WO2023226760A1 - 一种话题推荐方法、装置、计算机设备及存储介质 - Google Patents

一种话题推荐方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2023226760A1
WO2023226760A1 PCT/CN2023/093190 CN2023093190W WO2023226760A1 WO 2023226760 A1 WO2023226760 A1 WO 2023226760A1 CN 2023093190 W CN2023093190 W CN 2023093190W WO 2023226760 A1 WO2023226760 A1 WO 2023226760A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
topic
recommended
book
recommendation
Prior art date
Application number
PCT/CN2023/093190
Other languages
English (en)
French (fr)
Inventor
李晓洁
周雄达
李菁华
屈京
肖功伟
曾豪
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2023226760A1 publication Critical patent/WO2023226760A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/335—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques

Definitions

  • Embodiments of the present disclosure relate to a topic recommendation method, device, computer equipment, and storage medium.
  • users can select books of interest to read. After the user selects a book, if he wants to find other books of interest, he can only find new books of interest by previewing the introduction of more books or previewing the content, which results in low efficiency in finding books of interest.
  • Embodiments of the present disclosure provide at least one topic recommendation method, device, computer equipment, and storage medium.
  • embodiments of the present disclosure provide a topic recommendation method, including: in response to satisfying preset display conditions, determining target books to be displayed under the preset display conditions; and obtaining target recommendations that match the target books. Topics; display recommended books and the target recommended topics in a display manner that matches the preset display conditions; the recommended books at least include the target books.
  • the preset display conditions include at least one of the following: the current display page is the last page of a chapter of a reading book, the current display page is a book recommendation page; the response satisfies the preset display conditions, Determining the target book to be displayed under the preset display conditions includes: responding that the current display page is the last page of a chapter of a reading book, and using the reading book as the target book; or responding that the current display page is a book recommendation page , obtain at least one first recommended book, and use the at least one first recommended book as the target book.
  • the recommended books when the currently displayed page is the last page of a chapter of a reading book, the recommended books also include a second recommended book; the method further includes: recommending each topic under the topic based on the target Each recommended book information in the post is used to determine the second recommended book that matches the target recommended topic.
  • obtaining target recommended topics that match the target book includes: determining candidate recommended topics whose matching degree with the target book is greater than a set threshold; based on each of the candidates The number of converted readers corresponding to the recommended topics is ranked, and the target recommended topic is determined from the candidate recommended topics based on the sorting results; the number of converted readers refers to the number of converted readers who read the candidate recommended topics Finally, the number of new users who read books included in the candidate recommended topics.
  • the matching degree between the target book and any topic is determined according to the following steps: for any topic, the first classification information based on the topic, and the second classification of the target book information to determine how well the topic matches the target book.
  • the first classification information and the second classification information respectively have multiple classification levels; for any topic, the first classification information based on the topic and the second classification of the target book information to determine the matching degree between the topic and the target book, including: for any classification level, the first classification level information under the classification level based on the first classification information, and the second classification level information of the second classification information under the classification level, determining the level matching degree between the topic and the target book under the classification level; based on the level matching degree respectively determined under multiple classification levels, Determine how well the topic matches the target book.
  • displaying the recommended books and the target recommended topic in a display manner that matches the preset display conditions includes: when the preset display conditions include: the current display page In the case of reading the last page of a chapter of a book, each target recommended topic is displayed in sequence on the last page of the chapter, and under each target recommended topic, each recommended book matching the target recommended topic is displayed; or, in the predetermined time, It is assumed that the display conditions include: when the current display page is a book recommendation page, each recommended book and each target recommendation topic matched by the recommended book are displayed in sequence on the book recommendation page.
  • displaying each recommended book matching the target recommended topic includes: based on the target recommended topic corresponding to each recommended book.
  • the reading popularity determines the display order of the recommended books, and under the target recommendation topic, the recommended books are displayed in sequence according to the determined display order.
  • displaying each recommended book on the book recommendation page in sequence includes: based on the book consumption characteristics corresponding to each recommended book, determining each recommended book.
  • displaying the target recommended topic includes: obtaining topic attribute information corresponding to the target recommended topic; based on the topic attribute information corresponding to the target recommended topic and/or related to the target recommended topic
  • Each matching first recommended book generates a recommendation reason for the target recommended topic; wherein the recommendation reason is used to establish the target recommended topic and the Association of the first recommended book; based on the target text corresponding to the recommendation reason of the target recommended topic, replace the original text of the target recommended topic; based on the target text, display the updated target recommended topic.
  • the method further includes: in response to the first triggering operation on the target recommended topic, selecting each topic under the target recommended topic. Among the posts, determine the target topic post related to the recommended book; in response to the target topic post including multiple, display the topic post directory corresponding to the target topic post, and respond to any one of the topic post directory A second triggering operation of the target topic post is to display the target topic post, or in response to the target topic post including one, to display the target topic post.
  • embodiments of the present disclosure also provide a topic recommendation device, including: a determination module, configured to determine target books to be displayed under the preset display conditions in response to satisfying the preset display conditions; and an acquisition module, configured to Obtain target recommended topics that match the target books; a display module is used to display recommended books and the target recommended topics in a display manner that matches the preset display conditions; the recommended books at least include the target books .
  • the preset display conditions include at least one of the following: the current display page is the last page of a chapter of a book, and the current display page is a book recommendation page; Display conditions, when determining the target book to be displayed under the preset display conditions, are used to: respond that the current display page is the last page of a chapter of a reading book, and use the reading book as the target book; or, respond to the current display
  • the page is a book recommendation page, at least one first recommended book is obtained, and the at least one first recommended book is used as the target book.
  • the recommended books when the currently displayed page is the last page of a chapter of a reading book, the recommended books also include a second recommended book; the topic recommendation device further includes a processing module, configured to: based on the Describe the recommended book information in each topic post under the target recommended topic to ensure The second recommended book matching the target recommended topic is determined.
  • the acquisition module when acquiring a target recommendation topic that matches the target book, is configured to: determine candidate recommendation topics whose matching degree with the target book is greater than a set threshold; Based on the number of converted readers corresponding to each of the candidate recommended topics, the candidate recommended topics are sorted, and the target recommended topic is determined from the candidate recommended topics based on the ranking results; the number of converted readers refers to the number of converted readers who read After the candidate recommended topic is selected, the number of new users who read the books included in the candidate recommended topic.
  • the acquisition module determines the matching degree between the target book and any topic according to the following steps: for any topic, the first classification information based on the topic, and the target book The second classification information determines the matching degree between the topic and the target book.
  • the first classification information and the second classification information respectively have multiple classification levels; for any topic, the acquisition module selects the first classification information based on the topic and the target
  • the second classification information of the book when determining the matching degree between the topic and the target book, is used to: for any classification level, the first classification level information under the classification level based on the first classification information, and the second classification
  • the second classification level information of the information under the classification level determines the level matching degree between the topic and the target book under the classification level; based on the level matching degree determined respectively under multiple classification levels, determines the level matching degree between the topic and the target book under the classification level.
  • the matching degree of the target book is used to: for any classification level, the first classification level information under the classification level based on the first classification information, and the second classification The second classification level information of the information under the classification level determines the level matching degree between the topic and the target book under the classification level; based on the level matching degree determined respectively under multiple classification levels, determines the level matching degree between the topic and the target book under the classification level.
  • the display module when displaying the recommended books and the target recommended topics in a display manner that matches the preset display conditions, is configured to: Including: when the current display page is the last page of a chapter of a reading book, each target recommended topic is displayed in sequence on the last page of the chapter, and under each target recommended topic, each recommended book matching the target recommended topic is displayed; or , the preset display conditions include: when When the previous display page is a book recommendation page, each recommended book and each target recommendation topic matching the recommended book are displayed in sequence on the book recommendation page.
  • the display module when displaying each recommended book matching the target recommendation topic, is configured to: based on each of the recommended books under the target recommendation topic The corresponding reading popularity of the recommended books determines the display order of the recommended books. Under the target recommendation topic, the recommended books are displayed in sequence according to the determined display order.
  • the display module is configured to: based on the book consumption characteristics corresponding to each of the recommended books. , determine the display order of each of the recommended books; the book consumption characteristics include the number of readers and the reading time; on the book recommendation page, display the recommended books based on the determined display order of each of the recommended books.
  • the display module when displaying the target recommended topic, is configured to: obtain topic attribute information corresponding to the target recommended topic; based on the topic attribute information corresponding to the target recommended topic and/ Or each first recommended book matching the target recommended topic generates a recommendation reason for the target recommended topic; wherein the recommendation reason is used to establish an association between the target recommended topic and the first recommended book; based on The target text corresponding to the recommendation reason of the target recommended topic replaces the original text of the target recommended topic; based on the target text, the updated target recommended topic is displayed.
  • the display module is further configured to: in response to the first triggering operation on the target recommended topic, download the target recommended topic from the target recommended topic. Among each topic post, determine the target topic post related to the recommended book; in response to the target topic post including multiple, display the topic post directory corresponding to the target topic post, And in response to a second triggering operation on any target topic post in the topic list, display the target topic post, or in response to the target topic post including one, display the target topic post.
  • an optional implementation manner of the present disclosure also provides a computer device, a processor, and a memory.
  • the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the instructions stored in the memory.
  • Machine-readable instructions when the machine-readable instructions are executed by the processor, when the machine-readable instructions are executed by the processor, the above-mentioned first aspect, or any possible implementation of the first aspect, is executed. steps in the way.
  • an optional implementation manner of the present disclosure also provides a computer-readable storage medium.
  • the computer-readable storage medium stores a computer program. When the computer program is run, it executes the above-mentioned first aspect, or any of the first aspects. steps in a possible implementation.
  • the topic recommendation methods, devices, computer equipment and storage media can first determine the books that the user is interested in, that is, the corresponding books to be displayed under different display conditions. target books. Using the target book, the target recommended topic matching the target book can be obtained, so that the target recommended topic and the recommended books containing the target book can be displayed under different display conditions. In this way, in addition to the determined books of interest, the user can directly obtain other books of interest from the displayed recommended books and target recommended topics, thereby improving the efficiency of finding books of interest.
  • Figure 1 shows a flow chart of a topic recommendation method provided by an embodiment of the present disclosure
  • Figure 2 shows a schematic diagram of the last page of a chapter of a book provided by an embodiment of the present disclosure
  • Figure 3 shows a schematic diagram of a book recommendation page provided by an embodiment of the present disclosure
  • Figure 4 shows a schematic diagram of displaying recommended books and target recommended topics on the last page of a chapter of a reading book provided by an embodiment of the present disclosure
  • Figure 5 shows a schematic diagram of displaying recommended books and target recommended topics on a book recommendation page provided by an embodiment of the present disclosure
  • Figure 6 shows another schematic diagram of displaying recommended books and target recommended topics on a book recommendation page provided by an embodiment of the present disclosure
  • Figure 7 shows a schematic diagram of displaying target topic posts provided by an embodiment of the present disclosure
  • Figure 8 shows a schematic diagram of a topic recommendation device provided by an embodiment of the present disclosure.
  • FIG. 9 shows a schematic diagram of a computer device provided by an embodiment of the present disclosure.
  • the present disclosure provides a topic recommendation method.
  • the books that the user is interested in can first be determined, that is, the corresponding target books to be displayed under different display conditions.
