WO2020151548A1 - 关注页面的排序方法及装置 - Google Patents

关注页面的排序方法及装置 Download PDF

Info

Publication number
WO2020151548A1
WO2020151548A1 PCT/CN2020/072226 CN2020072226W WO2020151548A1 WO 2020151548 A1 WO2020151548 A1 WO 2020151548A1 CN 2020072226 W CN2020072226 W CN 2020072226W WO 2020151548 A1 WO2020151548 A1 WO 2020151548A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
content
attention
concerned
coefficient
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/072226
Other languages
English (en)
French (fr)
Inventor
龚彦云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing ByteDance Network Technology Co Ltd
Original Assignee
Beijing ByteDance Network Technology Co Ltd
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 Beijing ByteDance Network Technology Co Ltd filed Critical Beijing ByteDance Network Technology Co Ltd
Publication of WO2020151548A1 publication Critical patent/WO2020151548A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/957Browsing optimisation, e.g. caching or content distillation

Definitions

  • the present disclosure relates to the field of Internet technology, and in particular to a method and device for sorting attention pages. Background technique
  • the content in the user's attention page can be sorted according to the release time of the content.
  • this sorting method of following pages cannot recommend content that the user is interested in based on the user's points of interest, thereby affecting the user experience.
  • the following page sorting method, device, electronic device, and storage medium proposed in the present disclosure are used to solve the related technology, the following page sorting method based on publishing time cannot recommend the content that the user is interested in according to the user's point of interest, which affects the user The problem of experience.
  • the method for sorting attention pages proposed in an embodiment of the present disclosure includes: obtaining multiple attention content in the attention page; obtaining user characteristics of the user and the characteristics of the multiple attention content; according to the user characteristics and the multiple Generating user interest values of the plurality of attention contents, and sorting the plurality of attention contents according to the user interest values of the plurality of attention contents.
  • the acquiring the user characteristics of the user includes:
  • the historical browsing data includes at least one of the following data: user click data, follow-up data, comment data, and forwarding data;
  • the user characteristics are generated according to the points of interest of the user.
  • the feature of the focused content includes: Type information of the concerned content, popularity information of the concerned content, and interaction information between the publisher of the concerned content and the user.
  • the generating user interest values of the multiple focused content based on the user characteristics and the multiple focused content characteristics include:
  • a first coefficient corresponding to each focused content is generated, where the first coefficient corresponding to each focused content is used to indicate that each focused content is related to the The correlation between user characteristics;
  • a third coefficient corresponding to each concerned content is generated, where the third coefficient corresponding to each concerned content is used to indicate each concerned content The degree of interaction between the publisher of the content and the user;
  • the user interest values of the plurality of attention contents are generated.
  • At least one of generating the user interest values of the multiple concerned contents includes:
  • At least one of the first coefficient, the second coefficient, and the third coefficient corresponding to the plurality of attention contents is input into a preset user interest value recognition model to generate the plurality of attention contents Where the preset user interest value recognition model is generated through training.
  • the method further includes: acquiring a plurality of to-be-recommended content matching the user characteristics;
  • the method further includes: acquiring the user’s information according to the interaction information between the publisher of the concerned content and the user Social preferences information;
  • the device for sorting attention pages proposed in another embodiment of the present disclosure includes: a first obtaining module, which is used to obtain multiple attention content in the attention page; and a second obtaining module, which is used to obtain the user characteristics of the user and the multiple Features of the content of interest; a generating module, configured to generate user interest values of the multiple content of interest according to the characteristics of the user and the features of the multiple content of interest; and a sorting module, configured to The interest value of the user who pays attention to the content is sorted.
  • the second obtaining module includes: an obtaining unit, configured to obtain historical browsing data of the user, where the historical browsing data includes Following number At least one of the data: user's click data, attention-added data, comment data, and forwarding data; a first generating unit, configured to generate points of interest of the user according to the user’s historical browsing data; a second generating unit, using Generating the user characteristics according to the user's points of interest.
  • the characteristics of the focused content include: type information of the focused content, popularity information of the focused content, and the publisher of the focused content and the user Interactive information.
  • the generating module includes: a third generating unit, configured to generate each user profile according to the user characteristics and the type information of each concerned content; A first coefficient corresponding to each attention content, where the first coefficient corresponding to each attention content is used to indicate the degree of correlation between each attention content and the user characteristics;
  • the fourth generating unit is configured to generate a second coefficient corresponding to each concerned content according to the popularity information of each concerned content
  • the fifth generating unit is configured to generate a third coefficient corresponding to each concerned content according to the interaction information between the publisher of each concerned content and the user, wherein the third coefficient corresponding to each concerned content is used Yu represents the degree of interaction between the publisher of each concerned content and the user;
  • a sixth generating unit configured to generate user interest values of the plurality of attention contents according to at least one of the first coefficient, the second coefficient, and the third coefficient respectively corresponding to the plurality of attention contents .
  • the sixth generating unit is specifically used for:
  • At least one of the first coefficient, the second coefficient, and the third coefficient corresponding to the plurality of attention contents is input into a preset user interest value recognition model to generate the plurality of attention contents Where the preset user interest value recognition model is generated through training.
  • the apparatus further includes: a third acquisition module, configured to acquire a plurality of to-be-recommended content matching the user characteristics;
  • the recommendation module is configured to recommend the multiple content to be recommended to the user.
  • the device further includes: a fourth acquisition module, configured to respond to the interaction between the publisher of the concerned content and the user Information, obtaining social preference information of the user;
  • the processing module is configured to generate the person to be recommended of the user according to the social preference information of the user, and recommend the person to be recommended to the user.
  • the electronic device proposed in another embodiment of the present disclosure includes: a processor and a memory; wherein, the processor reads the executable program code stored in the memory to run the executable program code corresponding to the executable program code.
  • the program is used to implement the sorting method of the attention pages as described above.
  • the non-transitory computer-readable storage medium provided by another embodiment of the present disclosure has a computer program stored thereon, It is characterized in that, when the program is executed by the processor, the method for sorting the attention pages as described above is implemented.
  • Another aspect of the present disclosure provides a computer program, which when executed by a processor, implements the aforementioned method for sorting attention pages.
  • the method, apparatus, electronic device, computer-readable storage medium, and computer program for sorting attention pages provided by the embodiments of the present disclosure can obtain multiple attention content in the attention page, as well as the user characteristics of the user and the characteristics of the multiple attention content. And according to the user characteristics and the characteristics of the multiple concerned contents, multiple user interest values of the concerned contents are generated, and then the multiple concerned contents are sorted according to the user interest values of the multiple concerned contents.
  • the attention content that the user is interested in can be displayed first, which not only improves the user experience, but also increases the click volume of the page content.
  • FIG. 1 is a schematic flowchart of a method for sorting attention pages according to an embodiment of the disclosure
  • FIG. 2 is a schematic flowchart of another method for sorting attention pages provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of an apparatus for sorting attention pages provided by an embodiment of the present disclosure
  • FIG. 4 is a schematic structural diagram of an electronic device provided by the disclosed embodiment
  • Fig. 5 is a schematic structural diagram of a non-transitory computer-readable storage medium provided by an embodiment of the present disclosure. detailed description
  • the embodiment of the present disclosure proposes a method for ranking the following pages in the related technology, which is based on the publishing time-based sorting method of the following pages, which cannot recommend the content of interest to the user according to the user's points of interest, which affects the user experience.
  • the method for sorting attention pages provided by the embodiments of the present disclosure can obtain multiple attention content in the attention page, as well as the user characteristics of the user and the characteristics of the multiple attention content, and generate multiple attention pages according to the user characteristics and the characteristics of the multiple attention content.
  • a user interest value of the following content and then the multiple attention content is sorted according to the user interest value of the multiple attention content. Therefore, by sorting the attention content according to the user interest value of each attention content, the attention content that the user is interested in can be displayed first, which not only improves the user experience, but also increases the content of the page. Hit volume.
  • FIG. 1 is a schematic flowchart of a method for sorting attention pages according to an embodiment of the disclosure.
  • the sorting method of the following pages includes the following steps:
  • Step 101 Obtain multiple following contents in a following page.
  • the identifier of the attention page may be the domain name and IP address of the attention page and other information that can uniquely determine the attention page.
  • Toutiao APP after following author A, a user can click on author A on a similar page such as "My follow” to get the content published by author A. Therefore, after the user's click operation on author A is obtained, a follow page corresponding to author A can be generated, and multiple follow content in the follow page can include multiple articles published by author A.
  • Step 102 Acquire the user characteristics of the user and the characteristics of the multiple concerned contents.
  • the user characteristics of the user refer to the characteristics that can reflect the user's points of interest.
  • the characteristics of the content of interest may refer to the type of the content of interest, for example, it may be entertainment, sports, current affairs, economics, and so on.
  • the user’s historical browsing data can be determined first according to the user’s user identification, and the type of content that the user has browsed is determined according to the user’s historical browsing data, and the types of content that the user has viewed The amount of clicks on the content, and then the type of content that the user has viewed and the amount of clicks on various types of content are determined as the user characteristics of the user.
  • the user ID of the user refers to identity authentication information that can uniquely determine the user, for example, it may be a registered account of the user.
  • the characteristics of the multiple content of interest in the attention page can be the type information of the content of interest. Therefore, the following can be determined according to the classification label set by the publisher for each content to be posted when multiple content of interest is published. Features of multiple attention content on the page.
  • the manner of acquiring the user characteristics of the user and the characteristics of multiple focused content in the focused page may include, but is not limited to, the situations listed above.
  • the user characteristics included in the user characteristics can be preset according to actual needs
  • the content included in the feature of the content and the focused content, and the manner of determining the user feature and the feature of the focused content are not limited in the embodiment of the present disclosure.
  • Step 103 Generate user interest values of the multiple focused content according to the user characteristics and the multiple focused content characteristics.
  • the user characteristics and the characteristics of the multiple focused content in the focused page can be used to generate the multiple focused content in the focused page User interest value.
  • the following content that is of interest to the user and the content of interest that the user is not interested in the follow page can be determined first.
  • Each concerned content that matches the type of content browsed is determined as each concerned content that the user is interested in;
  • each concerned content included in the following page that does not match the type of content browsed by the user is determined as each concerned content that the user is not interested in follow the content.
  • the number of clicks on various types of content included in the user characteristics can be determined.
  • the user clicks more on a certain type of content it can be determined that the user's interest value of this type of focused content is greater; otherwise, it can be determined that the user's interest value of this type of focused content is smaller; For a certain type of focused content that the user has not browsed, that is, each focused content included in the focused page that is not of interest to the user, the user interest value of each focused content that is not of interest to the user may be determined as 0.
  • Step 104 Sort the multiple focused content according to the user interest value of the multiple focused content.
  • the attention content in the attention page can be sorted according to the user interest value of each attention content in the attention page.
  • each concerned content in the following page can be sorted in descending order. If the following page includes the following content with the same user interest value, the following content with the same user interest value can be further sorted according to the release time of the following content with the same user interest value. That is, it can be sorted in ascending order according to the time interval between the publication time and the current time of each concerned content with the same user interest value, that is, the following contents are arranged before the preceding contents.
  • the method for sorting attention pages can obtain multiple attention content in the attention page, as well as the user characteristics of the user and the characteristics of the multiple attention content, and generate multiple attention pages according to the user characteristics and the characteristics of the multiple attention content.
  • a user interest value of the following content and then the multiple attention content is sorted according to the user interest value of the multiple attention content. Therefore, by sorting the attention content according to the user interest value of each attention content, the attention content that the user is interested in can be displayed first, which not only improves the user experience, but also increases the click volume of the page content.
  • the type information, popularity information, and content are determined to determine the correlation between the characteristics of the concerned content and the user characteristics, and then determine the user interest value of the multiple concerned contents in the following page, so as to further improve the interest in the following page The degree of conformity between the sorting of each concerned content and the user's point of interest.
  • FIG. 2 is a schematic flowchart of another method for sorting attention pages according to an embodiment of the disclosure.
  • the sorting method of the attention pages includes the following steps:
  • Step 201 Obtain multiple following contents in a following page.
  • Step 202 Obtain the user characteristics of the user and the characteristics of the multiple concerned content, where the characteristics of the concerned content include: type information of the concerned content, popularity information of the concerned content, and the relationship between the publisher of the concerned content and the user Interactive information.
