refer to Figure 3, the method includes:
  • Step S210 Obtain and display a second tag list from the server.
  • the second tag list is generated based on the first tag list and the stored recommended tag list.
  • the first tag list is based on the content of the user's browsing within the target time period. Label generation.
  • the mobile terminal may obtain the second tag list from the server for the user to select a tag.
  • the second tag list is jointly generated by the server according to the first tag list and the recommended tag list stored by the server.
  • the mobile terminal displays the second tag list, and specifically displays each tag in the second tag list, and provides selection authority for each tag.
  • the user can select each displayed label, that is, the user can select whether each label is a label of interest to him.
  • Step S220 Receive the user's selection of the label in the second label list, and return the selection result to the server, for instructing the server to generate a new recommended label list according to the selection result.
  • the mobile terminal When the user performs a selection operation on the mobile terminal, the mobile terminal receives the user's selection of the label in the second label list. When the user finishes selecting the label in the second label list, the mobile terminal may return the selection result to the server.
  • the selection result includes the user's selection information, that is, through the selection result, it can be known which tags in the second tag list the user selects as the tags of interest. Therefore, the server can generate a new recommended tag list according to the tag selected by the user in the selection result.
  • Step S230 Receive content recommended by the server according to the new recommended tag list.
  • the mobile terminal When the server pushes content to the mobile terminal according to the new recommended tag list, the mobile terminal is used to receive the server's pushed content. It can be understood that there may be a certain time interval between step S230 and step S220, and the time interval is not limited. In other words, when the mobile terminal returns the selection result to the server, and the server generates a new recommended tag list, the mobile terminal may receive the content pushed by the server according to the new tag list. Or the next time the mobile terminal opens the relevant application program, the content push of the server is received.
  • the second label list provided by the mobile terminal to the user for selection includes the label corresponding to the content browsed by the user within the target time period and the label previously selected by the user, thereby making the user-selectable label more complete
  • the completeness and accuracy of user selections can improve the content push effect.
  • a content recommendation method provided by an embodiment of the present application is applied to a content recommendation system.
  • the content recommendation system is shown in FIG. 1 and includes a mobile terminal and a server that interact with each other. As shown in Figure 4, the method includes:
  • Step S310 The server obtains a first tag list, and the first tag list is generated according to the tags corresponding to the content browsed by the user in the target time period.
  • the server may obtain tags corresponding to the content browsed by the user in the target time period according to the user's browsing of the content in the target time period.
  • a mobile terminal may be used as a user, or a user account may be used as a user.
  • the mobile terminal can feed back the user's browsing situation to the server, such as when the user opens the content and when the user closes the content.
  • the server can know which content the user has browsed in the target time period, and then according to the correspondence between the content and the label, the server can know which tags the user has browsed in the target time period.
  • the tags viewed by the user are tags corresponding to the content viewed by the user.
  • the mobile terminal may count which tags corresponding to the content the user browsed according to the user's click on and off of the content and operations on the content browsing interface, and then feed back the statistical results to the server.
  • the feedback may be periodic feedback, feedback when the corresponding application is closed, or the server actively obtains it from the mobile terminal. If the mobile terminal initiates a request to update the recommended tag list to the server, then when the mobile terminal initiates a request to update the recommended tag list, the latest statistical user browsing of the tag is fed back to the server. Therefore, the server can obtain which tags the user has viewed in the target time period.
  • the server may select a tag from the tags viewed by the user within the target time period to generate a first tag list.
  • the server may select all the tags viewed by the user in the target time period to generate a first tag list, that is, the tags in the first tag list are tags viewed by the user in the target time period.
  • the server may also select some tags viewed by the user in the target time period to generate a first tag list, that is, the tags in the first tag list are partial tags viewed by the user in the target time period.
  • the server may also obtain the number of times the user browses each tab. Among them, the content corresponding to a certain label is opened and browsed once, and it can be counted that the label is browsed once. For example, if a user browses content A, content B, content C, and content D within the target time period, content A corresponds to label a, content B corresponds to label b, content C corresponds to label a, and content D corresponds to label c, In the target time period, the user browsed the content corresponding to the tags a, b, and c, in which the tag a was browsed twice, and the tag b and the tag c were browsed once.
  • the server selects some tags from the tags viewed by the user within the target time period to generate the first tag list, it may select tags whose browsing times are greater than the target number to generate the first tag list.
  • the specific value of the target number of times is not limited in the embodiment of the present application, and can be set according to actual conditions.
  • the number of tags whose browsing times are greater than the target number may be too small, so if the first tag list is generated with tags whose browsing times are greater than the target number, the tags in the first tag list may be Not comprehensive. Therefore, the acquired tags may be sorted according to the number of views from high to low, and then according to the sorting result, the target number of tags may be selected from high to low to generate the first tag list. For example, if the target number is set to 10, after sorting all the tags viewed by the user in the target time period from high to low, then select 10 tags from high to low in the sorting result to generate the first tag list.
  • a label with a browsing number greater than a target number may be selected from the acquired labels first, and when the number of labels with a browsing number greater than the target number is less than the target number, the A certain number of tags are selected in the tag to complement the target number according to the number of views from high to low.
  • the server may also know the browsing time of each piece of content, so as to count the browsing time corresponding to each tag.
  • the browsing time of each tag may be that the browsing time of each piece of browsed content corresponding to the tag is accumulated. For example, a user browses content A, content B, and content C within a target time period, content A corresponds to label a, content B corresponds to label b, and content C corresponds to label a, where content A browses for x minutes and content B browses for y minutes If the content C is browsed for z minutes, the user can obtain that the time for the user to browse the tag a is x + z minutes and the time for the tag b is y minutes in the target time period.
  • the server selects some tags from the tags browsed by the user in the target time period to generate the first tag list, it may select tags with a browsing time greater than the target time length to generate the first tag list.
  • the specific value of the target time length is not limited in the embodiments of the present application, and can be set according to actual conditions.
  • the number of tags whose browsing time is greater than the target time length may be too small, so if the first tag list is generated with tags whose browsing time is greater than the target time length, it may be 'S label is not comprehensive. Therefore, the acquired tags can be sorted according to the length of browsing time from high to low, and then according to the sorting result, the target number of tags can be selected from high to low to generate the first tag list. For example, the target number is set to 10, after sorting all the tags viewed by the user in the target time period according to the length of browsing time from high to low, select 10 tags from high to low in the sorting result to generate the first tag list .
  • the target time period may be a time period between the time when the recommended tag list was generated last time and the current time. That is to say, after the previous recommended tag list is generated, content recommendation is performed according to the recommended tag list, and at the same time, the user's browsing of the content is recounted to obtain the browsing status of each tag.
  • the target time period may also be a pre-stored time period.
  • the target time period may be a length of time stored according to actual statistical requirements.
  • the target time period represents a period of time before the current time. For example, if the target time period is one week, the browsing status of the tag within a week before the current time can be counted.
  • Step S320 The server obtains a second label list, which is jointly generated according to the first label list and the stored recommended label list.
  • the first tag list is generated based on the user's actual browsing content, so that the first tag list may represent the user's conscious or unconscious browsing preferences within the target time period.
  • the statistics of the first tag list may be missed.
  • the statistics of the first tag list may also be missed. Therefore, in the embodiment of the present application, the first tag list and the stored recommended tag list may also be combined to generate a second tag list for user selection.
  • all tags in the first tag list and all tags in the recommended tag list may be selected to generate the second tag list.
  • the first tag list and the recommended tag list may be combined as two sub-tag lists to generate the second tag list.
  • the second tag list includes two sub-tag lists, and the tags in each sub-tag list are adjacent to each other. That is to say, in the second label list, each label in the first label list is adjacent to each other, and each label in the recommended label list is adjacent to each other.
  • only two sub-tag lists can be set to display adjacent tags. You can also set the two sub-label categories to display corresponding to their label list names, which is convenient for users to distinguish.
  • all tags in the first tag list and all tags in the recommended tag list may be sorted according to browsing times or browsing times to generate a second tag list.
  • the sorting may be from high to low, which is convenient for the user to select the content of interest.
  • the ranking may also be from low to high, which is not limited in the embodiments of the present application.
  • a partial label and a label in the first label list may be selected from the recommended label list to generate a second label list.
  • the standard for selecting tags from the recommended tag list is not limited, and may be selecting tags with a browsing time greater than a predetermined number of times, or selecting tags with a browsing time greater than a predetermined length of time, or selecting a specified number of tags with the most views Or, select the specified number of tags with the largest browsing time.
  • a tag with big data statistics may be added to generate a second tag list.
  • the label of this big data statistic corresponds to the type that most users prefer.
  • the server can count the browsing status of all users, and obtain the total number of browsing times or the total browsing time of each tag being browsed by all users. Add a certain number of tags with the highest browsing times or the longest browsing time as the tags for big data statistics to the selection results of the first tag list and the recommended tag list.
  • some labels in the second label list may be set as selected labels.
  • the label set as selected means that the default user selects it. If the user does not cancel the selection, the selected label is used to generate a list of recommended labels.
  • the tag in the second tag list that the user has viewed more than a specified number of times may be set as the selected tag.
  • the specific value of the specified number of times is not limited in the embodiments of the present application.
  • the label in the second label list whose user browsing time is greater than the specified time length may be set as the selected label.
  • the specific value of the specified time length is not limited in the embodiments of the present application.
  • the recommended tag list for generating the second tag list together with the first tag list is the recommended tag list stored in the server.
  • the stored recommended tag list is the recommended tag list obtained and stored the previous time, and is used as a standard for pushing content to the mobile terminal. That is, before obtaining a new recommended tag list this time, the server pushes the content to the mobile terminal according to the recommended tag list obtained last time.
  • the stored recommended tag list may be obtained based on the previous recommended tag list and the content browsed by the user in the target time period in front of it.
  • a mobile terminal when the corresponding application starts the connection server for the first time on the mobile terminal, it does not have the previous recommended tag list and the user's browsing history, and multiple tags can be pushed to the mobile terminal It is for the user to choose to generate the first recommended tag list according to the user's choice.
  • a user account is used as a user, when the corresponding application logs in to a user account for the first time, it does not have the previous recommended tag list and the user's browsing history. At this time, multiple tags can be pushed to the mobile terminal for the user to choose To generate the first recommended tag list based on the user's selection.
  • the server sends the generated second tag list to the mobile terminal, so that the mobile terminal displays the second tag list to the user for selection.
  • Step S330 The mobile terminal obtains and displays a second tag list from the server, the second tag list is generated based on the first tag list and the stored recommended tag list, and the first tag list is based on the content browsed by the user in the target time period The corresponding label is generated.
  • the mobile terminal can obtain the second tag list generated by the server.
  • the mobile terminal displays the second label list so that the user can select a label from the second label list.
  • the mobile terminal displaying the labels of the second label list may be consistent with the display manner set by the second label list on the server.
  • the second tag list includes two sub-tag lists, and the tags in each sub-tag list are adjacent to each other. If only two sub-tag lists are set to display their respective tags next to each other, the second tag list may be displayed as shown in FIG. 5, the label in the dotted frame 201 represents the tag in the first tag list, and the dotted frame 202 The label in represents the label in the previous recommended label list. It is understandable that the dotted frame may not be displayed when the mobile terminal is displayed. If the two sub-label categories are set to be displayed corresponding to their label list names, the display may be as shown in FIG. 6.
  • the specific name of the tag list name is not limited in the embodiment of the present application. For example, in FIG. 6, “recently viewed” indicates the first tag list, and “previous setting” indicates the list of recommended tag obtained last time.
  • the label set as selected may be selected.
  • the label display format is displayed to distinguish it from the unselected label display, such as highlighting or graying. For example, as shown in FIG. 7, if the label a is set as the default selection on the server, the mobile terminal displays the label a as a selected label in a grayed-out form for display.
  • Step S340 The mobile terminal receives the user's selection of the label in the second label list, and returns the selection result to the server to instruct the server to generate a new recommended label list according to the selection result.
  • the user can select the tag he is interested in in the second tag list displayed on the mobile terminal.
  • the mobile terminal receives the user's selection of a certain tag, and if the tag itself is an unselected tag, the tag is set as the selected tag.
  • the label selected by the user can also be displayed in the display form of the selected label. For example, as shown in FIG. 8, if the user clicks on the label c, the label c is set as the selected label.
  • the user can also deselect the selected label. For example, if a user clicks on a selected label, the selected label is set as an unselected label. For example, if the user clicks the label a shown in FIG. 8 again, as shown in FIG. 9, the label a is set as an unselected label.
  • the selected label is set to the unselected label; if the selection operation of the unselected label is received, the unselected The label is set to the selected label.
  • the mobile terminal When the user selection is completed, the mobile terminal returns the selection result to the server. Wherein, when receiving the corresponding instruction triggered by the user and ending the selection, the selection result is returned to the server.
  • the mobile terminal may return all the tags in the second tag list to the server, and set the parameters in which the tag selected by the user is different from the unselected tags, so that the server can return the tags from the mobile terminal
  • the label selected by the user is identified in.
  • the mobile terminal may add a selected identifier to the tag selected by the user in the second tag list.
  • the mobile terminal returns a second label list carrying the selected identification to the server, for instructing the server to generate a new recommended label list through the label with the selected identification.
  • the second label list may also be divided into a selected label sub-list and an unselected label sub-list. And put the label selected by the user into the selected sub-list of tags, and put the label not selected by the user into the un-selected sub-list of tags. Therefore, the server that receives the second label list returned by the mobile terminal can only read the label in the selected label sub-list to obtain the label selected by the user.
  • the mobile terminal may discard the unselected labels in the second label list and simply return the selected labels to the server.
  • Step S350 The server acquires the label selected by the user from the second label list, and generates a new recommended label list.
  • the server may receive the selection result returned by the mobile terminal, and may obtain the label selected by the user from the second label list according to the selection result. For example, if the mobile terminal returns the tags in the entire second tag list, the server reads the tags selected by the user; if the mobile terminal returns only the tags selected by the user, all the received tags are used as the The selected label in the second label list.