  • the target book the target recommended topic matching the target book can be obtained, so that the target recommended topic and the recommended books containing the target book can be displayed under different display conditions.
  • the user can directly obtain other books of interest from the displayed recommended books and target recommended topics, thereby improving the efficiency of finding books of interest.
  • the execution subject of the topic recommendation method provided by an embodiment of the present disclosure is generally a computer device with certain computing capabilities.
  • the computer Devices include, for example: terminal devices or servers or other processing devices.
  • the terminal devices can be user equipment (User Equipment, UE), mobile devices, user terminals, terminals, cellular phones, cordless phones, personal digital assistants (Personal Digital Assistant, PDA) , handheld devices, computing devices, vehicle-mounted devices, wearable devices, etc.
  • the topic recommendation method can be implemented by a processor calling computer-readable instructions stored in a memory.
  • FIG. 1 a flow chart of a topic recommendation method provided by an embodiment of the present disclosure is shown.
  • the method includes steps S101 to S103, wherein:
  • S103 Display recommended books and the target recommended topic according to a display method that matches the preset display conditions; the recommended books at least include the target book.
  • the preset display conditions include at least one of the following: the current display page is the last page of a chapter of a reading book, and the current display page is a book recommendation page.
  • FIG. 2 is a schematic diagram of the last page of a chapter of a book provided by an embodiment of the present disclosure.
  • the user when the user reads a book, in response to turning the displayed reading page Page operation allows you to read chapters of books.
  • the preset display conditions when determining to display the last reading page corresponding to any chapter, it is determined that the preset display conditions are met, that is, the current display interface is the last page of the chapter of the book.
  • the chapter end page of a book may include the end pages of other chapters in the book except the last chapter, it may also include the chapter end page of the last chapter in the book, that is, the updated last page of the book, so in Figure 2 Two schematic diagrams (a) and (b) illustrate two different situations.
  • the reading book being read can be determined as the target book. Since the target book is a book that the user is reading or has finished reading, it can be considered that the user is more interested in content related to the book. Therefore, the target recommended topics that match the target books obtained in the subsequent steps will be closer to the topics that the user is interested in, thereby improving the efficiency of using the displayed topics to find other books.
  • FIG. 3 is a schematic diagram of a book recommendation page provided by an embodiment of the present disclosure.
  • the schematic diagram shows some recommended books, and specifically displays the book cover, title, author and other information.
  • the book recommendation page also includes a trigger button to view the complete list. In response to the triggering operation of the trigger button, a list in the form of a list of all recommended books can be displayed.
  • the book recommendation page includes multiple recommended books displayed.
  • the displayed recommended book is called the first recommended book.
  • the first recommended book can specifically be a book that is close to the user's reading preferences determined by using the historical reading data obtained by the user's authorization, or it can also be a predetermined recommended book, such as a book that is currently hotly recommended by other users, or a hotly recommended book on the platform. books.
  • the book recommendation page that can be displayed is determined to meet the preset display conditions.
  • the target books to be displayed under the preset display conditions you can Get at least one first recommended book in the book recommendation page, and set at least one first recommended book as a target book.
  • the target recommended topic that matches the target book obtained in the subsequent steps can also be close to the topic that the user is interested in, or Including topics that the platform hopes to recommend to users for display.
  • the target recommended topics matching the target books can also be obtained, so as to expand the display of the target books in the form of topics on the basis of displaying the target books. .
  • the following method when obtaining the target recommended topic that matches the target book, the following method can be used: determine the candidate recommended topic whose matching degree with the target book is greater than the set threshold; based on each of the candidate recommended topics The corresponding number of converted readers is ranked, and the target recommended topic is determined from the candidate recommended topics based on the sorting results; the number of converted readers refers to the number of converted readers after reading the candidate recommended topics. The number of new users who read books included in the candidate recommended topics.
  • target recommended topics matching the target book may be determined for display. Since there may be a large number of topics that match the target book in the e-reading platform, you can first determine the matching degree between the target book and each topic, and then filter out some recommended topics from each topic based on the set threshold as candidate recommended topics. .
  • the following method may be adopted: for any topic, based on the first classification information of the topic and the second classification information of the target book, determine The match between the recommended topic and the target book.
  • the topic and the target book can be classified in the same or similar way, so the topic and The target books can specifically have the same or similar classification information.
  • the book type corresponding to the book discussed under the topic is used as the first classification information of the topic
  • the book type corresponding to the target book is used as the second classification information, where the book type is, for example, novels, poems, autobiographies, and essays. If the book type of the target book is a novel, and there is a certain topic, and the book type corresponding to the book discussed under the topic is a novel, it can be considered that the matching degree between the topic and the target book is relatively high.
  • the topics filtered out may not necessarily be well related to the target books in the content under the classification. Therefore, when determining the classification information, multiple classification levels can also be determined. For example, novels and poetry are considered as the first classification level. For novels in the first classification level, science fiction novels, romance novels, and fantasy novels are determined as corresponding The second level of classification level. For the poetry in the first level of classification level, modern poetry and modern poetry are determined to be the corresponding second level of classification level, etc.
  • any classification level based on the first classification level information of the first classification information under the classification level and the second classification level information under the second classification level, it can be determined whether the topic and the target book are at that classification level.
  • the level matching degree under the classification level based on the level matching degree respectively determined under multiple classification levels, determine the matching degree between the topic and the target book.
  • the topics and target books can be determined one by one at the classification level.
  • Corresponding first classification level information and second classification level Level information is consistent to determine the hierarchical matching degree of the topic and the target book under each classification level.
  • classification hierarchy also has two mutually exclusive types, including modern poetry and modern poetry.
  • Example scenario 1 In the first classification level, if the first classification information of the topic is novels under the classification level, the second classification information of the target book is the second classification level information under the classification level. For poetry, since they are classified into two mutually exclusive types, it can be determined that the level matching between this topic and the target book under this classification level is low. In this case, since the next classification level is determined based on this classification level and is a further subdivision, if the level matching degree is determined to be low in this classification level, there is no need to determine the level matching degree of the next classification level. . and determine that the topic is a low match to the target book. If a numerical value is used to represent the matching degree between the topic and the target book, for example, the numerical value can be set to 0.
  • Example scenario 2 In the first classification level, if the first classification information of the topic is the first classification information under the classification level, and the second classification information of the target book is the second classification level information under the classification level, both are Poetry, it can be determined that the topic and the target book have a high level of matching under this classification level. However, since the classification methods at higher classification levels are relatively broad, if a numerical value is used to represent the hierarchical matching degree of this classification level, for example, the value can be set to 1, which means that the topic and the target book are at least at this classification level. matched.
  • the first classification information of the topic under the second classification level is modern poetry
  • the second classification information of the target book is under the second classification level
  • the two are mutually exclusive types in the second classification level.
  • the first The level matching degree determined in the classification level is 1. Since the classification method of the first classification level is relatively broad, the matching degree of the topic and the target book can be determined through a weighted method, such as setting the level matching degree corresponding to the first classification level. If the weight value is 0.5, then the level matching degree 1 of the first category is calculated with the weight value 0.5, and the matching degree between the topic and the target book is 0.5.
  • Example Scenario 3 Continue the hierarchical matching between the topic and the target book at the first classification level in the above Example Scenario 2 at the classification level.
  • the first classification information of the topic is the first classification level information under the second classification level
  • the second classification information of the target book is the second classification level information under the second classification level. All are modern poems.
  • it is determined that the topic and the target book are also the same under the subdivision classification of the second classification level. Therefore, it can be determined that the level matching degree of the topic and the target book under the second classification level is also relatively high. For example, it is determined that the The level matching degree between the topic and the target book at the two-category level is 1.
  • the weight value of the hierarchical matching degree can be set for the second classification level, such as 0.2. Therefore, using the weight value 0.5 set at the first classification level and the weight value 0.2 set at the second classification level, the matching degree between the topic and the target book can be calculated to be 0.7.
  • the classification hierarchy may also include types that can be selected from multiple sources.
  • the first classification level includes genre novels, and under the genre of novels, the genres in the second classification level can include romance, time travel, ancient style, struggle, etc.
  • the first classification information of the topic includes romance, time travel and ancient genre under the second classification level
  • the second classification information of the target book is under the second classification level information of the second classification level, Including romance, ancient style and struggle, it is matched at least under the two categories of romance and ancient style. It is considered that this topic has a high level of matching with the target book under the second classification level.
  • the first classification information of the topic only includes crossing under the second classification level, and cannot match any type of the second classification level information, it is considered that the topic is in the same category as the target book.
  • the level matching degree under the second classification level is low.
  • the obtained matching between the topic and the target book can be made more accurate.
  • candidate recommended topics can be determined from each topic by setting a threshold.
  • the threshold can be set artificially, such as 0.75 or 0.8, to obtain a sufficient number of candidate recommendation topics.
  • it can also be dynamically adjusted according to the actual situation. For example, if there are currently many topics that can be determined, and the matching degree between a large proportion of topics and the target book in each topic is greater than 0.8, then the set threshold can be dynamically adjusted to increase , for example, increase it to 0.85 to screen out an appropriate number of candidate recommendation topics.
  • the candidate recommendation topics can also be sorted based on the number of converted readers corresponding to each candidate recommendation topic, and the target recommendation topic can be determined from the candidate recommendation topics based on the sorting results.
  • the number of converted readers refers to the number of new users who read books included in the candidate recommended topics after reading the candidate recommended topics.
  • multiple candidate recommendation topics can be sorted in order from large to small, and the target recommendation topic for display can be determined based on the sorting results.
  • the current display page is the last page of a chapter of a reading book, and the currently displayed target books only include reading books, you can select multiple target recommended topics, such as selecting two or three targets. Recommend topics to enrich the display content shown to users.
  • the target books currently displayed may include multiple first recommended books. In order to avoid the display information being too scattered, one may be determined for each first recommended book. Or two target recommended topics.
  • the target recommendation topic can be and recommended books for display.
  • recommended books include at least the stated target book.
  • the recommended books displayed may include the reading book as the target book.
  • the displayed recommended books may include at least one first recommended book as the target book.
  • the recommended books and target recommended topics can be displayed in a display manner that matches the preset display conditions.
  • the default display condition is that the current display page is the chapter end page of a reading book and the book recommendation page are respectively explained.
  • each target can be displayed in sequence on the last page of the chapter.
  • Recommend topics, and under each target recommended topic display recommended books that match the target recommended topic.
  • recommended books matching the target recommendation topic include reading books as target books. Reading books can be displayed directly on the reading page. Recommended books matching the target recommendation topic may also include other books discussed under the target recommendation topic, for example, they may be obtained from the target recommendation topic. Specifically, the second recommended book that matches the target recommended topic may be determined based on the recommended book information in each topic post under the target recommended topic.
  • topic posts under the target recommendation topic are created around the target recommendation topic, allowing different users to discuss and communicate about books. Therefore, in the topic post, for example, the book information that the user discusses and communicates under the target recommendation topic can be determined in the name of the topic post and the comment message, such as the title of the book, the relevant author and other information, so as to determine the relevant book as the third 2. Recommend books and display them under the target recommended topic.
  • a target recommendation topic that matches the target book includes topic 1.