  • the user's historical browsing data may be determined first according to the user's user identification, and the user characteristics of the user may be determined according to the user's historical browsing data. That is, in a possible implementation form of the embodiment of the present disclosure, the foregoing step 202 may include:
  • the historical browsing data includes at least one of the following data: user click data, follow-up data, comment data, and forwarding data;
  • the user characteristics are generated according to the points of interest of the user.
  • the user’s historical browsing data can be obtained according to the user’s user identification (the user’s registered account, etc.), and the user can be extracted from the obtained historical browsing data.
  • the user's click data may include the types of content browsed by the user within a preset time period, and the amount of clicks to various types of content.
  • Adding data by following means that users add following data such as publishers and content types within a preset time period.
  • Comment data and forwarding data refer to the type of content that the user has commented on or forwarded within a preset time period, or the publisher corresponding to the commented or forwarded content, etc.
  • the preset time period is 1 month
  • the historical browsing data of users whose time interval from the current moment is within 1 month can be obtained, and from the historical browsing data of the users, users within 1 month can be extracted Click data, pay attention to add data, and comment data, forward data and other interactive data.
  • the historical browsing data of the user may include, but is not limited to, the situations listed above.
  • each data included in the historical browsing data and the preset time period can be preset according to actual needs, which is not limited in the embodiment of the present disclosure.
  • the user click data, attention addition data, Comment on data, forward data, and generate points of interest for users.
  • one or more content types with the highest click volume in the user's click data can be determined as the user's point of interest; and the content types included in the user's attention addition data, comment data, and forwarding data can be determined as Points of interest of users.
  • the user’s click data includes three types of content: sports, current affairs, and entertainment.
  • the click volume of "sports” content is 100
  • the click volume of "current affairs” content is 80
  • the content of "entertainment” "The click volume of the content is 10
  • the user’s attention addition data includes publisher A. According to the identity of publisher A, the label of publisher A is determined to be “beauty”, then the user’s point of interest can be determined as “sports, Current affairs, beauty.”
  • mapping relationship between the user's historical browsing data and the user's points of interest can be preset according to actual needs, which is not limited in the embodiment of the present disclosure.
  • the user characteristics of the user can be generated according to the user's points of interest.
  • the types of content included in the points of interest of the user and the amount of clicks of various types of content included in the points of interest of the user may be determined as the user characteristics of the user.
  • the characteristics of the multiple content of interest in the follow page may include information in multiple dimensions such as the type information of the content of interest, the popularity information of the content of interest, and the interaction information between the publisher of the content of interest and the user.
  • the relationship between the feature of the focused content and the user feature is determined from multiple dimensions, so as to further improve the user's interest value of each focused content in the determined focused page and the degree of conformity with the user's interest point.
  • the type information of the focused content can be determined based on the classification tags set by the publisher on the published content when the focused content is published, and the characteristics of multiple focused content in the focused page can be determined; or the words can be divided according to the focused content. Processing, and according to the word frequency of each word segmentation in the concerned content, determine the multiple word segments with the highest word frequency in the concerned content as keywords of the concerned content, and then perform semantic analysis on the keywords in the concerned content to determine the type information of the concerned content .
  • the popularity information of the concerned content can be determined according to the clicks of all users on the concerned content, that is, the more clicks of the concerned content, the higher the popularity of the concerned content; the less the clicks of the concerned content, the lower the popularity of the concerned content.
  • the interaction information between the publisher and the user who pays attention to the content may refer to the frequency of interaction between the publisher and the user, and may be determined by the publisher's identity and the user's user identity.
  • the method of determining the type information of the focused content, the popularity information of the focused content, and the interactive information between the publisher of the focused content and the user may include but is not limited to the situations listed above.
  • the dimensional information included in the feature of the focused content can be preset according to actual needs, and the manner of determining each dimensional information included in the feature of the focused content, which is not limited in the embodiment of the present disclosure.
  • Step 203 Generate a first coefficient corresponding to each content of interest according to the user characteristics and the type information of each content of interest, where the first coefficient corresponding to each content of interest is used to indicate each content of interest The correlation with the user characteristics.
  • the characteristics of each focused content may first include the type information of the focused content and the user characteristics of the user.
  • the content types corresponding to the points of interest of the user are included, and the amount of clicks of each content type corresponding to the points of interest of the user is included, and the correlation between each concerned content in the following page and the user characteristics of the user is determined, that is, each following The first coefficient corresponding to the content.
  • the first coefficient corresponding to each focused content can be determined according to the user's clicks on each content type corresponding to the point of interest, that is, the user's.
  • the higher the click volume of the content type corresponding to the content type information the greater the correlation between the focused content and the user characteristics of the user, that is, the greater the first coefficient corresponding to the focused content;
  • the type information of the focused content does not match the content type corresponding to the user's point of interest, that is, the content type corresponding to the user's point of interest does not include the type information of the focused content, it can be determined that the focused content is between the user characteristics of the user Irrelevant, that is, the first coefficient corresponding to the concerned content may be determined as 0.
  • the content types corresponding to the user's points of interest included in the user characteristics of the user are: sports, current affairs, and beauty.
  • the click volume for "sports” content is 100
  • the click volume for "current politics” content is 80.
  • the “beauty” content corresponds to 50 clicks
  • the following page includes 3 following contents.
  • the type information of the 3 following contents are: sports, beauty, and economy. Therefore, the type information can be determined as "sports"
  • the first coefficient corresponding to the attention content with "" is greater than the first coefficient corresponding to the attention content with the type information of "beauty”, and the first coefficient corresponding to the attention content with the type information of "economy” is 0.
  • Step 204 Generate a second coefficient corresponding to each focused content according to the popularity information of each focused content.
  • the second coefficient corresponding to the attention content may be generated according to the popularity information of the attention content, that is, the second coefficient corresponding to the attention content may be used to indicate the popularity of the attention content.
  • the higher the popularity of the focused content that is, the more clicks on the focused content, the greater the second coefficient corresponding to the focused content; the lower the popularity of the focused content, the less the clicks on the focused content, the less the focused content corresponds to the first The smaller the second coefficient.
  • Step 205 According to the interaction information between the publisher of each concerned content and the user, a third coefficient corresponding to each concerned content is generated, where the third coefficient corresponding to each concerned content is used to represent the The degree of interaction between the publisher of each concerned content and the user.
  • the degree of interaction between the publisher of each content of interest and the user can be determined based on the interaction information between the publisher of each content of interest in the follow page, that is, the degree of interaction between the publisher of each content of interest and the user The third coefficient.
  • the interaction frequency between each publisher of the following content and the user can be determined, and according to each The interaction frequency between the publisher of the concerned content and the user determines the third coefficient corresponding to each concerned content.
  • the higher the interaction frequency between the publisher of the concerned content and the user the higher the degree of interaction between the publisher of the concerned content and the user, that is, the greater the third coefficient corresponding to the concerned content;
  • the lower the frequency of interaction between people and users the lower the degree of interaction between the publisher of the concerned content and the user, that is, the smaller the third coefficient corresponding to the concerned content; If the interaction frequency is 0, the third coefficient corresponding to the concerned content can be determined Set to 0.
  • the follow page includes three follow contents: follow content A, follow content B, follow content C, follow content A corresponding to publisher A and the user interaction frequency is 10 times, follow content B corresponding to publisher B
  • the interaction frequency with the user is 5 times
  • the interaction frequency between the publisher C corresponding to the focused content C and the user is 0 times
  • the third coefficient corresponding to the focused content A is greater than the third coefficient corresponding to the focused content B
  • the focused content B corresponds to
  • the third coefficient is greater than the third coefficient corresponding to the attention content C
  • the third coefficient corresponding to the attention content C is zero.
  • Step 206 According to at least one of the first coefficient, the second coefficient, and the third coefficient respectively corresponding to the plurality of attention contents, generate user interest values of the plurality of attention contents.
  • the larger the first coefficient, the second coefficient, and the third coefficient of the focused content in the focused page the greater the correlation between the feature of the focused content and the user feature of the user, that is, The greater the correlation between the attention content and the user's point of interest. Therefore, the user interest value of each focused content can be determined according to one or more of the first coefficient, the second coefficient, and the third coefficient corresponding to each focused content.
  • the user's interest value of the focused content when determining the user's interest value of the focused content according to one or more of the first coefficient, the second coefficient, and the third coefficient corresponding to the focused content, it is possible to first determine each of the focused pages.
  • the coefficients required by the value of interest of the attention content are normalized.
  • the interest value of each attention content in the attention page is determined, and then the first coefficient corresponding to each attention content in the attention page may be normalized to the same interval range, for example, The first coefficient corresponding to each attention content in the attention page is normalized to the interval [0, 1]; correspondingly, if the first coefficient, the second coefficient, and the third coefficient corresponding to the attention content are determined to be in the attention page
  • the first coefficient, the second coefficient, and the third coefficient corresponding to each attention content in the attention page may be respectively normalized.
  • the ranges of the normalized first coefficient, second coefficient, and third coefficient may be different.
  • each attention content in the attention page corresponds to After the first coefficient, the second coefficient, and the third coefficient are respectively normalized, the sum of the first coefficient, the second coefficient, and the third coefficient corresponding to each concerned content can be determined as the user experience of each concerned content Interest value; or the average value of the first coefficient, the second coefficient, and the third coefficient corresponding to each content of interest may be determined as the user's interest value of each content of interest.
  • the user interest value for each concerned content may be the sum or average value of the first coefficient, the second coefficient, and the third coefficient corresponding to each concerned content, but is not limited to this.
  • the relationship between the first coefficient, the second coefficient, and the third coefficient corresponding to the user's interest in the content of interest can be determined according to actual needs, which is not limited in the embodiment of the present disclosure.
  • the foregoing step 206 may include:
  • the first coefficient, the second coefficient, and the third coefficient corresponding to the multiple attention contents are input into a preset user interest value recognition model to generate user interest in the multiple attention contents Value, where the preset user interest value recognition model is generated through training.
  • the preset user interest value recognition model is generated through training.
  • a large amount of attention content can be obtained first as training data, and according to the above method Determine the first coefficient, second coefficient, and third coefficient corresponding to each training data, and label the user-interested value of each training data, and then normalize the first coefficient and first coefficient of each training data.
  • One or more of the second coefficient, the third coefficient, and the labeled data (labeled user interest value) of each training data are input to the training model for training to generate a user interest value recognition model.
  • the interest value recognition model determines the user's interest value of each concerned content in the concerned page. Among them, when determining the user's interest value of each concerned content in the attention page, input the coefficients of the user's interest value recognition model, which are the same as the coefficients used when training the user's interest value recognition model.
  • Step 207 Sort the multiple focused content according to the user interest value of the multiple focused content.
  • the attention content in the attention page can be sorted according to the user interest value of each attention content in the attention page.
  • each concerned content in the following page can be sorted in descending order. If the following page includes the following content with the same user interest value, the following content with the same user interest value can be further sorted according to the release time or popularity information of the following content with the same user interest value. That is, it can be sorted in ascending order according to the time interval between the publication time and the current time of the following content with the same user interest value, that is, the following content will be arranged before the previously published following content; or according to the same user interest value The popularity of each concerned content is sorted in descending order.
  • step 207 it may further include:
  • a plurality of waiting lists matching the user characteristics can be determined. Recommend content, and recommend multiple determined content to be recommended to the user.
  • the content type that matches the user’s point of interest can be determined.
  • the type of content to be recommended is then obtained according to the popularity information of each content in the type of content to be recommended, and the content of the type of content to be recommended that has a higher popularity or a relatively recent release time is determined as the content to be recommended.
  • the type of content to be recommended may be one or more, that is, the type of content to be recommended may be one or more content types corresponding to the user's point of interest and with the highest click volume.
  • the content types corresponding to the user's points of interest included in the user characteristics of the user are: sports, current affairs, and beauty.
  • the click volume for "sports” content is 100
  • the click volume for "current politics” content is 80.