  • the server may generate a new recommended tag list from the tags selected by the user in the selection result. Specifically, the server generates a tag list from all tags selected by the user, and the tag list is used as a new recommended tag list to replace the previously generated recommended tag list. Store the new recommended tag list and use it as a standard for subsequent content recommendation.
  • the steps executed by the server and the steps executed by the mobile terminal do not necessarily have a strict sequence of steps, and may have a certain intersection.
  • this step of S350 includes multiple sub-steps: sending the second tag list to the mobile terminal for instructing the mobile terminal to provide the tags in the second tag list to the user for selection; receiving the mobile terminal according to The selection result returned by the user's selection operation; the tags selected by the user in the selection result are generated into a new recommended tag list.
  • the sub-step of sending the second tag list to the mobile terminal is executed before step S330, receiving the selection result returned by the mobile terminal according to the user's selection operation, and generating a new recommended tag list from the tags selected by the user in the selection result This sub-step is performed after step S340.
  • Step S360 The server pushes the content corresponding to the tag in the new recommended tag list to the mobile terminal.
  • the server pushes the content corresponding to the tag in the new recommended tag list.
  • the timing of the server pushing content to the mobile terminal is not limited.
  • a push may be performed once a new recommended tag list is generated.
  • content may be pushed to the mobile terminal periodically according to the latest recommended tag list.
  • the specific push cycle is not limited in the embodiments of the present application.
  • the server receives the content recommendation request sent by the mobile terminal.
  • the content corresponding to the recommended tag list is searched according to the content recommendation request.
  • the content corresponding to the newly acquired recommended tag list is searched. Then return the found content to the mobile terminal.
  • the content may be pushed according to the recommended label list when the application related to the recommended label list is opened; or when the application related to the recommended label list is used to log in to the account, the content may be pushed according to the recommended label list.
  • the number and method of the content pushed by the server to the mobile terminal each time are not limited in the embodiments of the present application, and may be based on the push methods commonly used in the related art.
  • all content generated between the last push and the current push may be pushed.
  • the number of pieces of content that the mobile terminal can display at a time is limited, and the target number of pieces of content can also be pushed to the mobile terminal each time it is pushed. Or each time it is pushed, the content of the latest period is pushed, and the specific length of the latest period is not limited. Or during the push, the batch is pushed to the mobile terminal in batches from near to far according to the content generation time. When the mobile terminal receives and displays a batch, it sends the next batch to the mobile terminal.
  • Step S370 The mobile terminal receives the content recommended by the server according to the new recommended tag list.
  • the server sends the pushed content to the mobile terminal, and the mobile terminal receives correspondingly. And, the mobile terminal displays the received content.
  • the push content corresponding to the tag received from the server by the content of the mobile terminal may be part of the content information, such as the title, introduction, or beginning part of the content.
  • the mobile terminal receives the trigger for the corresponding content, it initiates a request to obtain the content to the server, and the server sends the complete information of the corresponding content to the mobile terminal, and the mobile terminal displays it.
  • a second tag list is generated based on the stored recommended tag list and the user's browsing content, and the user can select the tag of interest from the second tag list, so that the user's selection basis is based on recent browsing results
  • the selectable benchmark is more comprehensive and the selection is more accurate, so that the new recommended label list generated based on the selection result is more comprehensive and accurate.
  • FIG. 10 and 11 illustrate a content recommendation method provided by an embodiment of the present application, which is applied to the content recommendation system shown in FIG. 1.
  • this method it is also possible to determine whether to update the recommended tag list according to the change of user preferences.
  • the method includes:
  • Step S410 The server obtains a first tag list, and the first tag list is generated according to the tags corresponding to the content browsed by the user in the target time period.
  • the server obtains the first tag list for generating the recommended tag list.
  • the specific time when the server acquires the first label list is not limited in the embodiment of the present application, and the trigger condition for acquiring the first label list may be one or more of the following.
  • the server may acquire the first tag list when receiving the request for updating the recommended tag list initiated by the mobile terminal.
  • the request to update the recommended tag list may be initiated by the mobile terminal when the mobile terminal receives the user's update recommended list trigger operation.
  • the server may periodically obtain the first label list.
  • the server may also update the first tag list under other triggering conditions, such as the user ’s page views and browsing time of the content reaching the first predetermined amount, indicating that the user browses the content more, and new interest tags may be generated ,
  • the first tag list can be obtained for generating a new recommended tag list.
  • the user ’s browsing volume or browsing time of the content within a predetermined time is less than the second predetermined quantity, indicating that the currently recommended content may not be the content of interest to the user, the user browses less content, and can obtain the first tag list for generating new List of recommended tags.
  • Step S420 The server judges whether the similarity between the first tag list and the stored recommended tag list is less than a preset threshold. If yes, go to step S430; if no, go to step S410.
  • step S410 is executed.
  • Step S430 To obtain the second label list.
  • step S430 is performed between the first tag list and the stored recommended tag list.
  • the server may determine whether the trigger condition for acquiring the first tag list is a request for updating the recommended tag list initiated by the user through the mobile terminal, and if so, perform the step of acquiring the second tag list.
  • the similarity measurement method between the first tag list and the stored recommended tag list is not limited.
  • the specific value of the preset threshold is not limited, and can be adjusted according to specific recommended requirements, such as 80%, 90%, etc.
  • Step S430 The server obtains a second label list, which is jointly generated according to the first label list and the stored recommended label list.
  • Step S440 The server sends the second label list to the mobile terminal.
  • Step S450 The mobile terminal obtains and displays a second tag list from the server, the second tag list is generated based on the first tag list and the stored recommended tag list, and the first tag list is based on the content browsed by the user in the target time period The corresponding label is generated.
  • Step S460 The mobile terminal receives the user's selection of the label in the second label list, and returns the selection result to the server to instruct the server to generate a new recommended label list according to the selection result.
  • Step S470 the server receives the selection result returned by the mobile terminal according to the user's selection operation; and generates a new recommended tag list from the tags selected by the user in the selection result.
  • Step S480 The server pushes the content corresponding to the tag in the new recommended tag list to the mobile terminal.
  • Step S490 The mobile terminal receives the content recommended by the server according to the new recommended tag list.
  • the recommended tag list may not be updated temporarily. Only when the similarity between the first tag list and the stored recommended tag list is less than the preset threshold, the recommended tag list is updated to reduce unnecessary updates of the recommended tag list, which can push the content more comprehensively and accurately , And can save recommended resources.
  • the content recommendation apparatus 500 includes: a first tag list acquisition module 510 for acquiring a first tag list, the first tag list generated according to tags corresponding to content viewed by a user within a target time period .
  • the second label list obtaining module 520 is configured to obtain a second label list, and the second label list is jointly generated according to the first label list and the stored recommended label list.
  • the recommended label list obtaining module 530 is configured to obtain a label selected by the user from the second label list and generate a new recommended label list.
  • the pushing module 540 is configured to push the content corresponding to the tag in the new recommended tag list to the mobile terminal.
  • the first label list obtaining module 510 may include: a label obtaining unit, configured to obtain a label corresponding to the content browsed by the user within a target time period.
  • the first label list generating unit is configured to select a label whose browsing times is greater than a target number of times from the acquired labels to generate the first label list.
  • the first tag list acquisition module 510 may include: a tag acquisition unit that acquires tags corresponding to the content browsed by the user within the target time period. Another first tag list generating unit selects a target number of tags from the acquired tags according to the number of views from high to low to generate the first tag list.
  • the target time period may be a time period between the time when the recommended tag list was generated last time and the current time.
  • the target time period may also be a pre-stored time period.
  • a judgment module may be further included, which is used to judge whether the similarity between the first label list and the stored recommended label list is less than a preset threshold. If yes, the second label list obtaining module 520 is used to obtain a second label list.
  • the second tag list acquisition module 520 may be used to sort the tags in the first tag list and the tags in the recommended tag list according to the user's browsing times from high to low To generate a second label list.
  • the second label list obtaining module 520 may also be used to combine the first label list and the recommended label list as two sub-label lists to generate the second label list.
  • the second label list obtaining module 520 may be further configured to set a label in the second label list that the user has viewed more than a specified number of times as the selected label.
  • the recommended tag list acquisition module 530 may include: a list sending unit, configured to send the second tag list to the mobile terminal, for instructing the mobile terminal to send the second tag
  • the tags in the list are provided to the user for selection.
  • the selection receiving unit is configured to receive the selection result returned by the mobile terminal according to the user's selection operation.
  • the recommended label list generating unit is used to generate a new recommended label list from the labels selected by the user in the selection result.
  • the pushing module 540 may include: a request receiving unit, configured to receive a content recommendation request sent by a mobile terminal.
  • the searching unit is used for searching the content corresponding to the new recommended tag list.
  • the content return unit is used to return the found content to the mobile terminal.
  • the embodiment of the present application further provides a content recommendation device 600, which is applied to a mobile terminal.
  • the content recommendation device 600 includes: a second tag list acquisition module 610 for acquiring and displaying a second tag list from a server, the second tag list is based on the first tag list and the stored recommended tag list Generated, the first tag list is generated according to the tags corresponding to the content browsed by the user within the target time period.
  • the selection module 620 is configured to receive the user's selection of the label in the second label list, and return the selection result to the server to instruct the server to generate a new recommended label list according to the selection result.
  • the content receiving module 630 is configured to receive content recommended by the server according to the new recommended tag list.
  • the second label list may include a label set as selected. If the selection module 620 receives a selection operation on the selected label, it may be used to set the selected label as an unselected label. If a selection operation for an unselected label is received, the selection module 620 may be used to set the unselected label as the selected label.
  • the selection module 620 may be used to return the selected label to the server.
  • the selection module 620 may include an identification unit for adding a selected identification to the tag selected by the user in the second tag list.
  • the label return unit is used to return the second label list carrying the selected identification to the server, for instructing the server to generate a new recommended label list through the label with the selected identification.
  • various optional implementations may be implemented separately, or two or more simultaneous implementations may be implemented on a logical basis, or two or more implementations may be implemented in combination with each other, etc. It is not limited in the embodiments of the present application.
  • the coupling between the modules may be electrical, mechanical, or other forms of coupling.
  • each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
  • the above integrated modules may be implemented in the form of hardware or software function modules.
  • FIG. 14 shows a structural block diagram of a mobile terminal 200 according to an embodiment of the present application.
  • the mobile terminal 200 may be an electronic device capable of running application programs, such as a smart phone, a tablet computer, a music playback device, and the like.
  • the electronic device has one or more processors 210 (only one is shown in the figure), a memory 220, and one or more programs. Wherein, the one or more programs are stored in the memory 220, and are configured to be executed by the one or more processors 210.
  • the one or more programs are configured to execute the method described in the corresponding embodiment of the foregoing mobile terminal.
  • the processor 210 may include one or more processing cores.
  • the processor 210 connects various parts of the entire mobile terminal 200 using various interfaces and lines, executes or executes instructions, programs, code sets or instruction sets stored in the memory 220, and calls data stored in the memory 220 to execute Various functions and processing data of the mobile terminal 200.
  • the processor 210 may adopt at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA)
  • DSP Digital Signal Processing
  • FPGA Field-Programmable Gate Array
  • PLA programmable logic array
  • the processor 210 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), an image processing unit (Graphics Processing Unit, GPU), and a modem.
  • CPU Central Processing Unit
  • GPU Graphics Processing Unit
  • modem modem
  • CPU mainly deals with operating system, user interface and application program, etc .
  • GPU is used for rendering and rendering of display content
  • modem is used for handling wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 210, and may be implemented by a communication chip alone.
  • the memory 220 may include random access memory (RAM) or read-only memory (Read-Only Memory).
  • the memory 220 may be used to store instructions, programs, codes, code sets, or instruction sets.
  • the memory 220 may include a storage program area and a storage data area, where the storage program area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing various method embodiments described above, and the like.
  • the storage data area can also be data created by the electronic device in use (such as phonebook, audio and video data, chat history data), etc.
  • the mobile terminal 200 may further include a display screen for displaying labels and contents.
  • the display screen may be a touch screen for the user to select a label through the display screen.
  • an embodiment of the present application further provides a server 700.
  • the server 700 includes one or more processors 710, a memory 720, and one or more programs.
  • the one or more programs are stored in the memory 720 and configured to be executed by the one or more processors 710, and the one or more programs are configured to execute the above-mentioned related embodiments of the server Describe the method.
  • FIG. 16 shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application.
  • the computer readable storage medium 800 stores program codes, and the program codes can be called by the processor to execute the method described in the above method embodiments corresponding to the mobile terminal.
  • the computer-readable storage medium 800 has a storage space for the program code 810 that executes any method steps in the method embodiments corresponding to the mobile terminal described above. These program codes can be read from or written into one or more computer program products.
  • the program code 810 may be compressed in an appropriate form, for example.
  • the computer-readable storage medium 800 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the computer-readable storage medium 800 includes a non-transitory computer-readable storage medium.
  • the mobile terminal that stores the code corresponding to the method described in the method embodiment corresponding to the foregoing mobile terminal may also be regarded as the computer-readable storage medium 800 provided by the embodiment of the present application.
  • FIG. 17 shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application.
  • the computer-readable storage medium 900 stores program codes, and the program codes can be called by a processor to execute the method described in the method embodiment corresponding to the server.
  • the computer-readable storage medium 900 has a storage space for executing the program code 910 of any method step in the method embodiment corresponding to the server. These program codes can be read from or written into one or more computer program products.
  • the program code 910 may be compressed in an appropriate form, for example.
  • the computer-readable storage medium 900 may be a storage space such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM that stores program code 910 that performs any of the method steps described above Electronic storage.
  • the computer-readable storage medium 900 includes a non-transitory computer-readable storage medium.
  • any medium that stores the code corresponding to the method described in the method embodiment corresponding to the server, a cloud disk, or the like can be regarded as the computer-readable storage medium 900 provided by the embodiment of the present application.