  • the books available under the target recommendation topic include “Book B”, “Book C”, and “Book D”. Then "Book B”, “Book C””, and “Book D” are displayed as recommended books under the target recommendation topic.
  • all the books that can be obtained can be determined by the reading popularity as explained below, and a preset number of recommended books can be determined , for example, if it is determined that only four recommended books can be displayed under a target recommendation topic, then four books will be selected for display based on the reading popularity of each book. Or, in another possible situation, if there are fewer books that can be obtained, for example, only three or four books can be obtained, then all the obtained books will be displayed as recommended books.
  • the display order of each recommended book can be determined based on the corresponding reading popularity of each recommended book under the target recommended topic. Under the target recommended topic , displaying the recommended books in sequence according to the determined display order.
  • the reading popularity corresponding to the recommended book can, for example, indicate the number of times the recommended book has been read in the recent period, or the number of people who read the recommended book. Using the reading popularity, you can filter the multiple books obtained, or sort the recommended books that have been determined, and the recommended books with higher reading popularity will be displayed first under the target recommendation topic.
  • FIG. 4 is a schematic diagram of displaying recommended books and target recommended topics on the last page of a chapter of a reading book provided by an embodiment of the present disclosure.
  • two target recommended topics corresponding to the target book are displayed, including Topic 1 and Topic 2, through the introductory word "This book has been recommended by the following topics".
  • Topic 1 and Topic 2 Through each target recommendation topic, multiple recommended books with a certain sorting method are also included, specifically based on book covers and book titles.
  • the display method is shown.
  • the topic post corresponding to the target recommended topic can be jumped and displayed.
  • the reading page displaying the recommended book can also be jumped, and the reading service of the recommended book can be provided to the user.
  • each recommendation can be displayed in sequence on the book recommendation page Books, and each target recommended topic that the recommended books match.
  • the recommended books matching the target recommendation topic include the target book, that is, the first recommended book including the above description. Since the recommended books are displayed on the book recommendation page, they can be displayed through the title, author, cover and other introductory information of the recommended books. When there are many recommended books, the recommended books can be arranged and displayed on the book recommendation page. For example, the recommended books include "Book a”, “Book b" and "Book c".
  • the display order of each recommended book can be determined based on the book consumption characteristics corresponding to each recommended book; the book consumption characteristics include the number of readers and the reading time; On the book recommendation page, the recommended books are displayed based on the determined display order of each of the recommended books.
  • the corresponding book consumption characteristics can be determined based on the number of readers of the book and the reading time according to the preset scoring rules. For example, regarding the book consumption characteristics of the number of readers, it is determined that when the number of readers is 0-5, the corresponding score is 10 points, and when the number of readers is 6-10, the corresponding score is 20 points, etc. For the book consumption characteristics of reading time, it is determined that the reading time is 0-10 hours, corresponding to The score is 10 points, and the reading time is 10-20 hours, the corresponding score is 20 points, etc. In this way, the book consumption characteristics of recommended books can be quantitatively measured in the form of scores, and it is also easier to use the book consumption characteristics to determine the display order of each recommended book, such as determining the display order by arranging the scores from high to low.
  • the corresponding target recommendation topics can be displayed in association with each other. For example, for the recommended books determined in the above example, it can be determined that the target recommended topic corresponding to "book a" in the recommended book is topic 1, the target recommended topic corresponding to "book b" is topic 2, and the target recommended topic corresponding to "book a" The target recommended topic is Topic 3.
  • FIG. 5 is a schematic diagram of displaying recommended books and target recommended topics on a book recommendation page provided by an embodiment of the present disclosure.
  • the target recommendation topic corresponding to the recommended topic is displayed at the associated position of each recommended book.
  • each recommended book may have multiple target recommendation topics.
  • the target recommendation topics corresponding to "book b" include topic 2 and topic 4.
  • the reading page of the recommended book in response to the triggering operation on the book cover or title of the recommended book, the reading page of the recommended book can be jumped to display; in response to the triggering operation on the target recommended topic, the target can be displayed. Topic posts corresponding to recommended topics.
  • the name of the target recommended topic can also be updated and displayed.
  • the updated name of the target recommended topic can reflect the association between the target recommended topic and the recommended book, and can be used as a recommendation reason to attract users to trigger viewing. .
  • the current displayed page is the last page of a chapter of a reading book.
  • the target recommendation topic is specifically determined through classification information when obtaining the target recommendation topic
  • the content of the target recommendation topic under the classification information is associated with the first recommended book.
  • the original name of the target recommendation topic can be displayed.
  • the name determined by the user when creating the target recommendation topic, and the original name of the target recommendation topic may not be good. It reflects the correlation with the first recommended book displayed, and it does not reflect the reason for displaying the target recommended topic. Therefore, it cannot effectively recommend by displaying the name of the target recommended topic. effect.
  • the recommendation reasons related to the target recommended topic may also be generated based on the topic attribute information related to the target recommended topic or the matching first recommended books.
  • the generated recommendation reasons can be used to replace the name of the target recommendation topic and be displayed, or the determined recommendation reasons can be displayed in association with the original name of the target recommendation topic to play a role in the target recommendation.
  • the recommendation function of recommended topics is also be generated based on the topic attribute information related to the target recommended topic or the matching first recommended books.
  • the topic attribute information corresponding to the target recommended topic may be obtained; based on the topic attribute information corresponding to the target recommended topic and/or each third topic matching the target recommended topic A recommended book, generating a recommendation reason for the target recommendation topic; wherein the recommendation reason is used to establish an association between the target recommendation topic and the recommended book; based on the target text corresponding to the recommendation reason for the target recommendation topic, Replace the original text of the target recommended topic; based on the target text, display the updated recommendation reasons for the target recommended topic.
  • the topic attribute information includes at least one of the following: the statistical number of each topic post under the target recommended topic, the topic title corresponding to each topic post, and the comment information corresponding to each topic post.
  • the original text of the corresponding target recommendation topic is, for example, "Recommend good novels", which cannot effectively recommend the user to view the target recommendation topic in order to obtain Information related to the number one recommended book.
  • the topic title corresponding to the topic post with a higher proportion under the target recommendation topic has the recommendation
  • the topic title involves the title, author name, protagonist name, etc. of the recommended book, and accordingly the recommendation reason for the target recommended topic can be determined to be "hotly discussed in the topic.”
  • FIG. 6 is another schematic diagram for displaying recommended books and target recommended topics on a book recommendation page according to an embodiment of the present disclosure.
  • the target recommendation topics of books a and book b are displayed with updated target text.
  • the target text displayed in the form of recommendation reasons is also displayed. To distinguish it from other target recommended topics displayed with the target text as the display content, it is marked with "*".
  • topic posts under the target recommended topic can be displayed in response to a triggering operation on the target recommended topic.
  • the target recommended topic can be downloaded from the target recommended topic. In each topic post, determine the target topic related to the recommended book posts, and display target topic posts related to recommended books.
  • the topic post directory corresponding to the target topic posts may be displayed.
  • multiple target topic posts can be displayed in an orderly manner in the form of a topic post directory.
  • the target topic post in response to a second trigger operation on any target topic post in the topic post directory, the target topic post can be displayed, and the user can view comments in the target topic post or discuss and communicate with other users, and obtain New books of interest.
  • the target topic post can be directly displayed.
  • FIG. 7 is a schematic diagram of displaying a target topic post provided by an embodiment of the present disclosure.
  • FIG. 7 shows a schematic diagram of a topic list displayed when multiple target topics are determined.
  • a topic post directory composed of multiple target topic posts under the target recommended topic "Topic 1" is shown.
  • the number of users and comments currently participating in the target topic post can also be displayed for user reference.
  • Figure 7 shows the target topic post displayed by the second triggering operation on any target topic post in (a) in Figure 7, or when the target topic post only includes one, the target topic is directly displayed. Sample image of the post.
  • the introduction of the target topic post, the user information corresponding to the users who have participated in the topic discussion (such as user avatar, user name, user identity, etc.), and the discussion content sent and displayed by the user can be displayed.
  • the discussion content may also specifically include reading links, covers and other information related to the book. The specific information may be determined according to the actual situation.
  • Figure 7 only provides an implementable example and is not limiting.
  • the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process.
  • the specific execution order of each step should be based on its function and possible The internal logic is determined.
  • the embodiments of the present disclosure also provide a topic recommendation device corresponding to the topic recommendation method. Since the principle of solving the problem of the device in the embodiment of the present disclosure is similar to the above-mentioned topic recommendation method in the embodiment of the present disclosure, the implementation of the device Please refer to the implementation of the method, and the repeated parts will not be repeated.
  • the device includes: a determination module 81, an acquisition module 82, and a display module 83; wherein,
  • Determination module 81 configured to determine the target book to be displayed under the preset display conditions in response to satisfying the preset display conditions
  • Obtaining module 82 is used to obtain target recommended topics matching the target book
  • the display module 83 is configured to display recommended books and the target recommended topics in a display manner that matches the preset display conditions; the recommended books at least include the target books.
  • the preset display conditions include at least one of the following: the current display page is the last page of a chapter of a reading book, and the current display page is a book recommendation page; the determination module 81 responds when the preset conditions are met. Assuming display conditions, when determining the target book to be displayed under the preset display conditions, it is used to: respond that the current display page is the last page of a chapter of a reading book, and use the reading book as the target book; or, respond to the current display page
  • the display page is a book recommendation page, obtain at least one first recommended book, and use the at least one first recommended book as the target book.
  • the recommended books when the currently displayed page is the last page of a chapter of a reading book, the recommended books also include a second recommended book; the topic recommendation device further includes a processing module 84 for: based on The recommended book information in each topic post under the target recommended topic determines the second recommended book that matches the target recommended topic.
  • the acquisition module 82 acquires the book matching the target book.
  • it is used to: determine candidate recommended topics whose matching degree with the target book is greater than a set threshold; based on the number of converted readers corresponding to each candidate recommended topic, select each candidate recommended topic Sort, and determine the target recommended topic from the candidate recommended topics based on the sorting results; the number of converted readers refers to the number of new users who read the books included in the candidate recommended topics after reading the candidate recommended topics. .
  • the acquisition module 82 determines the matching degree between the target book and any topic according to the following steps: for any topic, the first classification information based on the topic, and the target The second classification information of the book determines the matching degree between the topic and the target book.
  • the first classification information and the second classification information respectively have multiple classification levels; for any topic, the acquisition module 82 selects the first classification information based on the topic, and the The second classification information of the target book, when determining the matching degree between the topic and the target book, is used to: for any classification level, the first classification level information under the classification level based on the first classification information, and the second The second classification level information of the classification information under the classification level determines the level matching degree between the topic and the target book under the classification level; based on the level matching degree determined respectively under multiple classification levels, determines the topic Match to the target book.
  • the display module 83 when displaying the recommended books and the target recommended topic in a display manner that matches the preset display conditions, is configured to: in the preset display The conditions include: when the current display page is the last page of a chapter of a reading book, each target recommended topic is displayed in sequence on the last page of the chapter, and under each target recommended topic, each recommended book matching the target recommended topic is displayed; Alternatively, when the preset display conditions include: the current display page is a book recommendation page, each recommended book and each target recommendation topic matching the recommended book are displayed in sequence on the book recommendation page.