  • the number of hits corresponding to the "beauty” content is 50
  • the type of content to be recommended can be determined as “sports”
  • the popularity information or release time of each content of the type "sports” change
  • One or more content with the highest popularity is determined as content to be recommended and recommended to the user; or one or more content with the most recent publication time may be determined as content to be recommended and recommended to the user.
  • the above examples are only exemplary and should not be regarded as a limitation of the present disclosure.
  • the type and quantity of content to be recommended, the quantity of content to be recommended, and the method for determining the content to be recommended can be preset according to actual needs, and the embodiment of the present disclosure does not limit this.
  • the method may further include: acquiring social preference information of the user according to the interaction information between the publisher of the concerned content and the user;
  • the user’s interaction information can be determined based on the interactive information between each publisher of the concerned content and the user, such as the user’s likes, comments, and attention to the concerned content or the publisher of the concerned content.
  • Social preferences information For example, big data analysis can be used to determine the type of content or publisher's tag with a high number of users' likes, comments, or follow, and determine the determined content type or publisher's tag as the user's social preferences
  • the user’s social preference information publishers or other users who match the user’s social preference information are determined as persons to be recommended and recommended to the user.
  • user A often comments and likes "sports” content and publishers who frequently publish “sports” content. Therefore, user A's social preferences information can be determined as "sports", and then other frequent The publisher who publishes the "sports" content is determined as the person to be recommended, or other users who frequently follow the "sports” content are determined as the person to be recommended, and the determined person to be recommended is recommended to the user A.
  • the sorting method of the following pages can obtain multiple following contents in the following pages, as well as the user characteristics of the user and the characteristics of the multiple following contents, and according to the user characteristics and the type information of each concerned content, Generate a first coefficient representing the correlation between each concerned content and user characteristics, and generate a second coefficient corresponding to each concerned content according to the popularity information of each concerned content, and then according to the publisher and user of each concerned content Generate a third coefficient corresponding to each concerned content, and then generate a user experience of the plurality of concerned contents according to at least one of the first coefficient, the second coefficient, and the third coefficient respectively corresponding to the plurality of concerned contents Interest value, and sort the multiple focused content according to the interest value of the multiple focused users.
  • the user’s interest value of each concerned content can be determined according to the user characteristics and the type information and popularity information of each concerned content in the concerned page, and the interaction information between the publisher of the concerned content and the user.
  • the content to be recommended and the person to be recommended that match the characteristics of the user are determined, so that not only the attention content that the user is interested in can be displayed first, which increases the number of clicks on the page content, but also can dig out the content and potential that the user may be interested in.
  • Social relations provide a rich content consumption experience and further improve the user experience.
  • the present disclosure also proposes a sorting device for attention pages.
  • FIG. 3 is a schematic structural diagram of an apparatus for sorting attention pages provided by an embodiment of the disclosure.
  • the sorting device 30 of the concerned page includes:
  • the first obtaining module 31 is configured to obtain multiple attention content in the attention page
  • the second obtaining module 32 is configured to obtain the user characteristics of the user and the characteristics of the multiple attention contents; the generating module 33 is configured to generate the multiple attentions according to the user characteristics and the characteristics of the multiple attention contents User interest value of the content; and
  • the sorting module 34 is used for sorting the multiple concerned contents according to the user interest value of the plurality of concerned contents.
  • the device for sorting attention pages provided by the embodiments of the present disclosure can be configured in any electronic device to execute the aforementioned method for sorting attention pages.
  • the device for sorting attention pages can acquire multiple attention content in the attention page, as well as the user characteristics of the user and the characteristics of the multiple attention content, and generate multiple attention content based on the user characteristics and the characteristics of the multiple attention content.
  • a user interest value of the following content and then the multiple attention content is sorted according to the user interest value of the multiple attention content.
  • the attention content that the user is interested in can be displayed first, which not only improves the user experience, but also increases the click volume of the page content.
  • the above-mentioned second acquisition module 32 includes:
  • An acquiring unit configured to acquire historical browsing data of the user, where the historical browsing data includes at least one of the following data: user click data, follow-up data, comment data, and forwarding data;
  • the first generating unit is configured to generate points of interest of the user according to the historical browsing data of the user; the second generating unit is configured to generate the user characteristics according to the points of interest of the user.
  • the features of the aforementioned content of interest include: type information of the content of interest, information of the popularity of the content of interest, and interaction information between the publisher of the content of interest and the user.
  • the foregoing generating module 33 includes:
  • the third generating unit is configured to generate a first coefficient corresponding to each concerned content according to the user characteristics and the type information of each concerned content, wherein the first coefficient corresponding to each concerned content is used to represent the The degree of correlation between each concerned content and the user characteristics;
  • the fourth generating unit is configured to generate a second coefficient corresponding to each concerned content according to the popularity information of each concerned content
  • the fifth generating unit is configured to generate a third coefficient corresponding to each concerned content according to the interaction information between the publisher of each concerned content and the user, wherein the third coefficient corresponding to each concerned content is used Yu represents the degree of interaction between the publisher of each concerned content and the user;
  • the sixth generating unit is configured to generate user interest of the plurality of attention contents according to at least one of the first coefficient, the second coefficient and the third coefficient respectively corresponding to the plurality of attention contents value.
  • the above-mentioned sixth generating unit is specifically configured to: correspond to the first coefficient, the second coefficient, and the first coefficient respectively corresponding to the multiple attention contents At least one of the three coefficients is input into a preset user interest value recognition model to generate the user interest values of the multiple attention content, wherein the preset user interest value recognition model is generated through training.
  • the device 30 for sorting the attention pages described above further includes:
  • the third obtaining module is configured to obtain a plurality of to-be-recommended content matching the user characteristics
  • the recommendation module is configured to recommend the multiple content to be recommended to the user.
  • the above-mentioned device 30 for sorting the attention pages further includes: a fourth acquisition module, which is used to determine the interaction information between the publisher of the attention content and the user To obtain the social preference information of the user;
  • the processing module is configured to generate the person to be recommended of the user according to the social preference information of the user, and recommend the person to be recommended to the user.
  • the device for sorting attention pages can obtain multiple attention content in the attention page, as well as the user characteristics of the user and the characteristics of the multiple attention content, and generate according to the user characteristics and the type information of each attention content
  • the first coefficient representing the correlation between each concerned content and user characteristics, and the second coefficient corresponding to each concerned content is generated according to the popularity information of each concerned content, and then according to the relationship between the publisher and the user of each concerned content
  • Generate a third coefficient corresponding to each focused content and then generate a plurality of users interested in the focused content according to at least one of the first coefficient, the second coefficient, and the third coefficient corresponding to the multiple focused content. Value, and sort the multiple concerned contents according to the interest value of the multiple concerned users.
  • the user’s interest value of each concerned content can be determined according to the user characteristics and the type information and popularity information of each concerned content in the concerned page, and the interaction information between the publisher of the concerned content and the user. Identify the to-be-recommended content that matches the user’s characteristics To accommodate people to be recommended, not only can the user’s interest in the following content be displayed first, which increases the number of clicks on the page content, but also can dig out the content and potential social relations that the user may be interested in, and provide rich content consumption The user experience is further improved.
  • the present disclosure also proposes an electronic device.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the disclosure.
  • the terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (for example, Car navigation terminal) and other mobile terminals and fixed terminals such as digital TV, desktop computer, etc.
  • the electronic device shown in FIG. 4 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device 700 may include a processing device (such as a central processing unit, a graphics processor, etc.) 701, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 702 or from a storage device 708.
  • the programs in the memory (RAM) 703 execute various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 700 are also stored.
  • the processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704.
  • An input/output (I/O) interface 705 is also connected to the bus 704.
  • the following devices can be connected to the I/O interface 705: including input devices 706 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, vibration An output device 707 such as a device; a storage device 708 such as a magnetic tape, a hard disk, etc.; and a communication device 709.
  • the communication device 709 may allow the electronic device 700 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 4 shows an electronic device 700 having various devices, it should be understood that it is not required to implement or have all the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.
  • the process described above with reference to the flowchart can be implemented as a computer software program.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 709, or installed from the storage device 708, or installed from the ROM 702.
  • the processing device 701 executes the above-mentioned functions defined in the method of the embodiment of the present disclosure.
  • the aforementioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium may be any A tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device is caused to: obtain at least two Internet protocol addresses; and send to the node evaluation device including the at least two A node evaluation request for an Internet Protocol address, wherein the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; where the acquired The Internet Protocol address indicates the edge node in the content distribution network.
  • the computer readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; Among the at least two Internet Protocol addresses, an Internet Protocol address is selected; the selected Internet Protocol address is returned; wherein the received Internet Protocol address indicates an edge node in the content distribution network.
  • the computer program code used to perform the operations of the present disclosure may be written in one or more programming languages or a combination thereof.
  • the above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language.
  • the program code may be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN)-or, it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code includes one or more for realizing specified logical functions Executable instructions.
  • the functions noted in the blocks may also occur in a different order than noted in the drawings. For example, two blocks shown in succession may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and a combination of blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs prescribed functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware. Wherein, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • the first obtaining unit can also be described as "a unit for obtaining at least two Internet Protocol addresses.”
  • the electronic device provided by the embodiment of the present disclosure can execute the aforementioned method for sorting the attention pages, obtain multiple attention content in the attention page, and the user characteristics of the user and the characteristics of the multiple attention content, and according to the user characteristics and The characteristics of the multiple attention content generate multiple user interest values of the attention content, and then the multiple attention content is sorted according to the user interest values of the multiple attention content. Therefore, by sorting the attention content according to the user interest value of each attention content, the attention content that the user is interested in can be displayed first, which not only improves the user experience, but also increases the click volume of the page content.
  • the present disclosure also proposes a non-transitory computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for sorting attention pages as described in the foregoing embodiment is implemented.
  • FIG. 5 is a schematic diagram illustrating a computer-readable storage medium according to an embodiment of the present disclosure.
  • a computer-readable storage medium 800 according to an embodiment of the present disclosure has non-transitory computer-readable instructions 810 stored thereon.
  • the non-transitory computer-readable instruction 810 is executed by the processor, all or part of the steps of the method for sorting the attention pages of the aforementioned embodiments of the present disclosure are executed.
  • another embodiment of the present disclosure provides a computer program, which when executed by a processor, implements the method for sorting the attention pages described in the embodiment of the present disclosure.
  • first and second are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with “first” and “second” may explicitly or implicitly include at least one of the features. In the description of the present disclosure, “plurality” means at least two, for example, two, three, etc., unless otherwise specifically defined.
  • a “computer-readable medium” can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, device, or device or in combination with these instruction execution systems, devices, or devices.
  • computer readable media include the following: electrical connections (electronic devices) with one or more wiring, portable computer disk cases (magnetic devices), random access memory (RAM), Read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), optical fiber device, and portable CD-ROM (CDR0M).
  • the computer-readable medium may even be paper or other suitable medium on which the program can be printed, because it can be used for example by optically scanning the paper or other medium, and then editing, interpreting, or other suitable media if necessary. The program is processed in a way to obtain the program electronically and then stored in the computer memory.
  • each part of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof.
  • multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system.
  • Discrete logic gate circuits for implementing logic functions on data signals
  • Logic circuits application specific integrated circuits with suitable combinational logic gates
  • PGA programmable gate array
  • FPGA field programmable gate array
  • the functional units in the various embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
  • the storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种关注页面的排序方法及装置(30),属于互联网技术领域。其中,所述方法包括:获取关注页面中的多个关注内容(101);获取用户的用户特征以及多个关注内容的特征(102);根据用户特征和多个关注内容的特征,生成多个关注内容的用户感兴趣值(103);以及根据多个关注内容的用户感兴趣值,对所述多个关注内容进行排序(104)。由此,通过这种关注页面的排序方法,使得用户感兴趣的关注内容可以优先显示,不仅改善了用户体验,而且增加了页面内容的点击量。