Abstract

本申请公开了一种内容推荐方法、装置、移动终端及服务器，涉及互联网技术领域。其中，该方法包括：获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成；获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表；向移动终端推送所述新的推荐标签列表中标签对应的内容。该方案中，既推送到用户感兴趣的内容，又可以剔除用户不感兴趣的内容，提高推送效果。

Description

内容推荐方法、装置、移动终端及服务器 技术领域
本申请涉及互联网技术领域，更具体地，涉及一种内容推荐方法、装置、移动终端及服务器。
背景技术
随着科学技术的发展，移动终端已经成为人们日常生活中最常用的电子产品之一。人们通常通过电子产品浏览各种内容，如网页、视频等。但是很多用户感兴趣的内容用户可能无法主动获取到，因此，可以通过移动终端向用户推送其感兴趣的内容。但是，现有的推荐方式，对于用户已经丧失兴趣的内容也会持续推送，而用户感兴趣的内容可能并没有推送到，推送效果较差。
发明内容
鉴于上述问题，本申请提出了一种内容推荐方法、装置、移动终端及服务器，以改善上述问题。
第一方面，本申请实施例提供了一种内容推荐方法，所述方法包括：获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成；获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表；向移动终端推送所述新的推荐标签列表中标签对应的内容。
第二方面，本申请实施例提供了一种内容推荐方法，所述方法包括：从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表；接收服务器根据所述新的推荐标签列表推荐的内容。
第三方面，本申请实施例提供了一种内容推荐装置，所述装置包括：第一标签列表获取模块，用于获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；第二标签列表获取模块，用于获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成；推荐标签列表获取模块，用于获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表；推送模块，用于向移动终端推送所述新的推荐标签列表中标签对应的内容。
第四方面，本申请实施例提供了一种内容推荐装置，所述装置包括：第二标签列表获取模块，用于从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；选择模块，用于接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表；内容接收模块，用于接收服务器根据所述新的推荐标签列表推荐的内容。
第五方面，本申请实施例提供了一种服务器，包括：一个或多个处理器；存储器；一个或多个程序。其中所述一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执上述服务器对应的方法。
第六方面，本申请实施例提供了移动终端，包括：一个或多个处理器；存储器；一个或多个程序。其中所述一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行上述移动终端对应的方法。
第七方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有程序代码，所述程序代码可被处理器调用执行上述移动终端对应的方法。
本申请实施例提供的内容推荐方法、装置、移动终端及服务器，根据用户浏览的内容的标签生成 第一标签列表，根据第一标签列表以及已有的推荐标签列表生成第二标签列表。用户可以从第二标签列表中选择其感兴趣的标签，生成用于进行内容推荐的新的推荐标签列表。因此，当根据新的推荐标签列表向移动终端推送内容，相对于之前存储的推荐标签列表，既推送到用户感兴趣的内容，又可以剔除用户不感兴趣的内容，提高推送效果。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1示出了本申请实施例提供的内容推荐系统的交互示意图。
图2示出了本申请一实施例提供的内容推荐方法的流程图。
图3示出了本申请另一实施例提供的内容推荐方法的流程图。
图4示出了本申请又一实施例提供的内容推荐方法的流程图。
图5示出了本申请实施例提供的标签的一显示示意图。
图6示出了本申请实施例提供的标签的另一显示示意图。
图7示出了本申请实施例提供的标签的又一显示示意图。
图8示出了本申请实施例提供的标签的再一显示示意图。
图9示出了本申请实施例提供的标签的还一显示示意图。
图10示出了本申请再一实施例提供的内容推荐方法的流程图。
图11示出了本申请再一实施例提供的内容推荐方法的信令交互图。
图12示出了本申请一实施例提供的内容推荐装置的功能模块图。
图13示出了本申请另实施例提供的内容推荐装置的功能模块图。
图14示出了本申请实施例提供的移动终端的结构框图。
图15示出了本申请实施例提供的服务器的结构框图。
图16是本申请实施例的用于保存或者携带实现根据本申请实施例的内容推荐方法的程序代码的一存储单元。
图17是本申请实施例的用于保存或者携带实现根据本申请实施例的内容推荐方法的程序代码的另一存储单元。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。
随着移动终端的功能越来越完善，满足用户各种需求的应用程序越来越多，用户可以通过移动终端浏览越来越多的信息，如各种新闻网页、评论文章、问答内容以及视频等。具体用户可以通过各种应用程序浏览信息，如通过新闻应用程序(Application，APP)，浏览器，问答APP，视频APP等。
但是用户并非对所有信息均感兴趣，不同用户感兴趣的信息可能并不相同，如某些用户可能对体育相关内容感兴趣，某些用户可能对购物内容感兴趣，某些用户可能对明星娱乐相关内容感兴趣等。若将所有内容无区别地向各个移动终端推送，则用户需要从移动终端接收到的大量信息中寻找感兴趣的内容，浪费用户的时间，降低用户的使用体验。因此，在向移动终端推送内容时，可以推送该移动终端对应的用户感兴趣的内容。
若要向移动终端推送用户感兴趣的内容，则需要了解用户对哪些内容感兴趣。通常的，可以对各条 内容进行分类，如科技、教育、明星、体育、星座、历史等等，具体分类方式以及所分类别在本申请实施例中并不限定。再根据用户感兴趣的类别进行推送。
其中，每种类别可以通过一个标签表示，一条内容属于哪个类别，则表示对应有表示该类别的标签。每条标签所对应的内容，则表示是属于该标签所对应的类别的内容。具体的，每条内容可以分为一个或多个类别，对应一个或多个不同的标签。例如，一篇新闻可以同时属于教育、体育以及历史三个类别，对应教育、体育以及历史三个标签。当然，标签只是用于说明类别的一种方式，任何对内容进行类别区分的形式都可以认为是用于表示类别的标签。
作为第一种实施方式，当应用程序在移动终端下载后首次使用时，可以提供多个标签供用户选择，以用户选中的标签作为该用户的兴趣标签，即用户感兴趣的标签。在向移动终端推送内容时，主要推送用户的兴趣标签对应的内容。
作为第二种实施方式，可以在应用程序中可以设置标签选择界面，用户可以随时从标签选择界面选择其感兴趣的标签。在向移动终端内推送内容时，推送选中的兴趣标签对应的内容。
作为第三种实施方式，根据一段时间内用户对各种内容的浏览确定用户感兴趣的标签。例如，根据用户浏览的内容，加权生成一个兴趣标签值，如以用户浏览频率高的标签、浏览时间长的标签等作为用户的兴趣标签。向移动终端推送用户的兴趣标签对应的内容。
作为第四种实施方式，可以在移动终端显示的内容提供不感兴趣的设置接口，若用户在该接口设置不感兴趣，则不再向用户推送相关类容或者减少相关内容的推送。如在浏览器的新闻网站下，每条新闻设置不感兴趣按键，若用户点击该按键表示用户对该条新闻或者该类新闻不感兴趣，不再向该移动终端推送。
发明人经过研究发现，在上述各种实施方式中，可能会持续向用户推送用户不感兴趣的内容，或者使用户漏选其感兴趣的内容。例如，在上述第一种实施方式中，用户在长时间的使用过程中，可能对最初选定的某些兴趣标签不再感兴趣，但是仍然会将该标签作为用户的兴趣标签，向用户推送相关内容。在上述第二种实施方式中，虽然用户可以从标签选择界面重新选定自己感兴趣的标签，但是仅从标签选择界面中的标签所对应的类别名称用户可能无法确定是否对该标签所对应的内容感兴趣，并且，用户感兴趣的内容可能也无法通过标签准确选定出来。从而在该实施方式下，向用户推送的内容并不一定是用户感兴趣的。在上述第三种实施方式下，虽然根据用户浏览的内容来推送用户感兴趣的内容，但是，若用户未搜索到并浏览过某些本身用户会感兴趣的内容，则不会向用户推送相关的内容，从而漏推送某些用户感兴趣的内容。或者用户无意间点击过某些不感兴趣的内容，也会持续向用户推送与其相关的用户不感兴趣的内容，导致推送不准确，影响用户的浏览体验。在上述第四种实施方式下，虽然用户可以直接在不感兴趣的内容条目下设置不感兴趣，但是只能针对单一的内容条目或者类别设置，仍然会向用户推送其他不感兴趣的内容。
因此，本申请实施例提出了一种内容推荐方法、装置、移动终端及服务器，结合用户浏览过的内容以及用户之前选定的标签向用户提供标签列表，使用户可以根据自身前一次选择的标签以及最近浏览过的内容选择感兴趣的标签。再根据用户选择的标签进行内容推送，使推送的内容更准确，且更少遗漏用户可能感兴趣的内容。
在本申请实施例提供的内容推荐方法、装置、移动终端及服务器可以通过服务器与移动终端之间的交互实现，服务器根据用户的浏览以及前一次选择生成的标签生成供用户选择的标签列表并发送到移动终端，移动终端将该标签列表进行显示以使用户进行选择操作。移动终端将用户的选择结果返回给服务器，使服务器可以根据用户的选择进行推送。
图1示出了本申请实施例中服务器100和移动终端200之间的一种交互示意图。如图1所示，移动终端200与服务器100通过网络进行数据交互，该网络可以为无线网络或有线网络。于本申请中，移动终端200可为手机、平板电脑、计算机、电子阅读器、穿戴式电子设备、车载设备等智能设备，在此不做具体的限定。
在移动终端200中可运行客户端，服务器100可运行服务端。例如，在本申请中，移动终端200中运行有浏览器或者各种可以进行内容浏览的APP等，用户可以通过该客户端进行内容浏览。而在服务器100中运行有该客户端所对应的服务端。移动终端中运行的客户端可以执行本申请实施例中移动终端对应的方法，服务器中对应的服务端可以用于执行本申请实施例中服务器所对应的方法。基于上述网络环境，客户端可以通过网络与服务器100进行数据交互，从而实现与服务器100上运行的服务端进行数据交互。
下面将结合附图并通过具体的实施例对本申请实施例提供的内容推荐方法、装置、移动终端及服务器进行详细说明。
如图2示出了本申请实施例提供的内容推荐方法，该方法可以应用于服务器。当然，在本申请实施例中，该方法并不限定应用于服务器，也可以应用于移动终端等，本申请主要以服务器为例进行说明。请参见图2，该方法包括：
步骤S110：获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。
用户通过移动终端进行内容浏览，其所浏览的内容分别对应有标签，从而可以获得用户在目标时间段内浏览过的内容所对应的标签。根据目标时间段内用户浏览的内容对应的标签，可以生成第一标签列表。其中，第一标签列表中包括一个或多个标签，每个标签表示一种类别的内容。