  • the display module 83 when displaying each recommended book matching the target recommendation topic, is configured to: based on the target recommendation topic as described below The corresponding reading popularity of each recommended book determines the display order of each recommended book. Under the target recommendation topic, the recommended books are displayed in sequence according to the determined display order.
  • the display module 83 displays each recommended book in sequence on the book recommendation page, and is configured to: based on the book consumption corresponding to each of the recommended books.
  • the display module 83 when displaying the target recommended topic, is configured to: obtain topic attribute information corresponding to the target recommended topic; based on the topic attribute information corresponding to the target recommended topic and /or each first recommended book that matches the target recommended topic generates a recommendation reason for the target recommended topic; wherein the recommendation reason is used to establish an association between the target recommended topic and the first recommended book; Based on the target text corresponding to the recommendation reason of the target recommended topic, replace the original text of the target recommended topic; based on the target text, display the updated target recommended topic.
  • the display module 83 is further configured to: in response to the first triggering operation on the target recommended topic, from the target recommended topic Among the following topic posts, determine the target topic post related to the recommended book; in response to the target topic post including multiple, display the topic post directory corresponding to the target topic post, and in response to the topic post directory A second trigger operation of any target topic post, display the target topic post, or, in response to the target topic post including one, display the target topic post.
  • An embodiment of the present disclosure also provides a computer device. As shown in Figure 9, which is a schematic structural diagram of the computer device provided by an embodiment of the present disclosure, it includes:
  • processor 10 and memory 20; the memory 20 stores machine-readable instructions executable by the processor 10, and the processor 10 is used to execute the machine-readable instructions stored in the memory 20, and the machine-readable instructions are used by the processor 10 When executing, processor 10 performs the following steps:
  • the target books In response to meeting the preset display conditions, determine the target books to be displayed under the preset display conditions; obtain the target recommended topics matching the target books; display the recommended books according to the display method matching the preset display conditions and the target recommended topic; the recommended books at least include the target book.
  • the above-mentioned memory 20 includes a memory 210 and an external memory 220; the memory 210 here is also called internal memory, and is used to temporarily store the operation data in the processor 10, as well as the data exchanged with external memory 220 such as a hard disk.
  • the processor 10 communicates with the external memory 220 through the memory 210.
  • the external memory 220 performs data exchange.
  • Embodiments of the present disclosure also provide a computer-readable storage medium.
  • a computer program is stored on the computer-readable storage medium.
  • the storage medium may be a volatile or non-volatile computer-readable storage medium.
  • Embodiments of the present disclosure also provide a computer program product.
  • the computer program product carries program code.
  • the instructions included in the program code can be used to execute the steps described in the above method embodiments.
  • the above-mentioned computer program product can be specifically implemented by hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium.
  • the computer program product is embodied as a software product, such as a Software Development Kit (SDK), etc. wait.
  • SDK Software Development Kit
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions described are implemented in the form of software functional units and sold or used as independent products, When used, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor.
  • the technical solution of the present disclosure essentially or part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium and includes a number of instructions to cause a computer device (to be a personal computer, server, or network device, etc.) that executes all or part of the steps of the methods described in various embodiments of the present disclosure.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program code. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开提供了一种话题推荐方法、装置、计算机设备及存储介质，其中，该方法包括：响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；获取与所述目标书籍匹配的目标推荐话题；按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。

Description

一种话题推荐方法、装置、计算机设备及存储介质
本申请要求于2022年5月26日递交的中国专利申请第202210582953.8号的优先权，在此全文引用上述中国专利申请公开的内容以作为本申请的一部分。
技术领域
本公开的实施例涉及一种话题推荐方法、装置、计算机设备及存储介质。
背景技术
在电子阅读平台中，用户可以挑选感兴趣的书籍进行阅读。在用户挑选书籍后，若希望找到其他感兴趣的书籍，则只能通过预览更多书籍的介绍或者预览内容找到新的感兴趣书籍，从而导致查找感兴趣书籍的效率较低。
发明内容
本公开实施例至少提供一种话题推荐方法、装置、计算机设备及存储介质。
第一方面，本公开实施例提供了一种话题推荐方法，包括：响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；获取与所述目标书籍匹配的目标推荐话题；按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。