Description

关注页面的排序方法及装置
相关申请的交叉引用
本公开要求北京字节跳动网络技术有限公司于 2019年 01月 24日提交的、申请名称为
“关注页面的排序方法及装置” 的、 中国专利申请号“201910066417. 0” 的优先权。 技术领域
本公开涉及互联网技术领域, 尤其涉及一种关注页面的排序方法及装置。 背景技术
互联网的飞速发展为人们提供了一个全新的信息存储、 加工、 传递和使用的载体, 利 用互联网进行工作、 学习、 娱乐、 社交等已是信息社会的常态。 人们可以通过各种各样的 社交类、 资讯类等内容消费产品, 进行社交、 获取资讯等, 并可以对感兴趣的内容或发布 人进行关注。
相关技术中, 在内容消费产品中, 可以根据内容的发布时间, 对用户关注页面中的内 容进行排序。 但是, 这种关注页面的排序方法, 无法根据用户的兴趣点, 推荐用户感兴趣 的内容, 从而影响了用户体验。 发明内容
本公开提出的关注页面的排序方法、 装置、 电子设备及存储介质, 用于解决相关技术 中, 基于发布时间的关注页面排序方法, 无法根据用户的兴趣点, 推荐用户感兴趣的内容, 影响用户体验的问题。
本公开一方面实施例提出的关注页面的排序方法, 包括: 获取关注页面中的多个关注 内容; 获取用户的用户特征以及所述多个关注内容的特征; 根据所述用户特征和所述多个 关注内容的特征, 生成所述多个关注内容的用户感兴趣值; 以及根据所述多个关注内容的 用户感兴趣值, 对所述多个关注内容进行排序。
可选地, 在第一方面实施例的一种可能的实现形式中, 所述获取用户的用户特征, 包 括:
获取所述用户的历史浏览数据, 其中, 所述历史浏览数据包括以下数据中的至少一个: 用户的点击数据、 关注添加数据、 评论数据、 转发数据;
根据所述用户的历史浏览数据生成所述用户的兴趣点;
根据所述用户的兴趣点生成所述用户特征。
可选地, 在第一方面实施例的另一种可能的实现形式中, 所述关注内容的特征, 包括: 关注内容的类型信息、 关注内容的热度信息和关注内容的发布人与所述用户之间的互 动信息。
可选地, 在第一方面实施例的再一种可能的实现形式中, 所述根据所述用户特征和所 述多个关注内容的特征, 生成所述多个关注内容的用户感兴趣值, 包括:
根据所述用户特征和每个关注内容的类型信息, 生成每个关注内容对应的第一系数, 其中, 所述每个关注内容对应的第一系数用于表示所述每个关注内容与所述用户特征之间 的相关度;
根据每个关注内容的热度信息, 生成每个关注内容对应的第二系数;
根据每个关注内容的发布人与所述用户之间的互动信息, 生成每个关注内容对应的第 三系数, 其中, 所述每个关注内容对应的第三系数用于表示所述每个关注内容的发布人与 所述用户之间的互动程度; 以及
根据所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数中的 至少一个, 生成所述多个关注内容的用户感兴趣值。
可选地, 在第一方面实施例的又一种可能的实现形式中, 所述根据所述多个关注内容 分别对应的所述第一系数、 所述第二系数和所述第三系数中的至少一个, 生成所述多个关 注内容的用户感兴趣值, 包括:
将所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数中的至 少一个输入预设的用户感兴趣值识别模型, 以生成所述多个关注内容的用户感兴趣值, 其 中, 所述预设的用户感兴趣值识别模型通过训练生成。
可选地, 在第一方面实施例的又一种可能的实现形式中, 所述方法, 还包括: 获取与所述用户特征匹配的多个待推荐内容;
将所述多个待推荐内容推荐给所述用户。
可选地, 在第一方面实施例的另一种可能的实现形式中, 所述方法, 还包括: 根据所述关注内容的发布人与所述用户之间的互动信息, 获取所述用户的社交喜好信 息;
根据所述用户的社交喜好信息生成所述用户的待推荐人, 并将所述待推荐人推荐给所 述用户。
本公开另一方面实施例提出的关注页面的排序装置, 包括: 第一获取模块, 用于获取 关注页面中的多个关注内容; 第二获取模块, 用于获取用户的用户特征以及所述多个关注 内容的特征; 生成模块, 用于根据所述用户特征和所述多个关注内容的特征, 生成所述多 个关注内容的用户感兴趣值; 以及排序模块, 用于根据所述多个关注内容的用户感兴趣值, 对所述多个关注内容进行排序。
可选地, 在第二方面实施例的一种可能的实现形式中, 所述第二获取模块, 包括: 获取单元, 用于获取所述用户的历史浏览数据, 其中, 所述历史浏览数据包括以下数 据中的至少一个: 用户的点击数据、 关注添加数据、 评论数据、 转发数据; 第一生成单元, 用于根据所述用户的历史浏览数据生成所述用户的兴趣点; 第二生成单元, 用于根据所述用户的兴趣点生成所述用户特征。
可选地, 在第二方面实施例的另一种可能的实现形式中, 所述关注内容的特征, 包括: 关注内容的类型信息、 关注内容的热度信息和关注内容的发布人与所述用户之间的互 动信息。
可选地, 在第二方面实施例的再一种可能的实现形式中, 所述生成模块, 包括: 第三生成单元, 用于根据所述用户特征和每个关注内容的类型信息, 生成每个关注内 容对应的第一系数, 其中, 所述每个关注内容对应的第一系数用于表示所述每个关注内容 与所述用户特征之间的相关度;
第四生成单元, 用于根据每个关注内容的热度信息, 生成每个关注内容对应的第二系 数;
第五生成单元, 用于根据每个关注内容的发布人与所述用户之间的互动信息, 生成每 个关注内容对应的第三系数, 其中, 所述每个关注内容对应的第三系数用于表示所述每个 关注内容的发布人与所述用户之间的互动程度; 以及
第六生成单元, 用于根据所述多个关注内容分别对应的所述第一系数、 所述第二系数 和所述第三系数中至少一个, 生成所述多个关注内容的用户感兴趣值。
可选地, 在第二方面实施例的又一种可能的实现形式中, 所述第六生成单元, 具体用 于:
将所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数中的至 少一个输入预设的用户感兴趣值识别模型, 以生成所述多个关注内容的用户感兴趣值, 其 中, 所述预设的用户感兴趣值识别模型通过训练生成。
可选地, 在第二方面实施例的又一种可能的实现形式中, 所述装置, 还包括: 第三获取模块, 用于获取与所述用户特征匹配的多个待推荐内容;
推荐模块, 用于将所述多个待推荐内容推荐给所述用户。
可选地, 在第二方面实施例的另一种可能的实现形式中, 所述装置, 还包括: 第四获取模块, 用于根据所述关注内容的发布人与所述用户之间的互动信息, 获取所 述用户的社交喜好信息;
处理模块, 用于根据所述用户的社交喜好信息生成所述用户的待推荐人, 并将所述待 推荐人推荐给所述用户。
本公开再一方面实施例提出的电子设备, 其包括: 处理器和存储器; 其中, 所述处理 器通过读取所述存储器中存储的可执行程序代码来运行与所述可执行程序代码对应的程 序, 以用于实现如前所述的关注页面的排序方法。
本公开又一方面实施例提出的非暂态计算机可读存储介质, 其上存储有计算机程序, 其特征在于, 所述程序被处理器执行时实现如前所述的关注页面的排序方法。 本公开又一方面实施例提出的计算机程序, 该程序被处理器执行时实现如前所述的关 注页面的排序方法。
本公开实施例提供的关注页面的排序方法、 装置、 电子设备、 计算机可读存储介质及 计算机程序, 可以获取关注页面中的多个关注内容, 以及用户的用户特征与多个关注内容 的特征, 并根据用户特征和多个关注内容的特征, 生成多个关注内容的用户感兴趣值, 进 而根据多个关注内容的用户感兴趣值, 对多个关注内容进行排序。 由此, 通过根据各关注 内容的用户感兴趣值, 对各关注内容进行排序, 从而使得用户感兴趣的关注内容可以优先 显示, 不仅改善了用户体验, 而且增加了页面内容的点击量。
本公开附加的方面和优点将在下面的描述中部分给出, 部分将从下面的描述中变得明 显, 或通过本公开的实践了解到。 附图说明
本公开上述的和 /或附加的方面和优点从下面结合附图对实施例的描述中将变得明显 和容易理解, 其中:
本公开上述的和 /或附加的方面和优点从下面结合附图对实施例的描述中将变得明显 和容易理解, 其中:
图 1为本公开实施例所提供的一种关注页面的排序方法的流程示意图;
图 2为本公开实施例所提供的另一种关注页面的排序方法的流程示意图;
图 3本公开实施例所提供的一种关注页面的排序装置的结构示意图;
图 4为公开实施例所提供的一种电子设备的结构示意图;
图 5本公开实施例所提供的一种非暂态计算机可读存储介质的结构示意图。 具体实施方式
下面详细描述本公开的实施例, 所述实施例的示例在附图中示出, 其中自始至终相同 或类似的标号表示相同或类似的要素。 下面通过参考附图描述的实施例是示例性的, 旨在 用于解释本公开, 而不能理解为对本公开的限制。
本公开实施例针对相关技术中, 基于发布时间的关注页面排序方法, 无法根据用户的 兴趣点, 推荐用户感兴趣的内容, 影响用户体验的问题, 提出一种关注页面的排序方法。
本公开实施例提供的关注页面的排序方法, 可以获取关注页面中的多个关注内容, 以 及用户的用户特征与多个关注内容的特征, 并根据用户特征和多个关注内容的特征, 生成 多个关注内容的用户感兴趣值, 进而根据多个关注内容的用户感兴趣值, 对多个关注内容 进行排序。 由此, 通过根据各关注内容的用户感兴趣值, 对各关注内容进行排序, 从而使 得用户感兴趣的关注内容可以优先显示, 不仅改善了用户体验, 而且增加了页面内容的点 击量。
下面参考附图对本公开提供的关注页面的排序方法、 装置、 电子设备、 存储介质及计 算机程序进行详细描述。
图 1为本公开实施例所提供的一种关注页面的排序方法的流程示意图。
如图 1所示, 该关注页面的排序方法, 包括以下步骤:
步骤 101, 获取关注页面中的多个关注内容。
需要说明的是, 用户在网页或者各种 APP中浏览信息时, 可以对自己感兴趣的信息类 型或者发布人进行关注, 从而使得服务器可以定期或者在用户再次访问该网页或再次使用 该 APP时, 向用户优先推送用户关注的内容; 或者可以根据用户对相应关注内容的点击操 作, 显示相应的关注页面。
在本公开实施例中, 在显示关注页面时, 可以首先根据关注页面的标识, 获取关注页 面中的多个关注内容。 其中, 关注页面的标识可以是关注页面的域名、 IP地址等可以将关 注页面唯一确定的信息。
举例来说, 在今日头条 APP中, 用户在关注了作者 A之后, 可以在“我的关注”等类 似页面中, 点击作者 A, 以获取作者 A发布的内容。 因此, 在获取到用户对作者 A的点击 操作之后, 可以生成与作者 A对应的关注页面, 关注页面中的多个关注内容可以包括作者 A发布的多篇文章。
步骤 102, 获取用户的用户特征以及所述多个关注内容的特征。
其中, 用户的用户特征, 是指可以反映用户的兴趣点的特征。 关注内容的特征, 可以 是指关注内容所属的类型, 比如, 可以是娱乐类、 体育类、 时政类、 经济类等。
需要说明的是, 在本公开实施例中, 可以首先根据用户的用户标识, 确定用户的历史 浏览数据, 并根据用户的历史浏览数据, 确定用户浏览过的内容的类型, 以及对各种类型 的内容的点击量, 进而将用户浏览过的内容的类型, 以及对各种类型的内容的点击量, 确 定为用户的用户特征。 其中, 用户的用户标识, 是指可以将用户唯一确定的身份认证信息, 比如, 可以是用户的注册账号。
作为一种可能的实现方式, 关注页面中多个关注内容的特征, 可以是关注内容的类型 信息, 因此, 可以根据多个关注内容发布时, 发布人对各发布内容设置的分类标签, 确定 关注页面中多个关注内容的特征。
作为另一种可能的实现方式, 还可以根据对关注页面中多个关注内容分别进行分词处 理, 并根据每个关注内容中各分词的词频, 将每个关注内容中词频最高的多个分词确定为 每个关注内容的关键词, 进而对每个关注内容中的关键词进行语义分析, 以确定出每个关 注内容的特征。
需要说明的是, 获取用户的用户特征以及关注页面中多个关注内容的特征的方式, 可 以包括但不限于以上列举的情形。 实际使用时, 可以根据实际需要预设用户特征中包括的 内容与关注内容的特征中包括的内容, 以及确定用户特征与关注内容的特征的方式, 本公 开实施例对此不做限定。
步骤 103 , 根据所述用户特征和所述多个关注内容的特征, 生成所述多个关注内容的 用户感兴趣值。
在本公开实施例中,确定出用户的用户特征以及关注页面中多个关注内容的特征之后, 即可根据用户特征与关注页面中多个关注内容的特征, 生成关注页面中多个关注内容的用 户感兴趣值。