步骤S120：获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成。
在服务器中，可以存储有推荐标签列表，该推荐标签列表为服务器向移动终端进行内容推送的依据。也就是说，推荐标签列表中包括一个或多个标签，服务器向移动终端推送推荐标签列表中标签对应的内容。
服务器根据结合第一标签列表以及存储的推荐标签列表中的标签，生成第二标签列表。也就是说，在第二标签列表中包括第一标签列表以及推荐标签列表中的标签。
步骤S130：获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表。
第二标签列表为提供给用户进行选择的标签列表，也就是说，用户可以从第二标签列表中选择其感兴趣的标签。用户从第二标签列表中选中的标签，表示用户对该标签对应的内容感兴趣，可以向用户推送该标签所对应的内容。因此，服务器可以获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表，替代之前存储的推荐标签列表，以作为向移动终端推送内容的依据。
步骤S140：向移动终端推送所述新的推荐标签列表中标签对应的内容。
服务器向移动终端推送内容时，推送新的推荐标签列表中的标签对应的内容。也就是说，向移动终端推送内容时，推送的为用户最新选中的兴趣标签相关类别的内容。
当然，在本申请实施例中，可以在生成新的推荐列表时，即根据该新的推荐列表向移动终端推送内容，也可以在生成新的列表后的其他时刻向移动终端推送内容。也就是说，步骤S140的执行时间可以与步骤S130的执行时间具有一定的间隔，且该间隔不做限制。另外，在获得新的推荐标签列表后，向用户推荐内容时，推送新的推荐标签列表对应的内容，直到重新生成推荐标签列表。
另外，若在本申请实施例提供的内容推荐方法应用于移动终端，则移动终端可以存储有推荐标签列表，并且从服务器获取第一标签列表。再根据第一标签列表以及存储的推荐标签列表共同生成第二标签列表。当用户对第二标签列表中的标签进行选择后，根据用户的选择生成新的推荐标签列表。移动终端可以根据新的推荐标签列表从服务器获取对应的内容进行显示推送。
在本申请实施例中，根据目标时间段内用户浏览的内容所对应的标签，以及存储的推荐标签列表中的标签，共同生成第二标签列表用作用户进行标签选择的基础。该第二标签列表中既包括用户之前选中过的感兴趣标签，又包括用户最近浏览的可能感兴趣的标签，尽可能减少对用户可能感兴趣的标签的遗漏，又使用户可以将之前选中的兴趣标签删除，提高推荐标签列表中标签的准确性以及完善性，提升推送效果。
图3示出了本申请实施例提供的内容推荐方法，应用于移动终端。请参见图3，该方法包括：
步骤S210：从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。
移动终端可以从服务器获取第二标签列表供用户进行标签选择。该第二标签列表为服务器根据第一标签列表以及服务器存储的推荐标签列表共同生成。
具体的，移动终端将第二标签列表进行显示，具体显示的为第二标签列表中各个标签，并提供对各个标签的选择权限。用户可以对显示的各个标签进行选择，即用户可以选择各个标签是否是自己感兴趣的标签。
步骤S220：接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表。
当用户在移动终端进行选择操作，移动终端接收到用户对第二标签列表中的标签的选择。当用户对第二标签列表中的标签选择结束，移动终端可以将选择结果返回给服务器。该选择结果中包括用户的选择信息，即通过该选择结果可以获知用户将第二标签列表中哪些标签选择为感兴趣的标签。因此，服务器可以根据该选择结果中用户选中的标签，生成新的推荐标签列表。
步骤S230：接收服务器根据所述新的推荐标签列表推荐的内容。
当服务器根据新的推荐标签列表向移动终端推送内容时，移动终端用于接收服务器的推送内容。可以理解的，步骤S230与步骤S220之间可以具有一定的时间间隔，且该时间间隔不做限制。也就是说，移动终端在将选择结果返回给服务器，服务器生成新的推荐标签列表，移动终端就可能接收到服务器根据该新的标签列表所推送的内容。或者在移动终端下一次开启相关的应用程序时，才接收到服务器的内容推送。
在本申请实施例中，移动终端提供给用户进行选择的第二标签列表包括用户目标时间段内浏览的内容所对应的标签以及用户之前选中的标签，从而使用户可选的标签更加完善，提高用户选择的完整性以及准确性，提高内容的推送效果。
如图4示出了本申请实施例提供的一种内容推荐方法，应用内容推荐系统。该内容推荐系统如图1所示，包括彼此交互的移动终端及服务器。如图4所示，该方法包括：
步骤S310：服务器获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。
服务器可以根据用户在目标时间段内对内容的浏览，获取目标时间段内用户浏览的内容对应的标签。其中，可以以一个移动终端作为一个用户，也可以以一个用户帐号作为一个用户。
具体的，作为一种实施方式，当用户在移动终端打开某条内容并开始浏览，移动终端可以将用户的 浏览情况向服务器反馈，如用户打开了那条内容、用户在何时关闭对该条内容的浏览等。从而服务器可以获知用户在目标时间段内浏览过哪些内容，再根据内容与标签的对应关系，服务器可以获知用户在目标时间段内浏览过哪些标签。其中，用户浏览过的标签为用户浏览过的内容对应的标签。
作为另一种实施方式，移动终端可以根据用户对内容的点击开启、关闭以及在内容浏览界面中的操作统计用户浏览了哪些标签对应的内容，再将统计结果反馈给服务器。该反馈可以是周期性反馈，可以是相应的应用程序关闭时反馈，或者是服务器主动向移动终端获取。若移动终端向服务器发起更新推荐标签列表的请求，则移动终端在发起更新推荐标签列表的请求时将最新统计的用户对标签的浏览情况反馈给服务器。从而服务器可以获取到目标时间段内用户浏览过哪些标签。
服务器可以从目标时间段内用户浏览过的标签中选择标签，生成第一标签列表。其中，服务器可以选取目标时间段内用户浏览过的全部标签生成第一标签列表，即第一标签列表中的标签为目标时间段内用户浏览过的标签。服务器也可以选取目标时间段内用户浏览过的部分标签生成第一标签列表，即第一标签列表中的标签为目标时间段内用户浏览过的部分标签。
作为一种实施方式，服务器还可以获取用户对各个标签的浏览次数。其中，某个标签对应的内容被打开浏览一次，可以统计该标签被浏览一次。例如，用户在目标时间段内浏览了内容A、内容B、内容C以及内容D，内容A对应标签a，内容B对应标签b，内容C对应标签a，内容D对应标签c，则可以获得在目标时间段内用户浏览过标签a、标签b、标签c对应的内容，其中标签a浏览了两次，标签b和标签c分别浏览了一次。
用户对标签的浏览次数越高，表明用户对该标签所对应的类型的相关内容浏览得越多，用户可能对该标签所对应的类型的相关内容越感兴趣。因此，可选的，服务器从目标时间段内用户浏览过的标签中选取部分标签生成第一标签列表时，可以选取浏览次数大于目标次数的标签，生成所述第一标签列表。其中，该目标次数的具体数值在本申请实施例中并不限定，可以根据实际情况进行设定。
可选的，在用户浏览量不足等情况下，浏览次数大于目标次数的标签的数量可能过少，从而若以浏览次数大于目标次数的标签生成第一标签列表，可能第一标签列表中的标签不太全面。因此，可以将获取的标签按照浏览次数由高到低排序，再根据排序结果，由高到低地选取目标个数的标签生成所述第一标签列表。例如，目标个数设定为10个，将目标时间段内用户浏览过的所有标签按照浏览次数由高到低排序后，从排序结果中从高到低选取10个标签生成第一标签列表。
可选的，在本申请实施例中，也可以先从获取的标签中选取浏览次数大于目标次数的标签，在浏览次数大于目标次数的标签数量少于目标个数的情况下，再从获取的标签中根据浏览次数由高到低选取一定数量的标签补足目标个数。
作为一种实施方式，服务器还可以获知对各条内容的浏览时间，从而统计各个标签对应的浏览时间。其中，每个标签的浏览时间可以是，该标签对应的各条被浏览过的内容的浏览时间累加。例如，用户在目标时间段内浏览了内容A、内容B以及内容C，内容A对应标签a，内容B对应标签b，内容C对应标签a，其中，内容A浏览x分钟，内容B浏览y分钟，内容C浏览了z分钟，则可以获得在目标时间段内用户浏览标签a的时间为x+z分钟，浏览标签b的时间为y分钟。
用户对标签的浏览时间越长，表明用户对该标签所对应的类型的相关内容浏览得越多，用户可能对该标签所对应的类型的相关内容越感兴趣。因此，可选的，服务器从目标时间段内用户浏览过的标签中选取部分标签生成第一标签列表时，可以选取浏览时间大于目标时间长度的标签，生成所述第一标签列表。其中，该目标时间长度的具体数值在本申请实施例中并不限定，可以根据实际情况进行设定。
可选的，在用户浏览量不足等情况下，浏览时间大于目标时间长度的标签的数量可能过少，从而若 以浏览时间大于目标时间长度的标签生成第一标签列表，可能第一标签列表中的标签不太全面。因此，可以将获取的标签按照浏览时间长短由高到低排序，再根据排序结果，由高到低地选取目标个数的标签生成第一标签列表。例如，目标个数设定为10个，将目标时间段内用户浏览过的所有标签按照浏览时间长短由高到低排序后，从排序结果中从高到低选取10个标签生成第一标签列表。
可选的，在本申请实施例中，该目标时间段可以是前一次生成推荐标签列表的时刻与当前时刻之间的时间段。也就是说，前一次生成推荐标签列表后，根据该推荐标签列表进行内容推荐，同时开始重新统计用户对内容的浏览，获取各个标签的浏览情况。
可选的，在本申请实施例中，该目标时间段也可以是预先存储的时间段。也就是说，该目标时间段可以是根据实际统计需求存储的一个时间长度。该目标时间段表示当前时刻之前的一段时间，例如，目标时间段为一周，则可以统计当前时刻以前的一周时间内对该个标签的浏览情况。
步骤S320：服务器获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成。
在本申请实施例中，第一标签列表根据用户的实际浏览内容生成，从而第一标签列表可以表示目标时间段内用户有意识或者无意识的浏览偏好。但是，对于目标时间段内用户没有浏览到的、或者浏览较少的类型的内容，第一标签列表的统计可能遗漏。另外，对于用户浏览较少的，但是用户主观希望可以被推送的内容，第一标签列表的统计也可能遗漏。因此，在本申请实施例中，还可以将第一标签列表与存储的推荐标签列表相结合，生成用于用户选择的第二标签列表。
作为一种实施方式，为了使标签覆盖类型更全面，可以选取第一标签列表的全部标签以及推荐标签列表的全部标签生成第二标签列表。
可选的，在该实施方式中，可以将第一标签列表以及所述推荐标签列表分别作为两个子标签列表合并，生成所述第二标签列表。在第二标签列表中包括两个子标签列表，各个子标签列表中的标签彼此相邻。也就说，在第二标签列表中，第一标签列表中的各个标签彼此相邻，推荐标签列表中的各个标签彼此相邻。其中，可以仅仅将两个子标签列表设置为各自的标签相邻显示。也可以将两个子标签类别设置为分别对应其标签列表名显示，方便用户分辨。
可选的，在该实施方式中，可以将第一标签列表中的全部标签与推荐标签列表中全部标签按照浏览次数或者浏览时间排序，生成第二标签列表。该排序可以是由高到低，方便用户对感兴趣内容的选择。当然，该排序也可以是由低到高，在本申请实施例中并不限定。
作为一种实施方式，为了减少用户的选择负担，也可以从推荐标签列表中选取部分标签与第一标签列表中的标签生成第二标签列表。其中，从推荐标签列表中选取标签的标准并不限定，可以是选取浏览次数大于预定次数的标签，或者是选取浏览时间大于预定时间长度的标签，或者是选取浏览次数最大的指定数量的标签，也或者是选取浏览时间最大的指定数量的标签等。