一种可选的实施方式中，所述预设展示条件包括下述至少一种：当前展示页面为阅读书籍的章节末页，当前展示页面为书籍推荐页面；所述响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍，包括：响应当前展示页面为阅读书籍的章节末页，将所述阅读书籍作为所述目标书籍；或者，响应当前展示页面为书籍推荐页面，获取至少一个第一推荐书籍，将所述至少一个第一推荐书籍作为所述目标书籍。
一种可选的实施方式中，在当前展示页面为阅读书籍的章节末页的情况下，所述推荐书籍还包括第二推荐书籍；所述方法还包括：基于所述目标推荐话题下各话题帖中的各推荐书籍信息，确定与所述目标推荐话题匹配的所述第二推荐书籍。
一种可选的实施方式中，所述获取与所述目标书籍匹配的目标推荐话题，包括：确定与所述目标书籍之间的匹配度大于设定阈值的候选推荐话题；基于各所述候选推荐话题分别对应的转化阅读人数，对所述各候选推荐话题排序，并基于排序结果从所述候选推荐话题中确定所述目标推荐话题；所述转化阅读人数是指在阅读所述候选推荐话题后，阅读所述候选推荐话题包括的书籍的新增用户数。
一种可选的实施方式中，根据以下步骤确定所述目标书籍与任一话题之间的匹配度：针对任一话题，基于该话题的第一分类信息、以及所述目标书籍的第二分类信息，确定该话题与所述目标书籍的匹配度。
一种可选的实施方式中，所述第一分类信息和第二分类信息分别具有多个分类层级；针对任一话题，基于该话题的第一分类信息、以及所述目标书籍的第二分类信息，确定该话题与所述目标书籍的匹配度，包括：针对任一分类层级，基于第一分类信息在该分类层级下的第一分类层级信息、 以及第二分类信息在该分类层级下的第二分类层级信息，确定该话题与所述目标书籍在该分类层级下的层级匹配度；基于在多分类层级下分别确定的所述层级匹配度，确定该话题与所述目标书籍的匹配度。
一种可选的实施方式中，所述按照与所述预设展示条件匹配的展示方式，展示所述推荐书籍以及所述目标推荐话题，包括：在所述预设展示条件包括：当前展示页面为阅读书籍的章节末页的情况下，在所述章节末页依次展示各目标推荐话题，并在每个目标推荐话题下，展示该目标推荐话题匹配的各推荐书籍；或者，在所述预设展示条件包括：当前展示页面为书籍推荐页面的情况下，在所述书籍推荐页面依次展示各推荐书籍，以及该推荐书籍匹配的各目标推荐话题。
一种可选的实施方式中，若当前展示页面为阅读书籍的章节末页，所述展示该目标推荐话题匹配的各推荐书籍，包括：基于该目标推荐话题下所述各个推荐书籍分别对应的阅读热度，确定所述各推荐书籍的展示顺序，在该目标推荐话题下，按照确定的展示顺序依次展示所述各推荐书籍。
一种可选的实施方式中，若当前展示页面为书籍推荐页面，所述在所述书籍推荐页面依次展示各推荐书籍，包括：基于各所述推荐书籍分别对应的书籍消费特征，确定各个所述推荐书籍的展示顺序；所述书籍消费特征包括阅读人数以及阅读时长；在所述书籍推荐页面，基于确定的各个所述推荐书籍的展示顺序展示所述推荐书籍。
一种可选的实施方式中，展示所述目标推荐话题，包括：获取所述目标推荐话题对应的话题属性信息；基于所述目标推荐话题对应的话题属性信息和/或与所述目标推荐话题匹配的各第一推荐书籍，生成所述目标推荐话题的推荐理由；其中，所述推荐理由用于建立所述目标推荐话题与所述 第一推荐书籍的关联；基于所述目标推荐话题的推荐理由对应的目标文本，替换所述目标推荐话题的原始文本；基于所述目标文本，展示更新后所述目标推荐话题。
一种可选的实施方式中，在展示推荐书籍以及所述目标推荐话题后，所述方法还包括：响应于对所述目标推荐话题的第一触发操作，从所述目标推荐话题下各话题帖中，确定与所述推荐书籍相关的目标话题帖；响应于所述目标话题帖包括多个，展示所述目标话题帖对应的话题帖目录，并响应于对所述话题帖目录中任一目标话题帖的第二触发操作，展示该目标话题帖，或者，响应于所述目标话题帖包括一个，展示所述目标话题帖。
第二方面，本公开实施例还提供一种话题推荐装置，包括：确定模块，用于响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；获取模块，用于获取与所述目标书籍匹配的目标推荐话题；展示模块，用于按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。
一种可选的实施方式中，所述预设展示条件包括下述至少一种：当前展示页面为阅读书籍的章节末页，当前展示页面为书籍推荐页面；所述确定模块在响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍时，用于：响应当前展示页面为阅读书籍的章节末页，将所述阅读书籍作为所述目标书籍；或者，响应当前展示页面为书籍推荐页面，获取至少一个第一推荐书籍，将所述至少一个第一推荐书籍作为所述目标书籍。
一种可选的实施方式中，在当前展示页面为阅读书籍的章节末页的情况下，所述推荐书籍还包括第二推荐书籍；所述话题推荐装置还包括处理模块，用于：基于所述目标推荐话题下各话题帖中的各推荐书籍信息，确 定与所述目标推荐话题匹配的所述第二推荐书籍。
一种可选的实施方式中，所述获取模块在获取与所述目标书籍匹配的目标推荐话题时，用于：确定与所述目标书籍之间的匹配度大于设定阈值的候选推荐话题；基于各所述候选推荐话题分别对应的转化阅读人数，对所述各候选推荐话题排序，并基于排序结果从所述候选推荐话题中确定所述目标推荐话题；所述转化阅读人数是指在阅读所述候选推荐话题后，阅读所述候选推荐话题包括的书籍的新增用户数。
一种可选的实施方式中，所述获取模块根据以下步骤确定所述目标书籍与任一话题之间的匹配度：针对任一话题，基于该话题的第一分类信息、以及所述目标书籍的第二分类信息，确定该话题与所述目标书籍的匹配度。
一种可选的实施方式中，所述第一分类信息和第二分类信息分别具有多个分类层级；针对任一话题，所述获取模块在基于该话题的第一分类信息、以及所述目标书籍的第二分类信息，确定该话题与所述目标书籍的匹配度时，用于：针对任一分类层级，基于第一分类信息在该分类层级下的第一分类层级信息、以及第二分类信息在该分类层级下的第二分类层级信息，确定该话题与所述目标书籍在该分类层级下的层级匹配度；基于在多分类层级下分别确定的所述层级匹配度，确定该话题与所述目标书籍的匹配度。
一种可选的实施方式中，所述展示模块在按照与所述预设展示条件匹配的展示方式，展示所述推荐书籍以及所述目标推荐话题时，用于：在所述预设展示条件包括：当前展示页面为阅读书籍的章节末页的情况下，在所述章节末页依次展示各目标推荐话题，并在每个目标推荐话题下，展示该目标推荐话题匹配的各推荐书籍；或者，在所述预设展示条件包括：当 前展示页面为书籍推荐页面的情况下，在所述书籍推荐页面依次展示各推荐书籍，以及该推荐书籍匹配的各目标推荐话题。
一种可选的实施方式中，若当前展示页面为阅读书籍的章节末页，所述展示模块在展示该目标推荐话题匹配的各推荐书籍时，用于：基于该目标推荐话题下所述各个推荐书籍分别对应的阅读热度，确定所述各推荐书籍的展示顺序，在该目标推荐话题下，按照确定的展示顺序依次展示所述各推荐书籍。
一种可选的实施方式中，若当前展示页面为书籍推荐页面，所述展示模块在所述书籍推荐页面依次展示各推荐书籍时，用于：基于各所述推荐书籍分别对应的书籍消费特征，确定各个所述推荐书籍的展示顺序；所述书籍消费特征包括阅读人数以及阅读时长；在所述书籍推荐页面，基于确定的各个所述推荐书籍的展示顺序展示所述推荐书籍。
一种可选的实施方式中，所述展示模块在展示所述目标推荐话题时，用于：获取所述目标推荐话题对应的话题属性信息；基于所述目标推荐话题对应的话题属性信息和/或与所述目标推荐话题匹配的各第一推荐书籍，生成所述目标推荐话题的推荐理由；其中，所述推荐理由用于建立所述目标推荐话题与所述第一推荐书籍的关联；基于所述目标推荐话题的推荐理由对应的目标文本，替换所述目标推荐话题的原始文本；基于所述目标文本，展示更新后所述目标推荐话题。
一种可选的实施方式中，在展示推荐书籍以及所述目标推荐话题后，所述展示模块还用于：响应于对所述目标推荐话题的第一触发操作，从所述目标推荐话题下各话题帖中，确定与所述推荐书籍相关的目标话题帖；响应于所述目标话题帖包括多个，展示所述目标话题帖对应的话题帖目录， 并响应于对所述话题帖目录中任一目标话题帖的第二触发操作，展示该目标话题帖，或者，响应于所述目标话题帖包括一个，展示所述目标话题帖。
第三方面，本公开可选实现方式还提供一种计算机设备，处理器、存储器，所述存储器存储有所述处理器可执行的机器可读指令，所述处理器用于执行所述存储器中存储的机器可读指令，所述机器可读指令被所述处理器执行时，所述机器可读指令被所述处理器执行时执行上述第一方面，或第一方面中任一种可能的实施方式中的步骤。
第四方面，本公开可选实现方式还提供一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被运行时执行上述第一方面，或第一方面中任一种可能的实施方式中的步骤。
本公开实施例提供的话题推荐方法、装置、计算机设备及存储介质，为了满足在不同阅读场景下的推荐需求，可以先确定用户感兴趣的书籍，也就是在不同的展示条件下对应的待展示的目标书籍。利用目标书籍，可以获取与目标书籍匹配的目标推荐话题，以在不同的展示条件下对目标推荐话题以及包含目标书籍的推荐书籍进行展示。这样，用户可以在确定的感兴趣的书籍之外，从展示出的推荐书籍和目标推荐话题中直接获取感兴趣的其他书籍，从而提高查找感兴趣书籍的效率。
为使本公开的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，此处的附图被并入说明书中并构成本说明书 中的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。应当理解，以下附图仅示出了本公开的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1示出了本公开实施例所提供的一种话题推荐方法的流程图；
图2示出了本公开实施例所提供的一种书籍的章节末页的示意图；
图3示出了本公开实施例所提供的一种书籍推荐页面的示意图；
图4示出了本公开实施例所提供的一种在阅读书籍的章节末页展示推荐书籍以及目标推荐话题的示意图；
图5示出了本公开实施例所提供的一种在书籍推荐页面展示推荐书籍以及目标推荐话题的示意图；
图6示出了本公开实施例所提供的另一种在书籍推荐页面展示推荐书籍以及目标推荐话题的示意图；
图7示出了本公开实施例所提供的一种展示目标话题帖时的示意图；
图8示出了本公开实施例所提供的一种话题推荐装置的示意图；以及
图9示出了本公开实施例所提供的一种计算机设备的示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。 通常在此处描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此，以下对本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围，而是仅仅表示本公开的选定实施例。基于本公开的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
经研究发现，用户在挑选感兴趣的书籍进行阅读时，还具有找到其他感兴趣的书籍的阅读需求。由于在各种不同的阅读场景下，仅会有针对性的展示出用户感兴趣的书籍，而不会展示出其他书籍或者相关内容，因此用户为了找到其他感兴趣的书籍，只能预览更多书籍的介绍或者预览内容，以查找到感兴趣的其他书籍，从而导致查找感兴趣书籍的效率较低。
基于上述研究，本公开提供了一种话题推荐方法，为了满足在不同阅读场景下的推荐需求，可以先确定用户感兴趣的书籍，也就是在不同的展示条件下对应的待展示的目标书籍。利用目标书籍，可以获取与目标书籍匹配的目标推荐话题，以在不同的展示条件下对目标推荐话题以及包含目标书籍的推荐书籍进行展示。这样，用户可以在确定的感兴趣的书籍之外，从展示出的推荐书籍和目标推荐话题中直接获取感兴趣的其他书籍，从而提高查找感兴趣书籍的效率。
针对以上方案所存在的缺陷，均是发明人在经过实践并仔细研究后得出的结果，因此，上述问题的发现过程以及下文中本公开针对上述问题所提出的解决方案，都应该是发明人在本公开过程中对本公开做出的贡献。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。
为便于对本实施例进行理解，首先对本公开实施例所公开的一种话题推荐方法进行详细介绍，本公开实施例所提供的话题推荐方法的执行主体一般为具有一定计算能力的计算机设备，该计算机设备例如包括：终端设备或服务器或其它处理设备，终端设备可以为用户设备(User Equipment，UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字助理(Personal Digital Assistant，PDA)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该话题推荐方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
下面对本公开实施例提供的话题推荐方法加以说明。
参见图1所示，为本公开实施例提供的话题推荐方法的流程图，所述方法包括步骤S101～S103，其中：