具体的, 可以首先根据用户的用户特征中包括的用户浏览过的内容的类型, 确定出关 注页面中用户感兴趣的各关注内容以及用户不感兴趣的各关注内容, 即将关注页面中包括 的与用户浏览过的内容的类型相符的各关注内容, 确定为用户感兴趣的各关注内容; 将关 注页面中包括的类型与用户浏览过的内容的类型不符的各关注内容, 确定为用户不感兴趣 的各关注内容。
作为一种可能的实现方式, 确定出关注页面中包括的用户感兴趣的各关注内容以及用 户不感兴趣的各关注内容之后, 可以根据用户特征中包括的对各种类型的内容的点击量, 确定关注页面中多个关注内容的用户感兴趣值。
具体的, 若用户对某类型的内容的点击量越大, 则可以确定该类型的关注内容的用户 感兴趣值越大; 反之, 则可以确定该类型的关注内容的用户感兴趣值越小; 对于用户未浏 览过的某类型的关注内容, 即关注页面中包括的用户不感兴趣的各关注内容, 则可以将用 户不感兴趣的各关注内容的用户感兴趣值确定为 0。
步骤 104, 根据所述多个关注内容的用户感兴趣值, 对所述多个关注内容进行排序。 在本公开实施例中, 在确定出关注页面中多个关注内容的用户感兴趣值之后, 即可以 根据关注页面中各关注内容的用户感兴趣值, 对关注页面中的各关注内容进行排序。
具体的, 可以根据关注页面中各关注内容的用户感兴趣值, 对关注页面中的各关注内 容进行降序排序。 若关注页面中包括用户感兴趣值相同的关注内容, 则可以根据用户感兴 趣值相同的关注内容的发布时间, 对用户感兴趣值相同的各关注内容进一步排序。 即可以 按照用户感兴趣值相同的各关注内容的发布时间与当前时刻间的时间间隔升序排序, 即将 在后发布的关注内容排列在在前发布的关注内容之前。
本公开实施例提供的关注页面的排序方法, 可以获取关注页面中的多个关注内容, 以 及用户的用户特征与多个关注内容的特征, 并根据用户特征和多个关注内容的特征, 生成 多个关注内容的用户感兴趣值, 进而根据多个关注内容的用户感兴趣值, 对多个关注内容 进行排序。 由此, 通过根据各关注内容的用户感兴趣值, 对各关注内容进行排序, 从而使 得用户感兴趣的关注内容可以优先显示, 不仅改善了用户体验, 而且增加了页面内容的点 击量。
在本公开一种可能实现形式中, 还可以从关注内容的类型信息、 热度信息、 关注内容 的发布人与用户之间的互动信息等多个维度, 确定关注内容的特征与用户特征间的关联, 进而确定出关注页面中多个关注内容的用户感兴趣值, 以进一步提高对关注页面中各关注 内容的排序与用户的兴趣点的相符程度。
下面结合图 2, 对本公开实施例提供的关注页面的排序方法进行进一步说明。
图 2为本公开实施例所提供的另一种关注页面的排序方法的流程示意图。
如图 2所示, 该关注页面的排序方法, 包括以下步骤:
步骤 201, 获取关注页面中的多个关注内容。
上述步骤 201 的具体实现过程及原理, 可以参照上述实施例的详细描述, 此处不再赘 述。
步骤 202 , 获取用户的用户特征以及所述多个关注内容的特征, 其中, 所述关注内容 的特征包括: 关注内容的类型信息、 关注内容的热度信息和关注内容的发布人与所述用户 之间的互动信息。
在本公开实施例中, 可以首先根据用户的用户标识, 确定用户的历史浏览数据, 并根 据用户的历史浏览数据, 确定用户的用户特征。 即在本公开实施例一种可能的实现形式中, 上述步骤 202, 可以包括:
获取所述用户的历史浏览数据, 其中, 所述历史浏览数据包括以下数据中的至少一个: 用户的点击数据、 关注添加数据、 评论数据、 转发数据;
根据所述用户的历史浏览数据生成所述用户的兴趣点;
根据所述用户的兴趣点生成所述用户特征。
需要说明的是,在本公开实施例一种可能的实现形式中,可以根据用户的用户标识(用 户的注册账号等), 获取用户的历史浏览数据, 并从获取的历史浏览数据中, 提取用户的点 击数据、 关注添加数据, 以及评论数据、 转发数据等互动数据。 其中, 用户的点击数据中 可以包括在预设时间段内用户浏览过的内容的类型, 以及对各类型内容的点击量。 关注添 加数据, 是指用户在预设时间段内添加关注的发布人、 内容类型等数据。 评论数据与转发 数据, 是指在预设时间段内用户评论过或转发过的内容类型, 或者评论过或转发过的内容 对应的发布人等。
举例来说, 预设时间段为 1个月, 则可以获取距当前时刻的时间间隔为 1个月内的用 户的历史浏览数据, 并从用户的历史浏览数据中, 提取出 1个月内用户的点击数据、 关注 添加数据, 以及评论数据、 转发数据等互动数据。
需要说明的是, 上述举例仅为示例性的, 不能视为对本公开的限制, 用户的历史浏览 数据中可以包括但不限于以上列举的情形。 实际使用时, 历史浏览数据中包括的各数据以 及预设时间段可以根据实际需要预设, 本公开实施例对此不做限定。
可以理解的是, 近期内的用户的历史浏览数据可以反映出用户近期的兴趣点。 因此, 在本公开实施例中, 可以根据从历史浏览数据中提取的用户的点击数据、 关注添加数据、 评论数据、 转发数据, 生成用户的兴趣点。 具体的, 可以将用户的点击数据中, 点击量最 高的一个或多个内容类型, 确定为用户的兴趣点; 以及将用户的关注添加数据、 评论数据、 转发数据中包括的内容类型, 确定为用户的兴趣点。
举例来说, 用户的点击数据中, 包括体育类、 时政类、 娱乐类三种类型的内容, “体育 类” 内容的点击量为 100, “时政类” 内容的点击量为 80, “娱乐类” 内容的点击量为 10; 用户的关注添加数据中包括发布人 A, 根据发布人 A的标识, 确定发布人 A的标签为“美 妆”, 则可以将用户的兴趣点确定为“体育、 时政、 美妆”。
需要说明的是, 上述举例仅为示例性的, 不能视为对本公开的限制。 实际使用时, 可 以根据实际需要预设用户的历史浏览数据与用户的兴趣点的映射关系, 本公开实施例对此 不做限定。
在本公开实施例中, 确定出用户的兴趣点之后, 即可根据用户的兴趣点, 生成用户的 用户特征。 作为一种可能的实现方式, 可以将用户的兴趣点中包括的内容类型, 以及用户 对兴趣点中包括的各类型内容的点击量, 确定为用户的用户特征。
需要说明的是, 关注页面中的多个关注内容的特征, 可以包括关注内容的类型信息、 关注内容的热度信息、 关注内容的发布人与用户之间的互动信息等多个维度的信息, 以从 多个维度确定关注内容的特征与用户特征间的联系, 从而进一步提高确定出的关注页面中 各关注内容的用户感兴趣值, 与用户的兴趣点的相符程度。
作为一种可能的实现方式, 关注内容的类型信息, 可以根据关注内容发布时, 发布人 对发布内容设置的分类标签, 确定关注页面中多个关注内容的特征; 也可以根据对关注内 容分别分词处理, 并根据关注内容中各分词的词频, 将关注内容中词频最高的多个分词确 定为关注内容的关键词, 进而对关注内容中的关键词进行语义分析, 以确定出关注内容的 类型信息。 关注内容的热度信息可以根据所有用户对该关注内容的点击量确定, 即关注内 容的点击量越多, 关注内容的热度越高; 关注内容的点击量越少, 关注内容的热度越低。 关注内容的发布人与用户之间的互动信息, 可以是指发布人与用户之间的互动频率, 可以 通过发布人的标识与用户的用户标识确定。
需要说明的是, 确定关注内容的类型信息、 关注内容的热度信息、 关注内容的发布人 与用户之间的互动信息的方式, 可以包括但不限于以上列举的情形。 实际使用时, 可以根 据实际需要预设关注内容的特征中包括的维度信息, 以及确定关注内容的特征中包括的各 维度信息的方式, 本公开实施例对此不做限定。
步骤 203, 根据所述用户特征和每个关注内容的类型信息, 生成每个关注内容对应的 第一系数, 其中, 所述每个关注内容对应的第一系数用于表示所述每个关注内容与所述用 户特征之间的相关度。
在本公开实施例中, 确定出用户的用户特征, 以及关注页面多个关注内容的特征之后, 即可以首先根据每个关注内容的特征中包括关注内容的类型信息, 以及用户的用户特征中 包括的用户的兴趣点对应的内容类型, 以及用户对兴趣点对应的各内容类型的点击量, 确 定出关注页面中的每个关注内容与用户的用户特征之间的相关度, 即每个关注内容对应的 第一系数。
具体的, 若关注内容的类型信息与用户的兴趣点对应的内容类型相符, 则可以根据用 户对兴趣点对应的各内容类型的点击量, 确定各关注内容对应的第一系数, 即用户对关注 内容的类型信息对应的内容类型的点击量越高, 该关注内容与用户的用户特征之间的相关 度越大, 即该关注内容对应的第一系数越大; 反之, 该关注内容与用户的用户特征之间的 相关度越小, 即该关注内容对应的第一系数越小。 若关注内容的类型信息与用户的兴趣点 对应的内容类型不相符,即用户的兴趣点对应的内容类型中未包括该关注内容的类型信息, 则可以确定该关注内容与用户的用户特征之间不相关, 即可以将该关注内容对应的第一系 数确定为 0。
举例来说, 用户的用户特征中包括的用户的兴趣点对应的内容类型有: 体育、 时政、 美妆, “体育类” 内容对应的点击量为 100, “时政类” 内容对应的点击量为 80, “美妆类” 内容对应的点击量为 50, 关注页面中包括 3个关注内容, 3个关注内容的类型信息分别为: 体育、 美妆、 经济, 因此, 可以确定类型信息为“体育” 的关注内容对应的第一系数, 大 于类型信息为“美妆” 的关注内容对应的第一系数, 类型信息为“经济” 的关注内容对应 的第一系数为 0。
步骤 204, 根据每个关注内容的热度信息, 生成每个关注内容对应的第二系数。
在本公开实施例中, 可以根据关注内容的热度信息生成关注内容对应的第二系数, 即 关注内容对应的第二系数可以用于表示关注内容的热度。 具体的, 关注内容的热度越高, 即关注内容的点击量越多, 关注内容对应的第二系数越大; 关注内容的热度越低, 即关注 内容的点击量越少, 关注内容对应的第二系数越小。
步骤 205 , 根据每个关注内容的发布人与所述用户之间的互动信息, 生成每个关注内 容对应的第三系数, 其中, 所述每个关注内容对应的第三系数用于表示所述每个关注内容 的发布人与所述用户之间的互动程度。
在本公开实施例中, 可以根据关注页面中每个关注内容的发布人与用户之间的互动信 息, 确定每个关注内容的发布人与用户之间的互动程度, 即每个关注内容对应的第三系数。
作为一种可能的实现方式, 可以首先根据关注页面中每个关注内容的发布人的标识, 以及用户的用户标识, 确定出每个关注内容的发布人与该用户的互动频率, 并根据每个关 注内容的发布人与该用户的互动频率, 确定每个关注内容对应的第三系数。 具体的, 关注 内容的发布人与用户的互动频率越高, 则表示该关注内容的发布人与用户之间的互动程度 越高, 即该关注内容对应的第三系数越大; 关注内容的发布人与用户的互动频率越低, 则 表示该关注内容的发布人与用户之间的互动程度越低,即该关注内容对应的第三系数越小; 若关注内容的发布人与用户之间的互动频率为 0, 则可以将该关注内容对应的第三系数确 定为 0。
举例来说, 关注页面中包括三个关注内容: 关注内容 A、 关注内容 B、 关注内容 C, 关 注内容 A对应的发布人甲与用户的互动频率为 10次,关注内容 B对应的发布人乙与用户的 互动频率为 5次, 关注内容 C对应的发布人丙与用户的互动频率为 0次, 则关注内容 A对 应的第三系数大于关注内容 B对应的第三系数, 关注内容 B对应的第三系数大于关注内容 C对应的第三系数, 且关注内容 C对应的第三系数为 0。
需要说明的是, 上述举例仅为示例性的, 不能视为对本公开的限制。 实际使用时, 可 以根据实际需要预设确定关注页面中各关注内容对应的第三系数的方式, 本公开实施例对 此不做限定。
步骤 206 , 根据所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第 三系数中的至少一个, 生成所述多个关注内容的用户感兴趣值。
需要说明的是, 在本公开实施例中, 关注页面中关注内容的第一系数、 第二系数、 第 三系数越大, 则表示关注内容的特征与用户的用户特征的关联性越大, 即关注内容与用户 的兴趣点的相关度越大。 因此, 可以根据每个关注内容对应的第一系数、 第二系数、 第三 系数中的一个或多个, 确定每个关注内容的用户感兴趣值。
作为一种可能的实现方式, 在根据关注内容对应的第一系数、 第二系数、 第三系数中 的一个或多个, 确定关注内容的用户感兴趣值时, 可以首先将确定关注页面中各关注内容 的感兴趣值需要的各系数, 进行归一化。 比如, 根据关注内容对应的第一系数, 确定关注 页面中各关注内容的感兴趣值, 则可以仅将关注页面中各关注内容对应的第一系数归一化 至相同的区间范围内, 比如将关注页面中各关注内容分别对应的第一系数归一化至 [0, 1] 区间内; 相应的, 若根据关注内容对应的第一系数、 第二系数、 第三系数, 确定关注页面 中各关注内容的感兴趣值, 则可以对关注页面中各关注内容分别对应的第一系数、 第二系 数、 第三系数分别进行归一化。 其中, 归一化后的第一系数、 第二系数、 第三系数的区间 范围可以是不同的。