作为一种实施方式，为了降低对热点内容类型的漏选几率，在第一标签列表以及推荐标签列表中选取标签后，可以再加入大数据统计的标签，生成第二标签列表。该大数据统计的标签为大部分用户偏好的类型对应的。具体的，服务器可以统计所有用户的浏览情况，获取每个的标签被所有用户浏览的浏览次数总和或者浏览时间总和。将其中浏览次数最高或者浏览时间最长的一定数量的标签，作为大数据统计的标签，加入到第一标签列表以及推荐标签列表的选取结果中。
作为一种实施方式，在本申请实施例中，为了方便用户选择，提高用户选择速度以及选择的便捷性，可以将第二标签列表中的部分标签设置为已选中的标签。其中设置为已选中的标签表示默认用户选中，若用户不取消对其选中，则作为用户选中的标签用于生成推荐标签列表。
可选的，由于标签的浏览次数越高，用户感兴趣的可能性越大，因此，可以将所述第二标签列表中用户浏览次数大于指定次数的标签设置为已选中的标签。该指定次数的具体数值在本申请实施例中并不限定。
可选的，由于标签的浏览时间越长，用户感兴趣的可能性越大，因此，可以将所述第二标签列表中用户浏览时间大于指定时间长度的标签设置为已选中的标签。该指定时间长度的具体数值在本申请实施例中并不限定。
在本申请实施例中，与第一标签列表共同生成第二标签列表的推荐标签列表为存储于服务器的推荐标签列表。该存储的推荐标签列表为前一次获得并存储的推荐标签列表，用于作为向移动终端推送内容的标准。即在本次获得新的推荐标签列表之前，服务器根据前一次获得的该推荐标签列表向移动终端推送内容。当然，该存储的推荐标签列表可以是根据其前一次的推荐标签列表以及其前面的目标时间段用户浏览的内容获得。其中，若以一个移动终端作为一个用户，当相应的应用程序在该移动终端首次开启连接服务器时，不具有前一次的推荐标签列表以及用户的浏览记录，此时可以向移动终端推送多种标签供用户选择，以根据用户的选择生成第一个推荐标签列表。若以一个用户帐号作为一个用户，当相应的应用程序在某个用户帐号首次登陆时，不具有前一次的推荐标签列表以及用户的浏览记录，此时可以向移动终端推送多种标签供用户选择，以根据用户的选择生成第一个推荐标签列表。
服务器将生成的第二标签列表发送给移动终端，以便移动终端将该第二标签列表显示给用户进行选择。
步骤S330：移动终端从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。
移动终端可以获得服务器生成的第二标签列表。移动终端将该第二标签列表显示，以使用户可以从第二标签列表中进行标签选择。
其中，移动终端对第二标签列表的标签显示可以与第二标签列表在服务器设置的显示方式一致。例如，在第二标签列表中包括两个子标签列表，各个子标签列表中的标签彼此相邻。若仅仅将两个子标签列表设置为各自的标签相邻显示，则对第二标签列表进行显示可以是如图5所示，虚线框201中的标签表示第一标签列表中的标签，虚线框202中的标签表示前一次的推荐标签列表中的标签。可以理解的，其中虚线框在移动终端显示时可以是不显示的。若将两个子标签类别设置为分别对应其标签列表名显示，则显示可以是如图6所示。其中，标签列表名具体为何种名字在本申请实施例中并不限定，例如图6中“最近浏览”表示第一标签列表，“前次设置”表示前一次获取的推荐标签列表。
在本申请实施例中，若移动终端接收到的第二标签列表中包括设置为已选中的标签，则在对该第二标签列表进行显示时，其中被设置为已选中的标签可以已选中的标签的显示形式进行显示，以区别于未被选中的标签显示，如高亮或置灰等。例如图7所示，若标签a在服务器被设置为默认选中，则在移动终端将标签a以置灰的形式表示为已选中的标签，进行显示。
步骤S340：移动终端接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表。
用户可以在移动终端显示的第二标签列表中选择自己感兴趣的标签。移动终端接收到用户对某个标签的选择，若该标签本身为未被选中的标签，则将该标签设置为已选中标签。并且，还可以将用户选中的标签以已选中的标签的显示形式进行显示。例如图8所示，若用户点击标签c，则将标签c设置为已选中的标签。
当然，用户也可以对已选中的标签取消选择。例如，用户点击已选中的标签，则将已选中的标签设 置为未选中的标签。例如用户再次对图8所示的标签a进行点击操作，则如图9所示，标签a被设置为未选中的标签。
也就是说，移动终端若接收到对已选中的标签的选择操作，将所述已选中的标签设置为未选中的标签；若接收到对未选中的标签的选择操作，将所述未选中的标签设置为已选中的标签。
当用户选择结束后，移动终端将选择结果返回给服务器。其中，可以是接收到用户触发的选择结束的相应指令时，将选择结果返回给服务器。
作为一种实施方式，移动终端可以将第二标签列表中所有的标签均返回到服务器，并且将其中用户选中的标签设置区别于未选中的标签的参数，以使服务器可以从移动终端返回的标签中识别出被用户选中的标签。
可选的，在该实施方式中，移动终端可以为所述第二标签列表中用户选择的标签添加选中标识。移动终端将携带有选中标识的第二标签列表返回给所述服务器，以用于指示所述服务器通过具有选中标识的标签生成新的推荐标签列表。
可选的，在该实施方式中，也可以将第二标签列表分为选中标签子列表以及未选中标签子列表。并且将用户选择的标签放入选中标签子列表中，将用户未选择的标签放入未选中标签子列表中。从而使接收到移动终端返回的第二标签列表的服务器，可以仅读取选中标签子列表中的标签，以获得用户选中的标签。
作为一种实施方式，为了减少传输数据量，降低传输能耗，移动终端可以将第二标签列表中用户未选中的标签舍弃，仅仅将已选中的标签返回给服务器。
步骤S350：服务器获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表。
服务器在向移动终端发送第二标签列表后，可能接收到移动终端返回的选择结果，可以根据选择结果获得用户从第二标签列表中选中的标签。例如，若移动终端返回的是整个第二标签列表中的标签，则服务器从中读取被用户选中的标签；若移动终端返回的仅为用户选中的，则将接收到的所有标签作为用户从第二标签列表中选中的标签。
服务器可以将选择结果中用户选中的标签生成新的推荐标签列表。具体的，服务器将所有用户选中的标签生成一个标签列表，该标签列表作为新的推荐标签列表，替代前一次生成的推荐标签列表。将该新的推荐标签列表存储，并作为后续内容推荐的标准。
可以理解的，在本申请实施例中，由服务器执行的步骤与由移动终端执行的步骤之间并不一定具有严格的步骤先后顺序，可能具有一定的交叉性。例如，当S350这一步骤中包括多个子步骤：将所述第二标签列表发送给移动终端，以用于指示移动终端将所述第二标签列表中的标签提供给用户选择；接收移动终端根据用户的选择操作返回的选择结果；将选择结果中用户选中的标签生成新的推荐标签列表。其中将所述第二标签列表发送给移动终端的子步骤执行于步骤S330之前，接收移动终端根据用户的选择操作返回的选择结果，以及将选择结果中用户选中的标签生成新的推荐标签列表两个子步骤执行于步骤S340之后。
步骤S360：服务器向移动终端推送所述新的推荐标签列表中标签对应的内容。
在需要向移动终端推送内容时，服务器推送新的推荐标签列表中标签对应的内容。
其中，服务器向移动终端推送内容的时机并不限定。
可选的，可以是在生成新的推荐标签列表即进行一次推送。
可选的，也可以是周期性地根据最新的推荐标签列表向移动终端进行内容推送。具体的推送周期在本申请实施例中并不限定。
可选的，也可以根据移动终端的内容推荐请求进行推送。例如，服务器接收移动终端发送的内容推荐请求。根据该内容推荐请求查找推荐标签列表对应的内容，当然，查找的为最新获取的推荐标签列表对应的内容。再将查找到的内容返回给所述移动终端。
可选的，也可以在于该推荐标签列表相关的应用程序打开时根据推荐标签列表进行内容推送；或者在推荐标签列表相关的应用程序进行帐号登录时，根据推荐标签列表进行内容推送。
服务器每次向移动终端推送内容的数量以及方式在本申请实施例中并不限定，可以以相关技术常用的推送方式为准。
例如，在本申请实施例中，可选的，每次推送时，可以推送上次推送与本次推送之间产生的所有内容。
可选的，推荐标签列表中的标签对应的内容可能较多，移动终端每次可显示的内容条数有限，每次推送时也可以推送目标数量的内容条数到移动终端。或者每次推送时，推送最近一段时间的内容，该最近一段时间的具体时间长度并不限定。或者在推送时，按照内容的产生时间由近到远分批次向移动终端推送，当移动终端接收并显示完一批，再向移动终端发送下一批。
步骤S370：移动终端接收服务器根据所述新的推荐标签列表推荐的内容。
服务器将推送的内容发送到移动终端，移动终端对应接收。并且，移动终端将接收到的内容进行显示。
其中，移动终端的内容从服务器接收到的标签对应的推送内容可以是内容的部分信息，如标题、简介或者开头部分内容等。当移动终端接收到对相应内容的触发，向服务器发起获取该内容的请求，服务器再将相应内容的完整信息发送到移动终端，移动终端对其进行显示。
在本申请实施例中，根据存储的推荐标签列表以及用户的浏览内容生成第二标签列表，用户可以从第二标签列表中选择感兴趣的标签，从而使用户的选择基础同时基于近期的浏览结果以及之前的选择，使可选的基准更全面且选择更准确，从而根据选择结果生成的新的推荐标签列表更全面准确。在推送时可以既推送到用户感兴趣的内容，又可以剔除用户不感兴趣的内容，提高推送效果
图10及图11示出了本申请实施例提供的一种内容推荐方法，应用于如图1所示的内容推荐系统。该方法中，还可以根据用户喜好的变化情况确定是否更新推荐标签列表。具体的，请参见图10及图11，该方法包括：
步骤S410：服务器获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。
服务器获取第一标签列表用于生成推荐标签列表。其中，服务器具体在何时获取第一标签列表在本申请实施例中并不限定，获取第一标签列表的触发条件可以是如下的一种或多种。
可选的，服务器可以在接收到移动终端发起的更新推荐标签列表的请求时获取第一标签列表。该更新推荐标签列表的请求可以为移动终端接收到用户的更新推荐列表触发操作时由移动终端发起。
可选的，服务器可以周期性地获取第一标签列表。
可选的，服务器也可以在其他触发条件下更新第一标签列表，如用户对内容的浏览量、浏览时间等达到第一预定数量，表示用户对内容浏览较多，可能有新的兴趣标签产生，可以获取第一标签列表以用于生成新的推荐标签列表。或者用户在预定时间内对内容的浏览量或者浏览时间小于第二预定数量，表示目前推荐的内容可能不是用户感兴趣的内容，用户浏览内容较少，可以获取第一标签列表以用于生成新的推荐标签列表。
步骤S420：服务器判断所述第一标签列表与存储的推荐标签列表之间的相似度是否小于预设阈值。 若是，执行步骤S430；若否，执行步骤S410。
若第一标签列表与存储的推荐标签列表之间的相似度大于或等于预设阈值，第一标签列表与存储的推荐标签列表相近，表示用户近期浏览类型偏好与服务器向其推荐的类型相近，可以不进行推荐标签列表的更新。并且，在下一次需要获取第一标签列表时执行步骤S410。
若第一标签列表与存储的推荐标签列表之间的相似度小于预设阈值，表示用户近期浏览类型偏好与服务器向其推荐的类型具有一定的差距，需要进行推荐标签列表的更新，执行步骤S430中获取第二标签列表的步骤。
可选的，在本申请实施例中，若服务器在接收到移动终端发起的更新推荐标签列表的请求时获取的第一标签列表，而该更新推荐标签列表的请求由用户触发于移动终端发起，则表示用户想要更新推荐标签列表。此时，不管第一标签列表与存储的推荐标签列表之间的相似度为多少，都执行步骤S430第一标签列表与存储的推荐标签列表之间的步骤。