S101：响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；
S102：获取与所述目标书籍匹配的目标推荐话题；
S103：按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。
下面对上述S101～S103加以详细说明。
针对上述S101，在具体实施中，预设展示条件包括下述至少一种：当前展示页面为阅读书籍的章节末页，当前展示页面为书籍推荐页面。
首先，对当前展示页面为阅读书籍的章节末页的情况进行说明。示例性的，参见图2所示，为本公开实施例提供的一种书籍的章节末页的示意图。具体地，在用户对书籍进行阅读时，响应于对显示出的阅读页面的翻 页操作，可以对书籍的章节进行阅读。在确定显示到任一章节对应的最后一个阅读页面时，确定满足预设展示条件，也即当前展示界面为书籍的章节末页。其中，由于书籍的章节末页可能包括书籍中除最后一个章节外其他章节末页，也可能包括书籍中最后一个章节的章节末页，也即该书籍的更新末级页面，因此在图2中以(a)、(b)两张示意图示出了两种不同的情况。
在该种预设展示条件下，在确定与预设展示条件下待展示的目标书籍时，可以将正在阅读的阅读书籍确定为目标书籍。由于目标书籍为用户在读、或者已读完的书籍，可以认为用户对该书籍相关的内容更感兴趣。因此在后续步骤中获取到的与目标书籍匹配的目标推荐话题，会更贴近于用户感兴趣的话题，进而提高利用展示出的话题查找其他书籍的效率。
其次，对当前展示页面为书籍推荐页面的情况进行说明。示例性的，参见图3所示，为本公开实施例提供的一种书籍推荐页面的示意图。在示意图中示出了部分推荐书籍，并具体展示出了书籍的封面、书名、作者等信息。另外，书籍推荐页面上还包括有查看完整榜单的触发按钮，响应于对该触发按钮的触发操作，可以展示出所有推荐书籍的榜单形式的列表。
在书籍推荐页面中，包括展示出的多本推荐书籍，在本公开实施例中将展示出的推荐书籍称为第一推荐书籍。其中，第一推荐书籍具体可以是利用用户授权得到的历史阅读数据确定的贴近用户阅读喜好的书籍，或者也可以是预先确定的推荐书籍，比如当前其他用户热推的书籍，或者平台中热推的书籍。具体地，响应于对推荐页面的触发操作，可以展示出的书籍推荐页面，确定满足预设展示条件。
在该种情况下，在确定在预设展示条件下待展示的目标书籍时，可以 获取书籍推荐页面中的至少一个第一推荐书籍，并将至少一个第一推荐书籍作为目标书籍。在该种情况下，由于目标书籍贴近用户阅读喜好，或者为平台中热推的书籍，因此在后续步骤中获取到的与目标书籍匹配的目标推荐话题也可以贴近于用户感兴趣的话题，或者包括平台希望推荐给用户进行展示的话题。
针对上述S102，在确定各预设条件下待展示的目标书籍的情况下，还可以获取与目标书籍匹配的目标推荐话题，以在展示目标书籍的基础上以话题的形式对目标书籍进行扩展展示。
在具体实施中，在获取与目标书籍匹配的目标推荐话题时，可以采用下述方式：确定与所述目标书籍之间的匹配度大于设定阈值的候选推荐话题；基于各所述候选推荐话题分别对应的转化阅读人数，对所述各候选推荐话题排序，并基于排序结果从所述候选推荐话题中确定所述目标推荐话题；所述转化阅读人数是指在阅读所述候选推荐话题后，阅读所述候选推荐话题包括的书籍的新增用户数。
具体地，在确定目标书籍的情况下，可以在电子阅读平台中确定多个话题，并从中确定与目标书籍匹配的目标推荐话题进行展示。由于电子阅读平台中与目标书籍匹配的话题的数量可能较多，因此可以先确定目标书籍与各话题之前的匹配度，再根据设定阈值从各话题中筛选出部分推荐话题，作为候选推荐话题。
其中，在确定目标书籍和任一话题之间的匹配度时，具体可以采用下述方式：针对任一话题，基于该话题的第一分类信息、以及所述目标书籍的第二分类信息，确定该推荐话题与所述目标书籍的匹配度。
示例性的，话题和目标书籍的分类方式可以相同或相似，因此话题和 目标书籍具体可以有相同或相似的分类信息。例如，将话题下讨论的书籍对应的书籍类型，作为话题的第一分类信息，将目标书籍对应的书籍类型作为第二分类信息，其中书籍类型例如为小说、诗歌、自传、散文。若目标书籍的书籍类型为小说，而具有某一话题，在该话题下讨论的书籍对应的书籍类型为小说，则可以认为该话题与目标书籍的匹配度较高。
在一种可能的情况下，若仅使用一个维度下分类方式对话题和目标书籍进行分类，由于分类基准比较宽泛，因此可能会有较多话题可以与目标书籍进行匹配，不能起到较好的筛选作用，筛选出的话题在分类下的内容中也并不一定能与目标书籍具有较好地关联。因此，在确定分类信息时，还可以确定多个分类层级，比如将小说、诗歌作为第一层分类层级，对于第一层分类层级中的小说，确定将科幻小说、言情小说、玄幻小说作为对应的第二层分类层级，对于第一层分类层级中的诗歌，确定将现代诗歌、近代诗歌作为对应的第二层分类层级等等。每一分类层级中划分出的类型数量越多，对目标书籍和话题的分类也会更细致。这样，相较于上述示例中仅利用小说、诗歌等书籍类型确定分类信息的方式，采用多个分类层级确定分类信息的方式更加细化，确定的匹配度也更能反应话题涉及的内容是否可以与目标书籍的内容在多种不同的分类层级上更匹配。
在具体实施中，可以针对任一分类层级，基于第一分类信息在该分类层级下的第一分类层级信息、以及第二分类层级下的第二分类层级信息，确定该话题与目标书籍在该分类层级下的层级匹配度；基于在多分类层级下分别确定的所述层级匹配度，确定该话题与所述目标书籍的匹配度。
在一种可能的情况下，若多个分类层级之间具有包含关系，并且在每个分类层级中还分别具有互斥的类型，则可以逐个在分类层级上确定话题与目标书籍在分类层级上分别对应的第一分类层级信息、以及第二分类层 级信息是否一致，以确定话题和目标书籍在每层分类层级下的层级匹配度。
示例性的，若具有两个分类层级，包括第一分类层级和第二分类层级，第一分类层级中具有两个互斥的类型，包括小说和诗歌；在第一分类层级诗歌下的第二分类层级也具有两个互斥的类型，包括近代诗歌和现代诗歌。
下面分别列举几种可能的示例场景进行说明。
示例场景1：在第一分类层级中，若话题的第一分类信息在该分类层级下的第一分类层级信息为小说，目标书籍的第二分类信息在该分类层级下的第二分类层级信息为诗歌，由于二者分类为两个互斥的类型，因此可以确定该话题与目标书籍在该分类层级下的层级匹配度较低。在该种情况下，由于下一分类层级基于该分类层级确定，是进一步的细分分类，因此若在该分类层级中确定层级匹配度较低，则无需再确定下一分类层级的层级匹配度。并确定该话题与目标书籍的匹配度较低。若采用数值表示该话题与目标书籍的匹配度时，例如可以设置数值为0。
示例场景2：在第一分类层级中，若话题的第一分类信息在该分类层级下的第一分类信息，与目标书籍的第二分类信息在该分类层级下的第二分类层级信息均为诗歌，则可以确定话题与目标书籍在该分类层级下的层级匹配度较高。但由于在较高分类层级下的分类方式比较宽泛，因此若采用数值表示该分类层级的层级匹配度时，例如可以设置数值为1，表示该话题与目标书籍之间至少在该分类层级下是匹配的。
而对于第二分类层级，若在第二分类层级中，话题的第一分类信息在该第二分类层级下的第一分类层级信息为近代诗歌，而目标书籍的第二分类信息在该第二分类层级下的第二分类层级信息为现代诗歌，则在第二分类层级中二者分别属于互斥的两种类型。在该种情况下，可以保留在第一 分类层级中确定的层级匹配度1，而由于第一分类层级的分类方式比较宽泛，因此可以通过加权的方式确定话题与目标书籍的匹配度，比如设置在第一分类层级对应的层级匹配度的权重值为0.5，则将对第一分类的层级匹配度1通过权重值0.5计算，得到话题与目标书籍的匹配度为0.5,。
示例场景3：延续上述示例场景2中在第一分类层级上对话题和目标书籍在分类层级下的层级匹配度。并且，在第二分类层级中，话题的第一分类信息在该第二分类层级下的第一分类层级信息，与目标书籍的第二分类信息在该第二分类层级下的第二分类层级信息均为现代诗歌。则在该种情况下，确定话题与目标书籍在第二分类层级的细分分类下也相同，因此可以确定该话题与目标书籍在第二分类层级下的层级匹配度也较高，例如确定第二分类层级下话题与目标书籍的层级匹配度为1。
与上述示例场景2相似的，可以为第二分类层级设置层级匹配度的权重值，比如为0.2。因此，利用第一分类层级设置的权重值0.5、第二分类层级设置的权重值0.2，可以计算得到话题与目标书籍的匹配度为0.7。
在另一种可能的情况下，在分类层级中还可能包括可以多选的类型。比如在第一分类层级中包括类型小说，在小说的类型下第二分类层级中的类型可以包括言情、穿越、古风、斗争等。示例性的，若话题的第一分类信息在第二分类层级下的第一分类层级信息包括言情、穿越和古风，并且目标书籍的第二分类信息在第二分类层级下的第二分类层级信息包括言情、古风和斗争，则至少在言情和古风两个类型下是匹配的，认为该话题与目标书籍在第二分类层级下的层级匹配度较高。而若话题的第一分类信息在第二分类层级下的第一分类层级信息仅包括穿越，则不并能与第二分类层级信息中的任一类型相匹配，则认为该话题与目标书籍在第二分类层级下的层级匹配度较低。
这样，通过多个分类层级下话题与目标书籍的层级匹配度，可以使得到的话题与目标书籍之间的匹配度更准确。
延续上述获取与目标书籍匹配的目标推荐话题的过程，在确定各话题与目标书籍之间的匹配度后，可以通过设定阈值从各话题中确定候选推荐话题。此处，设定阈值可以人为规定，比如设置为0.75或者0.8，以获取足够数量的候选推荐话题。或者，也可以根据实际情况动态调整，比如当前可以确定的话题较多，并且在各话题中具有较大比例的话题与目标书籍之间的匹配度大于0.8，则可以动态调节将设定阈值提高，比如提高至0.85，以筛选出适当数量的候选推荐话题。
在确定候选推荐话题后，还可以基于各所述候选推荐话题分别对应的转化阅读人数，对所述各候选推荐话题排序，并基于排序结果从所述候选推荐话题中确定所述目标推荐话题。其中，所述转化阅读人数是指在阅读所述候选推荐话题后，阅读所述候选推荐话题包括的书籍的新增用户数。
具体地，通过各候选推荐话题分别对应的转化阅读人数的数量，可以利用数量由大到小的顺序，将多个候选推荐话题依次进行排序，并根据排序结果确定用于展示的目标推荐话题。在一种可能的情况下，若当前展示页面为阅读书籍的章节末页，当前展示出的目标书籍仅包括阅读书籍，则可以挑选出多个目标推荐话题，比如挑选出两个或三个目标推荐话题，以丰富向用户展示的展示内容。在另一种可能的情况下，若当前展示页面为书籍推荐页面，当前展示出的目标书籍可以包括多个第一推荐书籍，为避免展示信息过于分散，可以为每个第一推荐书籍确定一个或两个目标推荐话题。
针对上述S103，在确定目标推荐话题的情况下，可以对目标推荐话题 和推荐书籍进行展示。针对推荐书籍，至少包括所述目标书籍。示例性的，在当前展示页面为阅读书籍的章节末页时，展示出的推荐书籍可以包括作为目标书籍的阅读书籍。在当前展示页面为书籍推荐页面时，展示出的推荐书籍可以包括作为目标书籍的至少一个第一推荐书籍。
在不同的预设展示条件下，具体可以按照与预设展示条件匹配的展示方式，对推荐书籍以及目标推荐话题进行展示。下面，分别对预设展示条件为当前展示页面为阅读书籍的章节末页和书籍推荐页面两种不同情况分别进行说明。
首先，在预设展示条件包括当前展示页面为章节末页的情况下，按照与预设展示条件匹配的展示方式，展示推荐书籍以及目标推荐话题时，可以在所述章节末页依次展示各目标推荐话题，并在每个目标推荐话题下，展示该目标推荐话题匹配的各推荐书籍。
其中，目标推荐话题匹配的推荐书籍，包括作为目标书籍的阅读书籍。阅读书籍可以直接在阅读页面上进行展示。目标推荐话题匹配的推荐书籍，还可以包括在目标推荐话题下讨论的其他书籍，例如可以从目标推荐话题中获取。具体地，可以基于所述目标推荐话题下各话题帖中的各推荐书籍信息，确定与所述目标推荐话题匹配的所述第二推荐书籍。
此处，目标推荐话题下的话题帖围绕目标推荐话题创建，可以使不同用户在其中对书籍进行讨论沟通。因此，在话题帖中，例如可以在话题帖的名称、评论留言中确定用户在目标推荐话题下讨论沟通的书籍信息，比如指示书籍的书名、相关作者等信息，以确定相关的书籍作为第二推荐书籍，并在目标推荐话题下关联展示。
示例性的，在章节末页进行展示时，若目标书籍为《书籍A》，也即用 户当前正在阅读的书籍，则将《书籍A》继续在阅读页面上进行展示。与目标书籍匹配的一个目标推荐话题包括话题1，在目标推荐话题下可以获取到的书籍包括《书籍B》、《书籍C》、以及《书籍D》，则将《书籍B》、《书籍C》、以及《书籍D》作为目标推荐话题下的推荐书籍进行展示。
此处，由于目标推荐话题下可以获取到的书籍的数量不限，因此在一种可能的情况下，可以将所有可获取的书籍通过下述说明的阅读热度，从中确定预设数量的推荐书籍，比如确定在一个目标推荐话题下仅能对四本推荐书籍进行展示，则利用各书籍的阅读热度挑选四本进行展示。或者，在另一种可能的情况下，若可以获取到的书籍较少，比如仅能获取到三本或四本，则将获取到的书籍均作为推荐书籍进行展示。
具体地，在展示该目标推荐话题匹配的各推荐书籍时，可以基于该目标推荐话题下所述各个推荐书籍分别对应的阅读热度，确定所述各推荐书籍的展示顺序，在该目标推荐话题下，按照确定的展示顺序依次展示所述各推荐书籍。