作为一种可能的实现方式, 若根据关注内容对应的第一系数、 第二系数、 第三系数, 确定关注页面中各关注内容的感兴趣值, 则在对关注页面中各关注内容分别对应的第一系 数、 第二系数、 第三系数, 分别进行归一化之后, 可以将每个关注内容对应的第一系数、 第二系数、 第三系数之和, 确定为每个关注内容的用户感兴趣值; 或者也可以将每个关注 内容对应的第一系数、 第二系数、 第三系数的均值, 确定为每个关注内容的用户感兴趣值。
需要说明的是, 对每个关注内容的用户感兴趣值, 可以是每个关注内容对应的第一系 数、 第二系数、 第三系数的和或者均值, 但不限于此。 实际使用时, 可以根据实际需要确 定对关注内容的用户感兴趣值, 与关注内容对应的第一系数、 第二系数、 第三系数的关系, 本公开实施例对此不做限定。
进一步的, 还可以预先训练出对关注内容的用户感兴趣值进行识别的模型, 并在确定 出关注页面中各关注内容的第一系数、 第二系数、 第三系数之后, 将各关注内容的第一系 数、 第二系数、 第三系数中的至少一个输入训练出的识别模型, 以生成各关注内容的用户 感兴趣值。 即在本公开实施例一种可能的实现形式中, 上述步骤 206, 可以包括:
将所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数输入预 设的用户感兴趣值识别模型, 以生成所述多个关注内容的用户感兴趣值, 其中, 所述预设 的用户感兴趣值识别模型通过训练生成。
需要说明的是, 预设的用户感兴趣值识别模型是通过训练生成的, 在对预设的用户感 兴趣值识别模型进行训练时, 可以首先获取大量关注内容, 作为训练数据, 并根据上述方 法确定出每个训练数据对应的第一系数、 第二系数、 第三系数, 以及对每个训练数据的用 户感兴趣值进行标注, 之后将每个训练数据归一化后的第一系数、 第二系数、 第三系数中 的一个或多个, 以及每个训练数据的标注数据(标注的用户感兴趣值), 输入训练模型进行 训练, 以生成用户感兴趣值识别模型。 之后在确定关注页面中的各关注内容的用户感兴趣 值时, 即可将确定出的各关注内容的第一系数、 第二系数、 第三系数中的一个或多个输入 训练出的用户感兴趣值识别模型, 从而确定出关注页面中各关注内容的用户感兴趣值。 其 中, 确定关注页面中的各关注内容的用户感兴趣值时, 输入用户感兴趣值识别模型的各系 数, 与训练用户感兴趣值识别模型时采用的各系数相同。
步骤 207, 根据所述多个关注内容的用户感兴趣值, 对所述多个关注内容进行排序。 在本公开实施例中, 在确定出关注页面中多个关注内容的用户感兴趣值之后, 即可以 根据关注页面中各关注内容的用户感兴趣值, 对关注页面中的各关注内容进行排序。
具体的, 可以根据关注页面中各关注内容的用户感兴趣值, 对关注页面中的各关注内 容进行降序排序。 若关注页面中包括用户感兴趣值相同的关注内容, 则可以根据用户感兴 趣值相同的关注内容的发布时间或热度信息,对用户感兴趣相同的各关注内容进一步排序。 即可以按照用户感兴趣值相同的各关注内容的发布时间与当前时刻间的时间间隔升序排 序, 即将在后发布的关注内容排列在在前发布的关注内容之前; 或者按照用户感兴趣值相 同的各关注内容的热度降序排序。
进一步的, 还可以根据用户的用户特征, 确定出其他与用户的用户特征相关度高的内 容, 推荐给用户。 即在本公开实施例一种可能的实现形式中, 上述步骤 207之后, 还可以 包括:
获取与所述用户特征匹配的多个待推荐内容;
将所述多个待推荐内容推荐给所述用户。
作为一种可能的实现方式, 可以根据用户的用户特征中包括的用户的兴趣点对应的内 容类型, 以及用户对兴趣点对应的各内容类型的点击量, 确定出与用户特征匹配的多个待 推荐内容, 并将确定出的多个待推荐内容推荐给用户。
具体的, 可以首先根据用户的兴趣点对应的内容类型, 确定出与用户的兴趣点相符的 待推荐内容的类型, 之后根据待推荐内容的类型中各内容的热度信息获取发布时间, 将待 推荐内容的类型中热度较高或发布时间较近的内容, 确定为待推荐内容。 其中, 待推荐内 容的类型可以是一个或多个, 即待推荐内容的类型可以是用户对兴趣点对应的、 点击量最 高的一个或多个内容类型
举例来说, 用户的用户特征中包括的用户的兴趣点对应的内容类型有: 体育、 时政、 美妆, “体育类” 内容对应的点击量为 100, “时政类” 内容对应的点击量为 80, “美妆类” 内容对应的点击量为 50, 则可以将待推荐内容的类型确定为“体育类”, 之后可以根据类 型为“体育类” 的各内容的热度信息或发布时间, 将热度最高的一个或多个内容确定为待 推荐内容, 并推荐给用户; 或者也可以将发布时间最近的一个或多个内容确定为待推荐内 容, 并推荐给用户。
需要说明的是, 上述举例仅为示例性的, 不能视为对本公开的限制。 实际使用时, 待 推荐的内容的类型数量、 待推荐的内容数量以及确定待推荐内容的方式, 可以根据实际需 要预设, 本公开实施例对此不做限定。
进一步的, 还可以根据用户关注内容的发布人与用户之间的互动信息, 确定用户的社 交喜好信息, 进而向用户推荐与用户的社交喜好信息相符的待推荐人, 以挖掘用户潜在的 社交关系。 即在本公开实施例一种可能的实现形式中, 上述步骤 207之后, 还可以包括: 根据所述关注内容的发布人与所述用户之间的互动信息, 获取所述用户的社交喜好信 息;
根据所述用户的社交喜好信息生成所述用户的待推荐人, 并将所述待推荐人推荐给所 述用户。
作为一种可能的实现方式, 可以根据每个关注内容的发布人与用户之间的互动信息, 如用户对关注内容或关注内容的发布人的点赞、 评论、 关注等互动信息, 确定用户的社交 喜好信息。 比如, 可以通过大数据分析的方式, 确定出用户点赞、 评论或关注次数较多的 内容类型或者发布人的标签, 并将确定出的内容类型或者发布人的标签, 确定为用户的社 交喜好信息, 进而根据用户的社交喜好信息, 将与用户的社交喜好信息相符的发布人或其 他用户, 确定为待推荐人, 并推荐给用户。
举例来说, 用户 A经常对“体育类” 的内容以及经常发布“体育类” 内容的发布人评 论和点赞,因此可以将用户 A的社交喜好信息确定为“体育”,之后可以将其他经常发布“体 育类” 内容的发布人确定为待推荐人, 或者将其他经常关注“体育类” 内容的用户, 确定 为待推荐人, 并将确定出的待推荐人推荐给用户 A。
进一步的, 作为另一种可能的实现方式, 还可以根据用户关注的发布人与其他用户的 关注信息, 挖掘出用户的潜在社交关系, 如可能认识的人等, 并推荐给用户。
本公开实施例提供的关注页面的排序方法, 可以获取关注页面中的多个关注内容, 以 及用户的用户特征与多个关注内容的特征, 并根据用户特征和每个关注内容的类型信息, 生成表示每个关注内容与用户特征之间的相关度的第一系数, 以及根据每个关注内容的热 度信息生成每个关注内容对应的第二系数, 之后根据每个关注内容的发布人与用户之间的 互动信息, 生成每个关注内容对应的第三系数, 进而根据多个关注内容分别对应的第一系 数、 第二系数和第三系数中的至少一个, 生成多个关注内容的用户感兴趣值, 并根据多个 关注内容的用户感兴趣值, 对多个关注内容进行排序。 由此, 通过根据用户特征以及关注 页面中各关注内容的类型信息、 热度信息、 关注内容的发布人与用户之间的互动信息, 确 定出各关注内容的用户感兴趣值, 并可以根据用户特征确定出与用户特征匹配的待推荐内 容与待推荐人, 从而不仅可以使得用户感兴趣的关注内容可以优先显示, 增加了页面内容 的点击量, 而且可以挖掘出用户可能感兴趣的内容与潜在的社交关系, 提供了丰富的内容 消费体验, 进一步改善了用户体验。
为了实现上述实施例, 本公开还提出一种关注页面的排序装置。
图 3为本公开实施例提供的一种关注页面的排序装置的结构示意图。
如图 3所示, 该关注页面的排序装置 30, 包括:
第一获取模块 31, 用于获取关注页面中的多个关注内容;
第二获取模块 32, 用于获取用户的用户特征以及所述多个关注内容的特征; 生成模块 33, 用于根据所述用户特征和所述多个关注内容的特征, 生成所述多个关注 内容的用户感兴趣值; 以及
排序模块 34,用于根据多个关注内容的用户感兴趣值,对所述多个关注内容进行排序。 在实际使用时, 本公开实施例提供的关注页面的排序装置, 可以被配置在任意电子设 备中, 以执行前述关注页面的排序方法。
本公开实施例提供的关注页面的排序装置, 可以获取关注页面中的多个关注内容, 以 及用户的用户特征与多个关注内容的特征, 并根据用户特征和多个关注内容的特征, 生成 多个关注内容的用户感兴趣值, 进而根据多个关注内容的用户感兴趣值, 对多个关注内容 进行排序。 由此, 通过根据各关注内容的用户感兴趣值, 对各关注内容进行排序, 从而使 得用户感兴趣的关注内容可以优先显示, 不仅改善了用户体验, 而且增加了页面内容的点 击量。
在本公开一种可能的实现形式中, 上述第二获取模块 32, 包括:
获取单元, 用于获取所述用户的历史浏览数据, 其中, 所述历史浏览数据包括以下数 据中的至少一个: 用户的点击数据、 关注添加数据、 评论数据、 转发数据;
第一生成单元, 用于根据所述用户的历史浏览数据生成所述用户的兴趣点; 第二生成单元, 用于根据所述用户的兴趣点生成所述用户特征。
进一步的, 在本公开另一种可能的实现形式中, 上述关注内容的特征, 包括: 关注内容的类型信息、 关注内容的热度信息和关注内容的发布人与所述用户之间的互 动信息。 在本公开一种可能的实现形式中, 上述生成模块 33, 包括:
第三生成单元, 用于根据所述用户特征和每个关注内容的类型信息, 生成每个关注内 容对应的第一系数, 其中, 所述每个关注内容对应的第一系数用于表示所述每个关注内容 与所述用户特征之间的相关度;
第四生成单元, 用于根据每个关注内容的热度信息, 生成每个关注内容对应的第二系 数;
第五生成单元, 用于根据每个关注内容的发布人与所述用户之间的互动信息, 生成每 个关注内容对应的第三系数, 其中, 所述每个关注内容对应的第三系数用于表示所述每个 关注内容的发布人与所述用户之间的互动程度; 以及
第六生成单元, 用于根据所述多个关注内容分别对应的所述第一系数、 所述第二系数 和所述第三系数中的至少一个, 生成所述多个关注内容的用户感兴趣值。
进一步的, 在本公开另一种可能的实现形式中, 上述第六生成单元, 具体用于: 将所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数中的至 少一个输入预设的用户感兴趣值识别模型, 以生成所述多个关注内容的用户感兴趣值, 其 中, 所述预设的用户感兴趣值识别模型通过训练生成。
在本公开一种可能的实现形式中, 上述关注页面的排序装置 30, 还包括:
第三获取模块, 用于获取与所述用户特征匹配的多个待推荐内容;
推荐模块, 用于将所述多个待推荐内容推荐给所述用户。
进一步的, 在本公开另一种可能的实现形式中, 上述关注页面的排序装置 30, 还包括: 第四获取模块, 用于根据所述关注内容的发布人与所述用户之间的互动信息, 获取所 述用户的社交喜好信息;
处理模块, 用于根据所述用户的社交喜好信息生成所述用户的待推荐人, 并将所述待 推荐人推荐给所述用户。
需要说明的是, 前述对图 1、 图 2所示的关注页面的排序方法实施例的解释说明也适 用于该实施例的推送信息展现装置 30, 此处不再赘述。
本公开实施例提供的关注页面的排序装置, 可以获取关注页面中的多个关注内容, 以 及用户的用户特征与多个关注内容的特征, 并根据用户特征和每个关注内容的类型信息, 生成表示每个关注内容与用户特征之间的相关度的第一系数, 以及根据每个关注内容的热 度信息生成每个关注内容对应的第二系数, 之后根据每个关注内容的发布人与用户之间的 互动信息, 生成每个关注内容对应的第三系数, 进而根据多个关注内容分别对应的第一系 数、 第二系数和第三系数中的至少一个, 生成多个关注内容的用户感兴趣值, 并根据多个 关注内容的用户感兴趣值, 对多个关注内容进行排序。 由此, 通过根据用户特征以及关注 页面中各关注内容的类型信息、 热度信息、 关注内容的发布人与用户之间的互动信息, 确 定出各关注内容的用户感兴趣值, 并可以根据用户特征确定出与用户特征匹配的待推荐内 容与待推荐人, 从而不仅可以使得用户感兴趣的关注内容可以优先显示, 增加了页面内容 的点击量, 而且可以挖掘出用户可能感兴趣的内容与潜在的社交关系, 提供了丰富的内容 消费体验, 进一步改善了用户体验。