也就是说，可选的，服务器可以判断获取第一标签列表的触发条件是否是由用户通过移动终端发起的更新推荐标签列表的请求，若是，则执行获取第二标签列表的步骤。
在本申请实施例中，第一标签列表与存储的推荐标签列表之间的相似度度量方式并不限定。例如，可以是，第一标签列表与推荐标签列表中相同标签占第一标签列表中总标签的比例，若该比例小于预设比例，则判定第一标签列表与存储的推荐标签列表之间的相似度小于预设阈值。其中，该预设阈值的具体值并不限定，可以根据具体推荐需求调整，如百分之八十，百分之九十等。
步骤S430：服务器获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成。
步骤S440：服务器将所述第二标签列表发送给移动终端。
步骤S450：移动终端从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。
步骤S460：移动终端接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表。
步骤S470：服务器接收移动终端根据用户的选择操作返回的选择结果；将选择结果中用户选中的标签生成新的推荐标签列表。
步骤S480：服务器向移动终端推送所述新的推荐标签列表中标签对应的内容。
步骤S490：移动终端接收服务器根据所述新的推荐标签列表推荐的内容。
在本申请实施例中，若第一标签列表与存储的推荐标签列表相近，则表示用户对内容的类型偏好与前一次确定推荐标签列表时相差不大，可以暂时不更新推荐标签列表。而在第一标签列表与存储的推荐标签列表的相似度小于预设阈值的情况下才进行推荐标签列表的更新，减小推荐标签列表的不必要更新，既能更加全面准确地向用户推送内容，又能节省推荐资源。
本申请实施例还提供了一种内容推荐装置500，该内容推荐装置可以应用于服务器。当然，在本申请实施例中也不排除将该内容推荐装置应用于服务器。具体的，请参见图12，该内容推荐装置500包括：第一标签列表获取模块510，用于获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。第二标签列表获取模块520，用于获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成。推荐标签列表获取模块530，用于获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表。推送模块540，用于向移动终端推送所述新的推荐标签列表中标签对应的内容。
可选的，在申请实施例中，第一标签列表获取模块510可以包括：标签获取单元，用于获取目标时间段内用户浏览的内容对应的标签。第一标签列表生成单元，用于从获取的标签中选取浏览次数大于目标次数的标签，生成所述第一标签列表。
可选的，第一标签列表获取模块510可以包括：签获取单元，获取目标时间段内用户浏览的内容对应的标签。另一第一标签列表生成单元，从获取的标签中按照浏览次数由高到低选取目标个数的标签，生成所述第一标签列表。
可选的，在本申请实施例中，所述目标时间段可以是前一次生成推荐标签列表的时刻与当前时刻之间的时间段。
可选的，在本申请实施例中，所述目标时间段也可以是预先存储的时间段。
可选的，在本申请实施例中，还可以包括判断模块，用于判断所述第一标签列表与存储的推荐标签列表之间的相似度是否小于预设阈值。若是，第二标签列表获取模块520，用于获取第二标签列表。
可选的，在本申请实施例中，第二标签列表获取模块520可以用于将所述第一标签列表中的标签以及所述推荐标签列表中的标签按照用户浏览次数由高到低进行排序，生成第二标签列表。
可选的，在本申请实施例中，第二标签列表获取模块520也可以用于将第一标签列表以及所述推荐标签列表分别作为两个子标签列表合并，生成所述第二标签列表。
可选的，在本申请实施例中，第二标签列表获取模块520还可以用于将所述第二标签列表中用户浏览次数大于指定次数的标签设置为已选中的标签。
可选的，在本申请实施例中，推荐标签列表获取模块530可以包括：列表发送单元，用于将所述第二标签列表发送给移动终端，以用于指示移动终端将所述第二标签列表中的标签提供给用户选择。选择接收单元，用于接收移动终端根据用户的选择操作返回的选择结果。推荐标签列表生成单元，用于将选择结果中用户选中的标签生成新的推荐标签列表。
可选的，在本申请实施例中，推送模块540可以包括：请求接收单元，用于接收移动终端发送的内容推荐请求。查找单元，用于查找所述新的推荐标签列表对应的内容。内容返回单元，用于将查找到的内容返回给所述移动终端。
本申请实施例还提供了一种内容推荐装置600，应用于移动终端。请参见图13，该内容推荐装置600包括：第二标签列表获取模块610，用于从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成。选择模块620，用于接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表。内容接收模块630，用于接收服务器根据所述新的推荐标签列表推荐的内容。
可选的，第二标签列表中可以包括设置为已选中的标签，选择模块620若接收到对已选中的标签的选择操作，可以用于将所述已选中的标签设置为未选中的标签。若接收到对未选中的标签的选择操作，选择模块620可以用于将所述未选中的标签设置为已选中的标签。
可选的，选择模块620可以用于将已选中的标签返回给服务器。
可选的，选择模块620可以包括标识单元，用于为所述第二标签列表中用户选择的标签添加选中标识。标签返回单元，用于将携带有选中标识的第二标签列表返回给所述服务器，以用于指示所述服务器通过具有选中标识的标签生成新的推荐标签列表。
在本申请实施例中，各种可选的实施方式之间可以分别实施，也可以在符合逻辑的基础上两个或多个同时实施，或者两个或多个实施方式之间相互组合实施等，在本申请实施例并不限定。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述的各个方法实施例之间可以相互参照。例如，上述描述装置和模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。上述系统对应的方法实施例可以参照服务器对应的方法实施例以及移动终端对应的方法实施例。另外，服务器对应的方法实施例也可以参照系统对应的方法实施例中服务器相关的描述，移动终端对应的方法实施例可以参照系统对应的方法实施例中系统对应的相关描述。
在本申请所提供的几个实施例中，模块相互之间的耦合可以是电性，机械或其它形式的耦合。
另外，在本申请各个实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
请参考图14，其示出了本申请实施例提供的一种移动终端200的结构框图。该移动终端200可以是智能手机、平板电脑、音乐播放设备等能够运行应用程序的电子设备。该电子设备一个或多个处理器210(图中仅示出一个)，存储器220以及一个或多个程序。其中，所述一个或多个程序被存储在所述存储器220中，并被配置为由所述一个或多个处理器210执行。所述一个或多个程序配置用于执行前述移动终端相应的实施例所描述的方法。
处理器210可以包括一个或者多个处理核。处理器210利用各种接口和线路连接整个移动终端200内的各个部分，通过运行或执行存储在存储器220内的指令、程序、代码集或指令集，以及调用存储在存储器220内的数据，执行移动终端200的各种功能和处理数据。可选地，处理器210可以采用数字信号处理(Digital Signal Processing，DSP)、现场可编程门阵列(Field－Programmable Gate Array，FPGA)、可编程逻辑阵列(Programmable Logic Array，PLA)中的至少一种硬件形式来实现。处理器210可集成中央处理器(Central Processing Unit，CPU)、图像处理器(Graphics Processing Unit，GPU)和调制解调器等中的一种或几种的组合。其中，CPU主要处理操作系统、用户界面和应用程序等；GPU用于负责显示内容的渲染和绘制；调制解调器用于处理无线通信。可以理解的是，上述调制解调器也可以不集成到处理器210中，单独通过一块通信芯片进行实现。
存储器220可以包括随机存储器(Random Access Memory，RAM)，也可以包括只读存储器(Read-Only Memory)。存储器220可用于存储指令、程序、代码、代码集或指令集。存储器220可包括存储程序区和存储数据区，其中，存储程序区可存储用于实现操作系统的指令、用于实现至少一个功能的指令、用于实现上述各个方法实施例的指令等。存储数据区还可以电子设备在使用中所创建的数据(比如电话本、音视频数据、聊天记录数据)等。
另外，该移动终端200还可以包括显示屏，用于对标签以及内容进行显示。该显示屏可以是触摸屏，用于用户通过显示屏选择标签。
请参考图15，本申请实施例还提供了一种服务器700。该服务器700包括一个或多个处理器710，存储器720以及一个或多个程序。其中所述一个或多个程序被存储在所述存储器720中并被配置为由所述一个或多个处理器710执行，所述一个或多个程序配置用于执行上述服务器对应的相关实施例描述的方法。
请参考图16，其示出了本申请实施例提供的一种计算机可读存储介质的结构框图。该计算机可读存储介质800中存储有程序代码，所述程序代码可被处理器调用执行上述移动终端对应的方法实施例中所描述的方法。
计算机可读存储介质800具有执行上述移动终端对应的方法实施例中的任何方法步骤的程序代码810的存储空间。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。程序代码810可以例如以适当形式进行压缩。
该计算机可读存储介质800可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。可选地，计算机可读存储介质800包括非易失性计算机可读介质(non-transitory computer-readable storage medium)。可选的，存储有上述移动终端对应的方法实施例中所描述的方法对应的代码的移动终端，也可以认为是本申请实施例提供的该计算机可读存储介质800。
另外，请参考图17，其示出了本申请实施例提供的一种计算机可读存储介质的结构框图。该计算机可读存储介质900中存储有程序代码，所述程序代码可被处理器调用执行上述服务器对应的方法实施例中所描述的方法。
该计算机可读存储介质900具有执行上述服务器对应的方法实施例中的任何方法步骤的程序代码910的存储空间。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。程序代码910可以例如以适当形式进行压缩。
其中该计算机可读存储介质900可以是存储执行上述方法中的任何方法步骤的程序代码910的存储空间诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。可选地，计算机可读存储介质900包括非易失性计算机可读介质(non-transitory computer-readable storage medium)。可选的，存储有上述服务器对应的方法实施例中所描述的方法对应的代码的服务器、云盘等任何介质，都可以认为是本申请实施例提供的该计算机可读存储介质900。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不驱使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (20)