此处，推荐书籍对应的阅读热度，例如可以指示在最近的一段时间内推荐书籍被阅读的次数，或者阅读该推荐书籍的人数。利用阅读热度，可以对获取到的多本书籍进行筛选，也可以对确定的推荐书籍进行排序，已将阅读热度较高的推荐书籍在目标推荐话题下靠前展示。
示例性的，参见图4所示，为本公开实施例提供的一种在阅读书籍的章节末页展示推荐书籍以及目标推荐话题的示意图。在图2中(a)示出的章节末页的基础上，通过“本书被以下话题推荐过”的引导词，展示出目标书籍对应的两个目标推荐话题，包括话题1和话题2。在每个目标推荐话题下，还包括具有确定排序方式的多本推荐书籍，具体以书籍封面和书名 的展示方式示出。此处，响应于对目标推荐话题的触发操作，可以跳转展示目标推荐话题对应的话题帖，具体可以参见下文中对应部分的说明，在此不再赘述。另外，响应于对推荐书籍的书籍封面或书名的触发操作，也可以跳转展示该推荐书籍的阅读页面，并向用户提供对该推荐书籍的阅读服务。
其次，在预设展示条件包括当前展示页面为书籍推荐页面的情况下，按照与预设展示条件匹配的展示方式，展示推荐书籍以及目标推荐话题时，可以在所述书籍推荐页面依次展示各推荐书籍，以及该推荐书籍匹配的各目标推荐话题。
其中，目标推荐话题匹配的推荐书籍包括目标书籍，也即包括上述说明的第一推荐书籍。由于是在书籍推荐页面上对推荐书籍进行展示的，因此可以通过推荐书籍的书名、作者、封面等介绍信息进行展示。在推荐书籍较多的情况下，可以在书籍推荐页面中对推荐书籍进行排列展示。示例性的，推荐书籍例如包括《书籍a》、《书籍b》以及《书籍c》。
此处，在书籍推荐页面依次展示各推荐书籍时，可以基于各所述推荐书籍分别对应的书籍消费特征，确定各个所述推荐书籍的展示顺序；所述书籍消费特征包括阅读人数以及阅读时长；在所述书籍推荐页面，基于确定的各个所述推荐书籍的展示顺序展示所述推荐书籍。
在一种可能的情况下，在确定任一推荐书籍的书籍消费特征时，例如可以根据预设的打分规则根据该书籍的阅读人数以及阅读时长确定对应的书籍消费特征。比如，对于阅读人数的书籍消费特征，确定在阅读人数为0-5人时，对应的分数为10分、在阅读人数为6-10人时，对应的分数为20分等。对于阅读时长的书籍消费特征，确定在阅读时长为0-10小时，对应 的分数为10分，在阅读时长为10-20小时，对应的分数为20分等。这样，可以定量的通过分数的形式衡量推荐书籍的书籍消费特征，也更便于利用书籍消费特征确定各个推荐书籍的展示顺序，比如按照分数从高到低排列的方式确定展示顺序。
此处，仅提供一种可能的为推荐书籍确定书籍消费特征的具体实施方式，若具有其他可选的方式，均在本公开实施例的保护范围之内，在此并不对确定书籍消费特征的方式做出限定。
对于推荐书籍，具有对应的目标推荐话题，在对推荐书籍进行展示时，可以将对应的目标推荐话题关联展示出。示例性的，对于上述示例中确定的推荐书籍，可以确定推荐书籍中《书籍a》对应的目标推荐话题为话题1、《书籍b》对应的目标推荐话题为话题2、《书籍a》对应的目标推荐话题为话题3。
示例性的，参见图5所示，为本公开实施例提供的一种在书籍推荐页面展示推荐书籍以及目标推荐话题的示意图。相较于图3示出的书籍推荐页面，在每个推荐书籍的关联位置处展示出了与该推荐话题对应的目标推荐话题。此处，每个推荐书籍可以具有多个目标推荐话题，例如在示意图中《书籍b》对应的目标推荐话题包括话题2和话题4。另外，与上述图4相似的，响应于对推荐书籍的书籍封面或者书名的触发操作，可以跳转展示该推荐书籍的阅读页面；响应于对目标推荐话题的触发操作，可以跳转展示目标推荐话题对应的话题帖。
在本公开另一实施例中，还可以对目标推荐话题的名称进行更新展示，更新后的目标推荐话题的名称能够体现出目标推荐话题与推荐书籍的关联，并可以作为推荐理由吸引用户触发查看。
示例性的，以当前展示页面为阅读书籍的章节末页为例进行说明。由于在获取目标推荐话题时，具体例如是通过分类信息确定的，因此目标推荐话题在分类信息下的内容是与第一推荐书籍是相关联的。但在对目标推荐话题进行展示时，具体可以对目标推荐话题原有的名称进行展示，比如用户在创建的该目标推荐话题时确定的名称，而目标推荐话题原有的名称可能并不能较好的反应出与展示出的第一推荐书籍之间的关联性，也并不能体现出将该目标推荐话题进行展示的理由，因此并不能通过展示出目标推荐话题的名称的方式起到有效地推荐作用。
因此，在展示目标推荐话题前，具体还可以根据目标推荐话题相关的话题属性信息、或者匹配的各第一推荐书籍，生成相关与目标推荐话题的推荐理由。此处，生成的推荐理由可以用于替换目标推荐话题的名称并进行展示，或者也可以在展示目标推荐话题原有名称的基础上，将确定的推荐理由一起关联展示出，以起到对目标推荐话题的推荐作用。
在具体实施中，在展示目标推荐话题时，具体可以获取所述目标推荐话题对应的话题属性信息；基于所述目标推荐话题对应的话题属性信息和/或与所述目标推荐话题匹配的各第一推荐书籍，生成所述目标推荐话题的推荐理由；其中，所述推荐理由用于建立所述目标推荐话题与所述推荐书籍的关联；基于所述目标推荐话题的推荐理由对应的目标文本，替换所述目标推荐话题的原始文本；基于所述目标文本，展示更新后所述目标推荐话题的推荐理由。
其中，话题属性信息包括下述至少一种：目标推荐话题下各话题帖的统计数量、各话题帖分别对应的话题标题、以及各话题帖分别对应的评论信息。利用目标推荐话题的话题属性和/或与目标推荐话题匹配的各第一推荐书籍，生成目标推荐话题的推荐理由时，例如可以从中确定与第一推荐 书籍关联的内容，然后再确定推荐理由。
示例性的，以第一推荐书籍为《书籍a》为例，对应的目标推荐话题的原始文本例如为“求推荐好看的小说”，这并不能有效地推荐用户查看该目标推荐话题，以获取与第一推荐书籍相关的信息。此处，例如可以根据确定的目标推荐话题下各话题帖和统计数量、以及各话题帖分别对应的话题标题，确定在目标推荐话题下具有较高比例的话题帖对应的话题标题中具有与推荐书籍关联的内容，比如在较多数量的话题帖中话题标题中涉及到推荐书籍的书名、作者名、主角名字等，则相应的可以确定目标推荐话题的推荐理由为“话题中正在热议《书籍a》”。
在确定目标推荐话题的推荐理由后，可以将“话题中正在热议《书籍a》”作为目标文本，并利用目标文本对目标推荐话题的原始文本进行替换并更新展示出。这样，在展示目标推荐话题时，可以通过目标文本更直观地展示出目标推荐话题与所述第一推荐书籍的关联。
示例性的，参见图6所示，为本公开实施例提供的另一种在书籍推荐页面展示推荐书籍以及目标推荐话题的示意图。相较于图5示出的书籍推荐页面，书籍a和书籍b的目标推荐话题以更新后的目标文本进行展示。针对书籍c，还展示出了以推荐理由的方式展示出的目标文本，为与其他以目标文本作为展示内容展示出的目标推荐话题进行区分，以“*”进行标注。
另外，在本公开另一实施例中，在展示推荐书籍以及目标推荐话题后，可以响应于对目标推荐话题的触发操作，展示出目标推荐话题下的话题帖。在一种可能的情况下，由于目标推荐话题中的话题帖可能会包括与推荐书籍无关的话题帖，因此可以响应于对所述目标推荐话题的第一触发操作，从所述目标推荐话题下各话题帖中，确定与所述推荐书籍相关的目标话题 帖，并对于推荐书籍相关的目标话题帖进行展示。
在一种可能的情况下，若确定的目标话题帖包括多个，可以展示所述目标话题帖对应的话题帖目录。这样，通过话题帖目录的形式，可以有序地将多个目标话题帖进行展示。然后，还可以响应于对所述话题帖目录中任一目标话题帖的第二触发操作，展示该目标话题帖，用户则可以在目标话题帖中查看评论或者与其他用户讨论沟通，并获取到新的感兴趣的书籍。在另一种可能的情况下，若确定的目标话题帖包括一个，则可以直接对目标话题帖进行展示。
示例性的，参见图7所示，为本本公开实施例提供的一种展示目标话题帖时的示意图。其中，图7中(a)示出了在确定了多个目标话题帖的情况下，展示出的话题帖目录的示意图。在示意图中，展示出了目标推荐话题“话题1”下的多个目标话题帖构成的话题帖目录。在目标话题帖下还可以展示出在该目标话题帖中当前参与的用户数量和评论数量供用户参考。图7中(b)则示出了由图7中(a)对任一目标话题帖的第二触发操作展示出的目标话题帖，或者在目标话题帖仅包括一个时，直接展示出目标话题帖的示例图。其中，具体可以展示出目标话题帖的引言、已参与话题讨论的用户对应的用户信息(比如用户头像、用户名称、用户身份标识等)、以及用户发送展示的讨论内容。另外，在讨论内容中，具体还可以包括与书籍相关的阅读链接、封面等信息，具体可以根据实际情况确定，图7仅提供可实施的一种示例，并不做出限定。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
基于同一发明构思，本公开实施例中还提供了与话题推荐方法对应的话题推荐装置，由于本公开实施例中的装置解决问题的原理与本公开实施例上述话题推荐方法相似，因此装置的实施可以参见方法的实施，重复之处不再赘述。
参照图8所示，为本公开实施例提供的一种话题推荐装置的示意图，所述装置包括：确定模块81、获取模块82、以及展示模块83；其中，
确定模块81，用于响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；
获取模块82，用于获取与所述目标书籍匹配的目标推荐话题；
展示模块83，用于按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。
一种可选的实施方式中，所述预设展示条件包括下述至少一种：当前展示页面为阅读书籍的章节末页，当前展示页面为书籍推荐页面；所述确定模块81在响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍时，用于：响应当前展示页面为阅读书籍的章节末页，将所述阅读书籍作为所述目标书籍；或者，响应当前展示页面为书籍推荐页面，获取至少一个第一推荐书籍，将所述至少一个第一推荐书籍作为所述目标书籍。
一种可选的实施方式中，在当前展示页面为阅读书籍的章节末页的情况下，所述推荐书籍还包括第二推荐书籍；所述话题推荐装置还包括处理模块84，用于：基于所述目标推荐话题下各话题帖中的各推荐书籍信息，确定与所述目标推荐话题匹配的所述第二推荐书籍。
一种可选的实施方式中，所述获取模块82在获取与所述目标书籍匹配 的目标推荐话题时，用于：确定与所述目标书籍之间的匹配度大于设定阈值的候选推荐话题；基于各所述候选推荐话题分别对应的转化阅读人数，对所述各候选推荐话题排序，并基于排序结果从所述候选推荐话题中确定所述目标推荐话题；所述转化阅读人数是指在阅读所述候选推荐话题后，阅读所述候选推荐话题包括的书籍的新增用户数。
一种可选的实施方式中，所述获取模块82根据以下步骤确定所述目标书籍与任一话题之间的匹配度：针对任一话题，基于该话题的第一分类信息、以及所述目标书籍的第二分类信息，确定该话题与所述目标书籍的匹配度。
一种可选的实施方式中，所述第一分类信息和第二分类信息分别具有多个分类层级；针对任一话题，所述获取模块82在基于该话题的第一分类信息、以及所述目标书籍的第二分类信息，确定该话题与所述目标书籍的匹配度时，用于：针对任一分类层级，基于第一分类信息在该分类层级下的第一分类层级信息、以及第二分类信息在该分类层级下的第二分类层级信息，确定该话题与所述目标书籍在该分类层级下的层级匹配度；基于在多分类层级下分别确定的所述层级匹配度，确定该话题与所述目标书籍的匹配度。
一种可选的实施方式中，所述展示模块83在按照与所述预设展示条件匹配的展示方式，展示所述推荐书籍以及所述目标推荐话题时，用于：在所述预设展示条件包括：当前展示页面为阅读书籍的章节末页的情况下，在所述章节末页依次展示各目标推荐话题，并在每个目标推荐话题下，展示该目标推荐话题匹配的各推荐书籍；或者，在所述预设展示条件包括：当前展示页面为书籍推荐页面的情况下，在所述书籍推荐页面依次展示各推荐书籍，以及该推荐书籍匹配的各目标推荐话题。
一种可选的实施方式中，若当前展示页面为阅读书籍的章节末页，所述展示模块83在展示该目标推荐话题匹配的各推荐书籍时，用于：基于该目标推荐话题下所述各个推荐书籍分别对应的阅读热度，确定所述各推荐书籍的展示顺序，在该目标推荐话题下，按照确定的展示顺序依次展示所述各推荐书籍。
一种可选的实施方式中，若当前展示页面为书籍推荐页面，所述展示模块83在所述书籍推荐页面依次展示各推荐书籍时，用于：基于各所述推荐书籍分别对应的书籍消费特征，确定各个所述推荐书籍的展示顺序；所述书籍消费特征包括阅读人数以及阅读时长；在所述书籍推荐页面，基于确定的各个所述推荐书籍的展示顺序展示所述推荐书籍。
一种可选的实施方式中，所述展示模块83在展示所述目标推荐话题时，用于：获取所述目标推荐话题对应的话题属性信息；基于所述目标推荐话题对应的话题属性信息和/或与所述目标推荐话题匹配的各第一推荐书籍，生成所述目标推荐话题的推荐理由；其中，所述推荐理由用于建立所述目标推荐话题与所述第一推荐书籍的关联；基于所述目标推荐话题的推荐理由对应的目标文本，替换所述目标推荐话题的原始文本；基于所述目标文本，展示更新后所述目标推荐话题。