为了实现上述实施例, 本公开还提出一种电子设备。
图 4为本公开实施例提供的电子设备的结构示意图。
下面参考图 4, 其示出了适于用来实现本公开实施例的电子设备 700 的结构示意图。 本公开实施例中的终端设备可以包括但不限于诸如移动电话、 笔记本电脑、 数字广播接收 器、 PDA (个人数字助理)、 PAD (平板电脑)、 PMP (便携式多媒体播放器)、 车载终端 (例 如车载导航终端) 等等的移动终端以及诸如数字 TV、 台式计算机等等的固定终端。 图 4示 出的电子设备仅仅是一个示例, 不应对本公开实施例的功能和使用范围带来任何限制。
如图 4所示, 电子设备 700可以包括处理装置(例如中央处理器、 图形处理器等) 701, 其可以根据存储在只读存储器 (ROM) 702中的程序或者从存储装置 708加载到随机访问存 储器 (RAM) 703中的程序而执行各种适当的动作和处理。 在 RAM 703中, 还存储有电子设 备 700操作所需的各种程序和数据。 处理装置 701、 ROM 702以及 RAM 703通过总线 704彼 此相连。 输入 /输出 (I/O) 接口 705也连接至总线 704。
通常, 以下装置可以连接至 I/O接口 705: 包括例如触摸屏、 触摸板、 键盘、 鼠标、 摄像头、 麦克风、 加速度计、 陀螺仪等的输入装置 706 ; 包括例如液晶显示器 (IXD)、 扬 声器、 振动器等的输出装置 707; 包括例如磁带、 硬盘等的存储装置 708; 以及通信装置 709。通信装置 709可以允许电子设备 700与其他设备进行无线或有线通信以交换数据。 虽 然图 4示出了具有各种装置的电子设备 700, 但是应理解的是, 并不要求实施或具备所有 示出的装置。 可以替代地实施或具备更多或更少的装置。
特别地, 根据本公开的实施例, 上文参考流程图描述的过程可以被实现为计算机软件 程序。 例如, 本公开的实施例包括一种计算机程序产品, 其包括承载在计算机可读介质上 的计算机程序, 该计算机程序包含用于执行流程图所示的方法的程序代码。 在这样的实施 例中, 该计算机程序可以通过通信装置 709从网络上被下载和安装, 或者从存储装置 708 被安装, 或者从 ROM 702被安装。 在该计算机程序被处理装置 701执行时, 执行本公开实 施例的方法中限定的上述功能。
需要说明的是, 本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机 可读存储介质或者是上述两者的任意组合。 计算机可读存储介质例如可以是一一但不限于 一一电、 磁、 光、 电磁、 红外线、 或半导体的系统、 装置或器件, 或者任意以上的组合。 计算机可读存储介质的更具体的例子可以包括但不限于: 具有一个或多个导线的电连接、 便携式计算机磁盘、 硬盘、 随机访问存储器 (RAM)、 只读存储器 (R0M)、 可擦式可编程只 读存储器 (EPR0M或闪存)、 光纤、 便携式紧凑磁盘只读存储器 (⑶ -R0M)、 光存储器件、 磁存储器件、 或者上述的任意合适的组合。 在本公开中, 计算机可读存储介质可以是任何 包含或存储程序的有形介质, 该程序可以被指令执行系统、 装置或者器件使用或者与其结 合使用。 而在本公开中, 计算机可读信号介质可以包括在基带中或者作为载波一部分传播 的数据信号, 其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式, 包括但不限于电磁信号、 光信号或上述的任意合适的组合。 计算机可读信号介质还可以是 计算机可读存储介质以外的任何计算机可读介质, 该计算机可读信号介质可以发送、 传播 或者传输用于由指令执行系统、 装置或者器件使用或者与其结合使用的程序。 计算机可读 介质上包含的程序代码可以用任何适当的介质传输, 包括但不限于: 电线、 光缆、 RF (射 频) 等等, 或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的; 也可以是单独存在, 而未装配 入该电子设备中。
上述计算机可读介质承载有一个或者多个程序, 当上述一个或者多个程序被该电子设 备执行时, 使得该电子设备: 获取至少两个网际协议地址; 向节点评价设备发送包括所述 至少两个网际协议地址的节点评价请求, 其中, 所述节点评价设备从所述至少两个网际协 议地址中, 选取网际协议地址并返回; 接收所述节点评价设备返回的网际协议地址; 其中, 所获取的网际协议地址指示内容分发网络中的边缘节点。
或者, 上述计算机可读介质承载有一个或者多个程序, 当上述一个或者多个程序被该 电子设备执行时, 使得该电子设备: 接收包括至少两个网际协议地址的节点评价请求; 从 所述至少两个网际协议地址中, 选取网际协议地址; 返回选取出的网际协议地址; 其中, 接收到的网际协议地址指示内容分发网络中的边缘节点。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序 代码, 上述程序设计语言包括面向对象的程序设计语言一诸如 Java、 Smalltalk、 C++, 还 包括常规的过程式程序设计语言一诸如“C”语言或类似的程序设计语言。 程序代码可以完 全地在用户计算机上执行、 部分地在用户计算机上执行、 作为一个独立的软件包执行、 部 分在用户计算机上部分在远程计算机上执行、 或者完全在远程计算机或服务器上执行。 在 涉及远程计算机的情形中,远程计算机可以通过任意种类的网络一一包括局域网 (LAN)或广 域网 (WAN)—连接到用户计算机, 或者, 可以连接到外部计算机 (例如利用因特网服务提供 商来通过因特网连接)。
附图中的流程图和框图, 图示了按照本公开各种实施例的系统、 方法和计算机程序产 品的可能实现的体系架构、 功能和操作。 在这点上, 流程图或框图中的每个方框可以代表 一个模块、 程序段、 或代码的一部分, 该模块、 程序段、 或代码的一部分包含一个或多个 用于实现规定的逻辑功能的可执行指令。 也应当注意, 在有些作为替换的实现中, 方框中 所标注的功能也可以以不同于附图中所标注的顺序发生。 例如, 两个接连地表示的方框实 际上可以基本并行地执行, 它们有时也可以按相反的顺序执行, 这依所涉及的功能而定。 也要注意的是, 框图和 /或流程图中的每个方框、 以及框图和 /或流程图中的方框的组合, 可以用执行规定的功能或操作的专用的基于硬件的系统来实现, 或者可以用专用硬件与计 算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现, 也可以通过硬件的 方式来实现。 其中, 单元的名称在某种情况下并不构成对该单元本身的限定, 例如, 第一 获取单元还可以被描述为“获取至少两个网际协议地址的单元”。
需要说明的是, 本实施例的电子设备的实施过程和技术原理参见前述对本公开实施例 的关注页面的排序方法的解释说明, 此处不再赘述。
本公开实施例提供的电子设备, 可以执行如前所述的关注页面的排序方法, 获取关注 页面中的多个关注内容, 以及用户的用户特征与多个关注内容的特征, 并根据用户特征和 多个关注内容的特征, 生成多个关注内容的用户感兴趣值, 进而根据多个关注内容的用户 感兴趣值, 对多个关注内容进行排序。 由此, 通过根据各关注内容的用户感兴趣值, 对各 关注内容进行排序, 从而使得用户感兴趣的关注内容可以优先显示, 不仅改善了用户体验, 而且增加了页面内容的点击量。
为了实现上述实施例, 本公开还提出一种非暂态计算机可读存储介质, 其上存储有计 算机程序, 该程序被处理器执行时实现如前述实施例所述的关注页面的排序方法。
图 5为图示根据本公开的实施例的计算机可读存储介质的示意图。 如图 5所示, 根据 本公开实施例的计算机可读存储介质 800, 其上存储有非暂态计算机可读指令 810。 当该非 暂态计算机可读指令 810 由处理器运行时, 执行前述的本公开各实施例的关注页面的排序 方法的全部或部分步骤。
为了实现上述实施例, 本公开再一方面实施例提供一种计算机程序, 该程序被处理器 执行时, 以实现本公开实施例所述的关注页面的排序方法。
在本说明书的描述中, 参考术语“一个实施例”、 “一些实施例”、 “示例”、 “具体示 例”、 或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、 结构、 材料或者 特点包含于本公开的至少一个实施例或示例中。 在本说明书中, 对上述术语的示意性表述 不必须针对的是相同的实施例或示例。 而且, 描述的具体特征、 结构、 材料或者特点可以 在任一个或多个实施例或示例中以合适的方式结合。 此外, 在不相互矛盾的情况下, 本领 域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进 行结合和组合。
此外, 术语“第一”、 “第二”仅用于描述目的, 而不能理解为指示或暗示相对重要性 或者隐含指明所指示的技术特征的数量。 由此, 限定有“第一”、 “第二” 的特征可以明示 或者隐含地包括至少一个该特征。 在本公开的描述中, “多个”的含义是至少两个, 例如两 个, 三个等, 除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为, 表示包括一个 或更多个用于实现定制逻辑功能或过程的步骤的可执行指令的代码的模块、 片段或部分, 并且本公开的优选实施方式的范围包括另外的实现, 其中可以不按所示出或讨论的顺序, 包括根据所涉及的功能按基本同时的方式或按相反的顺序, 来执行功能, 这应被本公开的 实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和 /或步骤, 例如, 可以被认为是用于实 现逻辑功能的可执行指令的定序列表, 可以具体实现在任何计算机可读介质中, 以供指令 执行系统、 装置或设备 (如基于计算机的系统、 包括处理器的系统或其他可以从指令执行 系统、 装置或设备取指令并执行指令的系统) 使用, 或结合这些指令执行系统、 装置或设 备而使用。 就本说明书而言, “计算机可读介质”可以是任何可以包含、 存储、 通信、 传播 或传输程序以供指令执行系统、 装置或设备或结合这些指令执行系统、 装置或设备而使用 的装置。 计算机可读介质的更具体的示例 (非穷尽性列表) 包括以下: 具有一个或多个布 线的电连接部 (电子装置), 便携式计算机盘盒 (磁装置), 随机存取存储器 (RAM), 只读 存储器 (R0M), 可擦除可编辑只读存储器 (EPROM或闪速存储器), 光纤装置, 以及便携式 光盘只读存储器 (CDR0M)。 另外, 计算机可读介质甚至可以是可在其上打印所述程序的纸 或其他合适的介质, 因为可以例如通过对纸或其他介质进行光学扫描, 接着进行编辑、 解 译或必要时以其他合适方式进行处理来以电子方式获得所述程序, 然后将其存储在计算机 存储器中。
应当理解, 本公开的各部分可以用硬件、 软件、 固件或它们的组合来实现。 在上述实 施方式中, 多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或 固件来实现。 如, 如果用硬件来实现和在另一实施方式中一样, 可用本领域公知的下列技 术中的任一项或他们的组合来实现: 具有用于对数据信号实现逻辑功能的逻辑门电路的离 散逻辑电路, 具有合适的组合逻辑门电路的专用集成电路, 可编程门阵列 (PGA), 现场可 编程门阵列 (FPGA) 等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可 以通过程序来指令相关的硬件完成, 所述的程序可以存储于一种计算机可读存储介质中, 该程序在执行时, 包括方法实施例的步骤之一或其组合。
此外, 在本公开各个实施例中的各功能单元可以集成在一个处理模块中, 也可以是各 个单元单独物理存在, 也可以两个或两个以上单元集成在一个模块中。 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。 所述集成的模块如果以 软件功能模块的形式实现并作为独立的产品销售或使用时, 也可以存储在一个计算机可读 取存储介质中。
上述提到的存储介质可以是只读存储器, 磁盘或光盘等。 尽管上面已经示出和描述了 本公开的实施例, 可以理解的是, 上述实施例是示例性的, 不能理解为对本公开的限制, 本领域的普通技术人员在本公开的范围内可以对上述实施例进行变化、修改、 替换和变型。