  1. 一种内容推荐方法，其特征在于，所述方法包括：
    获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；
    获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成；
    获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表；
    向移动终端推送所述新的推荐标签列表中标签对应的内容。
  2. 根据权利要求1所述的方法，其特征在于，所述获取第一标签列表，包括：
    获取目标时间段内用户浏览的内容对应的标签；
    从获取的标签中选取浏览次数大于目标次数的标签，生成所述第一标签列表。
  3. 根据权利要求1所述的方法，其特征在于，所述获取第一标签列表，包括：
    获取目标时间段内用户浏览的内容对应的标签；
    从获取的标签中按照浏览次数由高到低选取目标个数的标签，生成所述第一标签列表。
  4. 根据权利要求1至3任一项所述的方法，其特征在于，所述目标时间段为前一次生成推荐标签列表的时刻与当前时刻之间的时间段。
  5. 根据权利要求1至3任一项所述的方法，其特征在于，所述目标时间段为预先存储的时间段。
  6. 根据权利要求1至5任一项所述的方法，其特征在于，所述获取第二标签列表之前，还包括：
    判断所述第一标签列表与存储的推荐标签列表之间的相似度是否小于预设阈值；
    若是，执行所述获取第二标签列表的步骤。
  7. 根据权利要求1至6任一项所述的方法，其特征在于，所述获取第二标签列表包括：
    将所述第一标签列表中的标签以及所述推荐标签列表中的标签按照用户浏览次数由高到低进行排序，生成第二标签列表。
  8. 根据权利要求1至6任一项所述的方法，其特征在于，所述获取第二标签列表包括：
    将第一标签列表以及所述推荐标签列表分别作为两个子标签列表合并，生成所述第二标签列表。
  9. 根据权利要求1至8任一项所述的方法，其特征在于，所述获取用户从所述第二标签列表中选中的标签之前，还包括：
    将所述第二标签列表中用户浏览次数大于指定次数的标签设置为已选中的标签。
  10. 根据权利要求1至9任一项所述的方法，其特征在于，所述获取用户从所述第二标签列表中选择的标签，生成新的推荐标签列表，包括：
    将所述第二标签列表发送给移动终端，以用于指示移动终端将所述第二标签列表中的标签提供给用户选择；
    接收移动终端根据用户的选择操作返回的选择结果；
    将选择结果中用户选中的标签生成新的推荐标签列表。
  11. 根据权利要求1至10任一项所述的方法，其特征在于，所述向移动终端推送所述新的推荐标签列表对应的内容，包括：
    接收移动终端发送的内容推荐请求；
    查找所述新的推荐标签列表对应的内容；
    将查找到的内容返回给所述移动终端。
  12. 一种内容推荐方法，其特征在于，所述方法包括：
    从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表 共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；
    接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表；
    接收服务器根据所述新的推荐标签列表推荐的内容。
  13. 根据权利要求12所述的方法，其特征在于，所述第二标签列表中包括设置为已选中的标签，所述接收用户对所述第二标签列表中标签的选择，包括：
    若接收到对已选中的标签的选择操作，将所述已选中的标签设置为未选中的标签，
    若接收到对未选中的标签的选择操作，将所述未选中的标签设置为已选中的标签。
  14. 根据权利要求12或13所述的方法，其特征在于，所述将选择结果返回给服务器，包括：
    将已选中的标签返回给服务器。
  15. 根据权利要求12或13所述的方法，其特征在于，所述将选择结果返回给服务器，包括：
    为所述第二标签列表中用户选择的标签添加选中标识；
    将携带有选中标识的第二标签列表返回给所述服务器，以用于指示所述服务器通过具有选中标识的标签生成新的推荐标签列表。
  16. 一种内容推荐装置，其特征在于，所述装置包括：
    第一标签列表获取模块，用于获取第一标签列表，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；
    第二标签列表获取模块，用于获取第二标签列表，所述第二标签列表根据所述第一标签列表以及存储的推荐标签列表共同生成；
    推荐标签列表获取模块，用于获取用户从所述第二标签列表中选中的标签，生成新的推荐标签列表；
    推送模块，用于向移动终端推送所述新的推荐标签列表中标签对应的内容。
  17. 一种内容推荐装置，其特征在于，所述装置包括：
    第二标签列表获取模块，用于从服务器获取第二标签列表并显示，所述第二标签列表根据第一标签列表以及存储的推荐标签列表共同生成，所述第一标签列表根据目标时间段内用户浏览的内容对应的标签生成；
    选择模块，用于接收用户对所述第二标签列表中标签的选择，并将选择结果返回给服务器，以用于指示服务器根据选择结果生成新的推荐标签列表；
    内容接收模块，用于接收服务器根据所述新的推荐标签列表推荐的内容。
  18. 一种服务器，其特征在于，包括：
    一个或多个处理器；
    存储器；
    一个或多个程序，其中所述一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行如权利要求1-11任一项所述的方法。
  19. 一种移动终端，其特征在于，包括：
    一个或多个处理器；
    存储器；
    一个或多个程序，其中所一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行如权利要求12-15任一项所述的方法。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有程序代码，所述程序代码可被处理器调用执行如权利要求12-15任一项所述的方法。
PCT/CN2018/113166 2018-10-31 2018-10-31 内容推荐方法、装置、移动终端及服务器 WO2020087386A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN201880099091.5A CN112930669B (zh) 2018-10-31 2018-10-31 内容推荐方法、装置、移动终端及服务器
PCT/CN2018/113166 WO2020087386A1 (zh) 2018-10-31 2018-10-31 内容推荐方法、装置、移动终端及服务器
EP18938863.0A EP3873065B1 (en) 2018-10-31 2018-10-31 Content recommendation method, mobile terminal, and server
US17/242,186 US20210248198A1 (en) 2018-10-31 2021-04-27 Content Recommendation Method and Apparatus, Mobile Terminal, and Server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/113166 WO2020087386A1 (zh) 2018-10-31 2018-10-31 内容推荐方法、装置、移动终端及服务器

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/242,186 Continuation US20210248198A1 (en) 2018-10-31 2021-04-27 Content Recommendation Method and Apparatus, Mobile Terminal, and Server

Publications (1)

Publication Number Publication Date
WO2020087386A1 true WO2020087386A1 (zh) 2020-05-07

Family

ID=70463527

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/113166 WO2020087386A1 (zh) 2018-10-31 2018-10-31 内容推荐方法、装置、移动终端及服务器

Country Status (4)

Country Link
US (1) US20210248198A1 (zh)
EP (1) EP3873065B1 (zh)
CN (1) CN112930669B (zh)
WO (1) WO2020087386A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111898028A (zh) * 2020-08-07 2020-11-06 北京小米移动软件有限公司 一种实体对象推荐方法、装置及存储介质
CN112579893A (zh) * 2020-12-15 2021-03-30 中国建设银行股份有限公司 一种信息推送、信息展示方法、装置及设备
CN113411379A (zh) * 2021-05-31 2021-09-17 《人民论坛》杂志社 基于浏览习惯的信息推送方法、装置和电子设备
CN113672156A (zh) * 2021-07-23 2021-11-19 青岛海尔科技有限公司 内容推送方法、装置、电子设备及存储介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113486244A (zh) * 2021-07-14 2021-10-08 深圳市点购电子商务控股股份有限公司 一种用户兴趣的探索方法和装置
CN113378068B (zh) * 2021-07-14 2023-07-18 聚好看科技股份有限公司 一种内容推荐方法及服务器
CN113761361A (zh) * 2021-07-29 2021-12-07 深圳市思为软件技术有限公司 一种房产资讯推荐方法及终端设备
CN114817731A (zh) * 2022-05-10 2022-07-29 北京字跳网络技术有限公司 内容推送方法、装置和电子设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090063568A1 (en) * 2007-08-30 2009-03-05 Samsung Electronics Co., Ltd. Method and apparatus for constructing user profile using content tag, and method for content recommendation using the constructed user profile
CN101901450A (zh) * 2010-07-14 2010-12-01 中兴通讯股份有限公司 媒体内容推荐方法和媒体内容推荐系统
CN103327111A (zh) * 2013-07-01 2013-09-25 百度在线网络技术（北京）有限公司 多媒体文件的推荐方法、系统和服务器
CN106250532A (zh) * 2016-08-04 2016-12-21 广州优视网络科技有限公司 应用推荐方法、装置及服务器
CN106503025A (zh) * 2015-09-08 2017-03-15 北京搜狗科技发展有限公司 一种应用推荐方法和系统
CN107844525A (zh) * 2017-10-12 2018-03-27 广州艾媒数聚信息咨询股份有限公司 一种基于用户行为的资讯个性化推荐方法、系统及装置

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8370203B2 (en) * 2002-10-07 2013-02-05 Amazon Technologies, Inc. User interface and methods for recommending items to users
US9015147B2 (en) * 2007-12-20 2015-04-21 Porto Technology, Llc System and method for generating dynamically filtered content results, including for audio and/or video channels
US8832099B2 (en) * 2010-03-09 2014-09-09 Yahoo! Inc. User specific feed recommendations
JP5574952B2 (ja) * 2010-12-28 2014-08-20 Ｋｄｄｉ株式会社 レコメンドシステム、レコメンド方法、およびレコメンドプログラム
US9305084B1 (en) * 2012-08-30 2016-04-05 deviantArt, Inc. Tag selection, clustering, and recommendation for content hosting services
US20140331142A1 (en) * 2013-05-06 2014-11-06 Tencent Technology (Shenzhen) Company Limited Method and system for recommending contents
CN104133820B (zh) * 2013-05-06 2016-03-30 腾讯科技（深圳）有限公司 内容推荐方法及内容推荐装置
JP2015022656A (ja) * 2013-07-22 2015-02-02 株式会社東芝 電子機器、方法およびプログラム
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
US10198498B2 (en) * 2015-05-13 2019-02-05 Rovi Guides, Inc. Methods and systems for updating database tags for media content
CN107612974B (zh) * 2017-08-23 2020-04-17 Oppo广东移动通信有限公司 信息推荐方法、装置、移动终端及存储介质
CN107798100A (zh) * 2017-10-30 2018-03-13 江西博瑞彤芸科技有限公司 一种应用推荐信息的配置方法
CN107818166A (zh) * 2017-11-07 2018-03-20 暴风集团股份有限公司 一种资讯推荐方法、装置、服务器及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090063568A1 (en) * 2007-08-30 2009-03-05 Samsung Electronics Co., Ltd. Method and apparatus for constructing user profile using content tag, and method for content recommendation using the constructed user profile
CN101901450A (zh) * 2010-07-14 2010-12-01 中兴通讯股份有限公司 媒体内容推荐方法和媒体内容推荐系统
CN103327111A (zh) * 2013-07-01 2013-09-25 百度在线网络技术（北京）有限公司 多媒体文件的推荐方法、系统和服务器
CN106503025A (zh) * 2015-09-08 2017-03-15 北京搜狗科技发展有限公司 一种应用推荐方法和系统
CN106250532A (zh) * 2016-08-04 2016-12-21 广州优视网络科技有限公司 应用推荐方法、装置及服务器
CN107844525A (zh) * 2017-10-12 2018-03-27 广州艾媒数聚信息咨询股份有限公司 一种基于用户行为的资讯个性化推荐方法、系统及装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111898028A (zh) * 2020-08-07 2020-11-06 北京小米移动软件有限公司 一种实体对象推荐方法、装置及存储介质
CN111898028B (zh) * 2020-08-07 2024-04-19 北京小米移动软件有限公司 一种实体对象推荐方法、装置及存储介质
CN112579893A (zh) * 2020-12-15 2021-03-30 中国建设银行股份有限公司 一种信息推送、信息展示方法、装置及设备
CN113411379A (zh) * 2021-05-31 2021-09-17 《人民论坛》杂志社 基于浏览习惯的信息推送方法、装置和电子设备
CN113672156A (zh) * 2021-07-23 2021-11-19 青岛海尔科技有限公司 内容推送方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
EP3873065A4 (en) 2021-10-06
EP3873065B1 (en) 2023-10-04
US20210248198A1 (en) 2021-08-12
CN112930669A (zh) 2021-06-08
CN112930669B (zh) 2023-06-20
EP3873065A1 (en) 2021-09-01

Similar Documents

Publication Publication Date Title
WO2020087386A1 (zh) 内容推荐方法、装置、移动终端及服务器
US11363129B2 (en) Method and apparatus for processing contact information using a wireless terminal
CN112868004B (zh) 资源推荐方法、装置、电子设备及存储介质
CN110245069B (zh) 页面版本的测试方法和装置、页面的展示方法和装置
CN109451333B (zh) 一种弹幕显示方法、装置、终端及系统
WO2018133725A1 (zh) 媒体文件的输出处理方法、客户端及系统
CN110889076B (zh) 评论信息发布方法、装置、客户端、服务器、系统和介质
CN110598098A (zh) 一种信息推荐方法、装置和用于信息推荐的装置
CN110674345A (zh) 一种视频搜索方法、装置及服务器
CN111246302A (zh) 浏览器下载数据的方法、装置和终端
CN110909616A (zh) 一种视频中商品购买信息获取方法、装置及电子设备
CN110659404A (zh) 一种信息推荐方法、装置及存储介质
CN112187622B (zh) 即时消息的展示方法、装置及服务器
US20230297618A1 (en) Information display method and electronic apparatus
CN116955817A (zh) 内容推荐方法、装置、电子设备以及存储介质
CN108134948B (zh) 电视节目推荐方法、装置、系统及可读存储介质
CN112818190B (zh) 内容分享方法、装置、电子设备和存储介质
CN115525834A (zh) 筛选并显示消息的方法、计算机装置及记录介质
CN110674386B (zh) 资源推荐方法、装置及存储介质
CN105094581A (zh) 信息处理的方法和装置
WO2021051744A1 (zh) 菜品推荐方法、推荐内容上传方法、装置及电子设备
CN112015924A (zh) 流媒体缓存方法及其装置、计算机可存储介质
WO2024093967A1 (zh) 一种推荐方法以及相关设备
CN114201702A (zh) 一种点赞处理方法、装置、系统、设备及存储介质
CN113469767A (zh) 订单信息的处理方法、装置、设备及计算机可读存储介质

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: 18938863

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018938863

Country of ref document: EP

Effective date: 20210527