Claims

权利要求书
1、 一种关注页面的排序方法, 其特征在于, 包括:
获取关注页面中的多个关注内容;
获取用户的用户特征以及所述多个关注内容的特征;
根据所述用户特征和所述多个关注内容的特征, 生成所述多个关注内容的用户感兴趣 值; 以及
根据所述多个关注内容的用户感兴趣值, 对所述多个关注内容进行排序。
2、如权利要求 1所述的关注页面的排序方法,其特征在于,所述获取用户的用户特征, 包括:
获取所述用户的历史浏览数据, 其中, 所述历史浏览数据包括以下数据中的至少一个: 用户的点击数据、 关注添加数据、 评论数据、 转发数据;
根据所述用户的历史浏览数据生成所述用户的兴趣点;
根据所述用户的兴趣点生成所述用户特征。
3、如权利要求 1或 2所述的关注页面的排序方法,其特征在于,所述关注内容的特征, 包括以下信息中的至少一种:
关注内容的类型信息、 关注内容的热度信息和关注内容的发布人与所述用户之间的互 动信息。
4、 如权利要求 3所述的关注页面的排序方法, 其特征在于, 所述根据所述用户特征和 所述多个关注内容的特征, 生成所述多个关注内容的用户感兴趣值, 包括:
根据所述用户特征和每个关注内容的类型信息, 生成每个关注内容对应的第一系数, 其中, 所述每个关注内容对应的第一系数用于表示所述每个关注内容与所述用户特征之间 的相关度;
根据每个关注内容的热度信息, 生成每个关注内容对应的第二系数;
根据每个关注内容的发布人与所述用户之间的互动信息, 生成每个关注内容对应的第 三系数, 其中, 所述每个关注内容对应的第三系数用于表示所述每个关注内容的发布人与 所述用户之间的互动程度; 以及
根据所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数中的 至少一个, 生成所述多个关注内容的用户感兴趣值。
5、 如权利要求 4所述的关注页面的排序方法, 其特征在于, 所述根据所述多个关注内 容分别对应的所述第一系数、 所述第二系数和所述第三系数中的至少一个, 生成所述多个 关注内容的用户感兴趣值, 包括:
将所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数中的至 少一个输入预设的用户感兴趣值识别模型, 以生成所述多个关注内容的用户感兴趣值, 其 中, 所述预设的用户感兴趣值识别模型通过训练生成。
6、 如权利要求 1-5任一所述的关注页面的排序方法, 其特征在于, 还包括: 获取与所述用户特征匹配的多个待推荐内容;
将所述多个待推荐内容推荐给所述用户。
7、 如权利要求 1-6任一所述的关注页面的排序方法, 其特征在于, 还包括: 根据所述关注内容的发布人与所述用户之间的互动信息, 获取所述用户的社交喜好信 息;
根据所述用户的社交喜好信息生成所述用户的待推荐人, 并将所述待推荐人推荐给所 述用户。
8、 一种关注页面的排序装置, 其特征在于, 包括:
第一获取模块, 用于获取关注页面中的多个关注内容;
第二获取模块, 用于获取用户的用户特征以及所述多个关注内容的特征;
生成模块, 用于根据所述用户特征和所述多个关注内容的特征, 生成所述多个关注内 容的用户感兴趣值; 以及
排序模块, 用于根据所述多个关注内容的用户感兴趣值, 对所述多个关注内容进行排 序。
9、如权利要求 8所述的关注页面的排序装置, 其特征在于, 所述第二获取模块, 包括: 获取单元, 用于获取所述用户的历史浏览数据, 其中, 所述历史浏览数据包括以下数 据中的至少一个: 用户的点击数据、 关注添加数据、 评论数据、 转发数据;
第一生成单元, 用于根据所述用户的历史浏览数据生成所述用户的兴趣点; 第二生成单元, 用于根据所述用户的兴趣点生成所述用户特征。
10、 如权利要求 8或 9所述的关注页面的排序装置, 其特征在于, 所述关注内容的特 征, 包括:
关注内容的类型信息、 关注内容的热度信息和关注内容的发布人与所述用户之间的互 动信息。
11、 如权利要求 10所述的关注页面的排序装置, 其特征在于, 所述生成模块, 包括: 第三生成单元, 用于根据所述用户特征和每个关注内容的类型信息, 生成每个关注内 容对应的第一系数, 其中, 所述每个关注内容对应的第一系数用于表示所述每个关注内容 与所述用户特征之间的相关度;
第四生成单元, 用于根据每个关注内容的热度信息, 生成每个关注内容对应的第二系 数;
第五生成单元, 用于根据每个关注内容的发布人与所述用户之间的互动信息, 生成每 个关注内容对应的第三系数, 其中, 所述每个关注内容对应的第三系数用于表示所述每个 关注内容的发布人与所述用户之间的互动程度; 以及 第六生成单元, 用于根据所述多个关注内容分别对应的所述第一系数、 所述第二系数 和所述第三系数中的至少一个, 生成所述多个关注内容的用户感兴趣值。
12、 如权利要求 11所述的关注页面的排序装置, 其特征在于, 所述第六生成单元, 具 体用于:
将所述多个关注内容分别对应的所述第一系数、 所述第二系数和所述第三系数中的至 少一个输入预设的用户感兴趣值识别模型, 以生成所述多个关注内容的用户感兴趣值, 其 中, 所述预设的用户感兴趣值识别模型通过训练生成。
13、 如权利要求 8-12任一所述的关注页面的排序装置, 其特征在于, 还包括: 第三获取模块, 用于获取与所述用户特征匹配的多个待推荐内容;
推荐模块, 用于将所述多个待推荐内容推荐给所述用户。
14、 如权利要求 8-13任一所述的关注页面的排序装置, 其特征在于, 还包括: 第四获取模块, 用于根据所述关注内容的发布人与所述用户之间的互动信息, 获取所 述用户的社交喜好信息;
处理模块, 用于根据所述用户的社交喜好信息生成所述用户的待推荐人, 并将所述待 推荐人推荐给所述用户。
15、 一种电子设备, 其特征在于, 包括处理器和存储器;
其中, 所述处理器通过读取所述存储器中存储的可执行程序代码来运行与所述可执行 程序代码对应的程序, 以用于实现如权利要求 1-7中任一所述的关注页面的排序方法。
16、 一种非暂态计算机可读存储介质, 其上存储有计算机程序, 其特征在于, 该程序 被处理器执行时, 实现如权利要求 1-7中任一所述的关注页面的排序方法。
PCT/CN2020/072226 2019-01-24 2020-01-15 关注页面的排序方法及装置 Ceased WO2020151548A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910066417.0A CN109783740A (zh) 2019-01-24 2019-01-24 关注页面的排序方法及装置
CN201910066417.0 2019-01-24

Publications (1)

Publication Number Publication Date
WO2020151548A1 true WO2020151548A1 (zh) 2020-07-30

Family

ID=66502254

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/072226 Ceased WO2020151548A1 (zh) 2019-01-24 2020-01-15 关注页面的排序方法及装置

Country Status (2)

Country Link
CN (1) CN109783740A (zh)
WO (1) WO2020151548A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109783740A (zh) * 2019-01-24 2019-05-21 北京字节跳动网络技术有限公司 关注页面的排序方法及装置
CN110263237A (zh) * 2019-05-31 2019-09-20 精硕科技(北京)股份有限公司 舆情数据的获取方法和装置
CN110971507B (zh) * 2019-11-26 2022-03-22 维沃移动通信有限公司 一种信息显示方法及电子设备
CN112131459B (zh) * 2020-08-07 2021-06-01 广州工商学院 基于大数据的知识产权信息检索软件管理系统及方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102841908A (zh) * 2011-06-21 2012-12-26 富士通株式会社 微博内容排序方法和微博内容排序装置
US20140258283A1 (en) * 2013-03-11 2014-09-11 Hon Hai Precision Industry Co., Ltd. Computing device and file searching method using the computing device
CN104933170A (zh) * 2015-06-30 2015-09-23 小米科技有限责任公司 信息展示方法及装置
CN105117425A (zh) * 2015-07-31 2015-12-02 北京奇虎科技有限公司 选择兴趣点poi数据的方法及装置
CN105653737A (zh) * 2016-03-01 2016-06-08 广州神马移动信息科技有限公司 用于内容文档排序的方法、设备和电子设备
CN109783740A (zh) * 2019-01-24 2019-05-21 北京字节跳动网络技术有限公司 关注页面的排序方法及装置

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101882162B (zh) * 2010-06-29 2016-05-11 北京搜狗科技发展有限公司 一种网络信息推送方法及系统
US10296653B2 (en) * 2010-09-07 2019-05-21 F5 Networks, Inc. Systems and methods for accelerating web page loading
CN102402518A (zh) * 2010-09-09 2012-04-04 中国移动通信有限公司 一种访问网页的方法及装置
CN105868291A (zh) * 2012-07-10 2016-08-17 北京奇虎科技有限公司 推荐网址的方法、装置及系统
CN103970796A (zh) * 2013-02-04 2014-08-06 深圳市世纪光速信息技术有限公司 查询偏好排序方法和装置
CN103150678B (zh) * 2013-03-12 2014-12-10 中国科学院计算技术研究所 微博中用户间潜在关注关系的发现方法及装置
CN104463615A (zh) * 2013-09-20 2015-03-25 祁勇 一种互联网广告的个性化精准投放方法
CN103778260A (zh) * 2014-03-03 2014-05-07 哈尔滨工业大学 一种个性化微博信息推荐系统和方法
CN105302807B (zh) * 2014-06-06 2020-01-10 腾讯科技(深圳)有限公司 一种获取信息类别的方法和装置
CN104239399B (zh) * 2014-07-14 2017-08-01 上海交通大学 社交网络中的潜在好友推荐方法
CN105069003B (zh) * 2015-06-15 2018-06-29 北京工业大学 一种基于转发链相似度的用户关注对象推荐计算方法
CN105183803A (zh) * 2015-08-25 2015-12-23 天津大学 一种社交网络平台中的个性化搜索方法及其搜索装置
CN106021363B (zh) * 2016-05-10 2019-12-17 百度在线网络技术(北京)有限公司 课程推荐方法和装置
CN107403389A (zh) * 2017-07-17 2017-11-28 广州特道信息科技有限公司 微博用户的潜在特征的挖掘方法及装置
CN108090206A (zh) * 2017-12-28 2018-05-29 北京小米移动软件有限公司 评论信息的排序方法及装置、电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102841908A (zh) * 2011-06-21 2012-12-26 富士通株式会社 微博内容排序方法和微博内容排序装置
US20140258283A1 (en) * 2013-03-11 2014-09-11 Hon Hai Precision Industry Co., Ltd. Computing device and file searching method using the computing device
CN104933170A (zh) * 2015-06-30 2015-09-23 小米科技有限责任公司 信息展示方法及装置
CN105117425A (zh) * 2015-07-31 2015-12-02 北京奇虎科技有限公司 选择兴趣点poi数据的方法及装置
CN105653737A (zh) * 2016-03-01 2016-06-08 广州神马移动信息科技有限公司 用于内容文档排序的方法、设备和电子设备
CN109783740A (zh) * 2019-01-24 2019-05-21 北京字节跳动网络技术有限公司 关注页面的排序方法及装置

Also Published As

Publication number Publication date
CN109783740A (zh) 2019-05-21

Similar Documents

Publication Publication Date Title
CN109522483B (zh) 用于推送信息的方法和装置
CN103699619A (zh) 一种用于提供搜索结果的方法及装置
US10097664B2 (en) Recommending media items based on purchase history
CN111522927B (zh) 基于知识图谱的实体查询方法和装置
CN113688310B (zh) 一种内容推荐方法、装置、设备及存储介质
CN110059172B (zh) 基于自然语言理解的推荐答案的方法和装置
CN107992554A (zh) 提供问答信息的聚合结果的搜索方法和装置
CN106096037A (zh) 基于人工智能的搜索结果聚合方法、装置以及搜索引擎
US20150254349A1 (en) System and Method for Providing Content in Real-Time
WO2021135319A1 (zh) 基于深度学习的文案生成方法、装置及电子设备
CN116304007A (zh) 一种信息推荐方法、装置、存储介质及电子设备
WO2020151548A1 (zh) 关注页面的排序方法及装置
CN107526718B (zh) 用于生成文本的方法和装置
CN106681598B (zh) 信息输入方法和装置
CN108369806A (zh) 可配置的通用语言理解模型
CN114722292A (zh) 书籍搜索方法、装置、设备和存储介质
CN111897950A (zh) 用于生成信息的方法和装置
CN108351891A (zh) 基于计算装置的属性的信息排名
CN110245298A (zh) 用于推送信息的方法和装置
CN108140055A (zh) 触发应用信息
CN113420723A (zh) 获取视频热点的方法、装置、可读介质和电子设备
CN108111603A (zh) 信息推荐方法、装置、终端设备及存储介质
CN112182386B (zh) 一种基于知识图谱的目标推荐方法及装置
CN110489563A (zh) 图结构的表示方法、装置、设备及计算机可读存储介质
KR101607919B1 (ko) 메신저에 검색 기능을 제공하고 검색 결과를 정렬하는 방법과 시스템 및 기록 매체

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: 20744271

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

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

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 20744271

Country of ref document: EP

Kind code of ref document: A1