一种可选的实施方式中，在展示推荐书籍以及所述目标推荐话题后，所述展示模块83还用于：响应于对所述目标推荐话题的第一触发操作，从所述目标推荐话题下各话题帖中，确定与所述推荐书籍相关的目标话题帖；响应于所述目标话题帖包括多个，展示所述目标话题帖对应的话题帖目录，并响应于对所述话题帖目录中任一目标话题帖的第二触发操作，展示该目标话题帖，或者，响应于所述目标话题帖包括一个，展示所述目标话题帖。
关于装置中的各模块的处理流程、以及各模块之间的交互流程的描述可以参照上述方法实施例中的相关说明，这里不再详述。
本公开实施例还提供了一种计算机设备，如图9所示，为本公开实施例提供的计算机设备结构示意图，包括：
处理器10和存储器20；所述存储器20存储有处理器10可执行的机器可读指令，处理器10用于执行存储器20中存储的机器可读指令，所述机器可读指令被处理器10执行时，处理器10执行下述步骤：
响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；获取与所述目标书籍匹配的目标推荐话题；按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。
上述存储器20包括内存210和外部存储器220；这里的内存210也称内存储器，用于暂时存放处理器10中的运算数据，以及与硬盘等外部存储器220交换的数据，处理器10通过内存210与外部存储器220进行数据交换。
上述指令的具体执行过程可以参考本公开实施例中所述的话题推荐方法的步骤，此处不再赘述。
本公开实施例还提供一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行上述方法实施例中所述的话题推荐方法的步骤。其中，该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例还提供一种计算机程序产品，该计算机程序产品承载有程序代码，所述程序代码包括的指令可用于执行上述方法实施例中所述的 话题推荐法的步骤，具体可参见上述方法实施例，在此不再赘述。
其中，上述计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中，所述计算机程序产品具体体现为计算机存储介质，在另一个可选实施例中，计算机程序产品具体体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统和装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。在本公开所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，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单元中，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单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使 用时，可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解，本公开的技术方案本质上或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上所述实施例，仅为本公开的具体实施方式，用以说明本公开的技术方案，而非对其限制，本公开的保护范围并不局限于此，尽管参照前述实施例对本公开进行了详细的说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应所述以权利要求的保护范围为准。

Claims (14)

  1. 一种话题推荐方法，包括：
    响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；
    获取与所述目标书籍匹配的目标推荐话题；
    按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。
  2. 根据权利要求1所述的方法，其中，所述预设展示条件包括下述至少一种：当前展示页面为阅读书籍的章节末页，当前展示页面为书籍推荐页面；
    所述响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍，包括：
    响应当前展示页面为阅读书籍的章节末页，将所述阅读书籍作为所述目标书籍；或者，
    响应当前展示页面为书籍推荐页面，获取至少一个第一推荐书籍，将所述至少一个第一推荐书籍作为所述目标书籍。
  3. 根据权利要求2所述的方法，其中，在当前展示页面为阅读书籍的章节末页的情况下，所述推荐书籍还包括第二推荐书籍；
    所述方法还包括：
    基于所述目标推荐话题下各话题帖中的各推荐书籍信息，确定与所述 目标推荐话题匹配的所述第二推荐书籍。
  4. 根据权利要求1-3中任一项所述的方法，其中，所述获取与所述目标书籍匹配的目标推荐话题，包括：
    确定与所述目标书籍之间的匹配度大于设定阈值的候选推荐话题；
    基于各所述候选推荐话题分别对应的转化阅读人数，对所述各候选推荐话题排序，并基于排序结果从所述候选推荐话题中确定所述目标推荐话题；
    所述转化阅读人数是指在阅读所述候选推荐话题后，阅读所述候选推荐话题包括的书籍的新增用户数。
  5. 根据权利要求4所述的方法，其中，根据以下步骤确定所述目标书籍与任一话题之间的匹配度：
    针对任一话题，基于所述话题的第一分类信息、以及所述目标书籍的第二分类信息，确定所述话题与所述目标书籍的匹配度。
  6. 根据权利要求5所述的方法，其中，所述第一分类信息和所述第二分类信息分别具有多个分类层级；针对任一话题，基于所述话题的所述第一分类信息、以及所述目标书籍的所述第二分类信息，确定所述话题与所述目标书籍的匹配度，包括：
    针对任一分类层级，基于所述第一分类信息在所述分类层级下的第一分类层级信息、以及所述第二分类信息在所述分类层级下的第二分类层级信息，确定所述话题与所述目标书籍在所述分类层级下的层级匹配度；
    基于在多分类层级下分别确定的所述层级匹配度，确定所述话题与所述目标书籍的匹配度。
  7. 根据权利要求1-6中任一项所述的方法，其中，所述按照与所述预设展示条件匹配的展示方式，展示所述推荐书籍以及所述目标推荐话题，包括：
    在所述预设展示条件包括：当前展示页面为阅读书籍的章节末页的情况下，在所述章节末页依次展示各目标推荐话题，并在每个目标推荐话题下，展示所述目标推荐话题匹配的各推荐书籍；或者，
    在所述预设展示条件包括：当前展示页面为书籍推荐页面的情况下，在所述书籍推荐页面依次展示各推荐书籍，以及所述推荐书籍匹配的各目标推荐话题。
  8. 根据权利要求7所述的方法，其中，若当前展示页面为阅读书籍的章节末页，所述展示所述目标推荐话题匹配的各推荐书籍，包括：
    基于所述目标推荐话题下所述各推荐书籍分别对应的阅读热度，确定所述各推荐书籍的展示顺序，在所述目标推荐话题下，按照确定的展示顺序依次展示所述各推荐书籍。
  9. 根据权利要求7所述的方法，其中，若当前展示页面为书籍推荐页面，所述在所述书籍推荐页面依次展示各推荐书籍，包括：
    基于各所述推荐书籍分别对应的书籍消费特征，确定各个所述推荐书籍的展示顺序；所述书籍消费特征包括阅读人数以及阅读时长；
    在所述书籍推荐页面，基于确定的各个所述推荐书籍的展示顺序展示所述推荐书籍。
  10. 根据权利要求1-9中任一项所述的方法，其中，展示所述目标推荐话题，包括：
    获取所述目标推荐话题对应的话题属性信息；
    基于所述目标推荐话题对应的话题属性信息和/或与所述目标推荐话题匹配的各第一推荐书籍，生成所述目标推荐话题的推荐理由；其中，所述推荐理由用于建立所述目标推荐话题与所述第一推荐书籍的关联；
    基于所述目标推荐话题的推荐理由对应的目标文本，替换所述目标推荐话题的原始文本；
    基于所述目标文本，展示更新后所述目标推荐话题。
  11. 根据权利要求1-10中任一项所述的方法，其中，在展示所述推荐书籍以及所述目标推荐话题后，所述方法还包括：
    响应于对所述目标推荐话题的第一触发操作，从所述目标推荐话题下各话题帖中，确定与所述推荐书籍相关的目标话题帖；
    响应于所述目标话题帖包括多个，展示所述目标话题帖对应的话题帖目录，并响应于对所述话题帖目录中任一目标话题帖的第二触发操作，展示所述目标话题帖，或者，
    响应于所述目标话题帖包括一个，展示所述目标话题帖。
  12. 一种话题推荐装置，包括：
    确定模块，用于响应满足预设展示条件，确定在所述预设展示条件下待展示的目标书籍；
    获取模块，用于获取与所述目标书籍匹配的目标推荐话题；
    展示模块，用于按照与所述预设展示条件匹配的展示方式，展示推荐书籍以及所述目标推荐话题；所述推荐书籍至少包括所述目标书籍。
  13. 一种计算机设备，包括：处理器、存储器，所述存储器存储有所述处理器可执行的机器可读指令，所述处理器用于执行所述存储器中存储的机器可读指令，所述机器可读指令被所述处理器执行时，所述处理器执行如权利要求1至11任一项所述的话题推荐方法。
  14. 一种计算机可读存储介质，其中，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被计算机设备运行时，所述计算机设备执行如权利要求1至11任一项所述的话题推荐方法。
PCT/CN2023/093190 2022-05-26 2023-05-10 一种话题推荐方法、装置、计算机设备及存储介质 WO2023226760A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210582953.8 2022-05-26
CN202210582953.8A CN114860919A (zh) 2022-05-26 2022-05-26 一种话题推荐方法、装置、计算机设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023226760A1 true WO2023226760A1 (zh) 2023-11-30

Family

ID=82641881

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/093190 WO2023226760A1 (zh) 2022-05-26 2023-05-10 一种话题推荐方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN114860919A (zh)
WO (1) WO2023226760A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114860919A (zh) * 2022-05-26 2022-08-05 北京字节跳动网络技术有限公司 一种话题推荐方法、装置、计算机设备及存储介质
CN115357753A (zh) * 2022-08-30 2022-11-18 北京字跳网络技术有限公司 一种信息展示方法、装置、计算机设备及存储介质
CN117591747B (zh) * 2024-01-11 2024-05-07 浙江同花顺智能科技有限公司 一种信息生成式推荐方法、装置、电子设备及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150227529A1 (en) * 2012-12-31 2015-08-13 Google Inc. Methods, systems, and media for recommending media content
US20170169498A1 (en) * 2015-12-15 2017-06-15 International Business Machines Corporation Identifying recommended electronic books with detailed comparisons
CN107783703A (zh) * 2017-09-26 2018-03-09 掌阅科技股份有限公司 电子书与电子书话题交互方法、计算设备、存储介质
CN107944033A (zh) * 2017-12-13 2018-04-20 北京百度网讯科技有限公司 关联话题推荐方法和装置
CN108255999A (zh) * 2017-12-29 2018-07-06 北京奇虎科技有限公司 内容推荐方法及装置
CN113378061A (zh) * 2021-07-02 2021-09-10 北京字节跳动网络技术有限公司 一种信息搜索方法、装置、计算机设备及存储介质
CN113987387A (zh) * 2021-10-29 2022-01-28 掌阅科技股份有限公司 页面展示方法、电子设备及计算机存储介质
CN114860919A (zh) * 2022-05-26 2022-08-05 北京字节跳动网络技术有限公司 一种话题推荐方法、装置、计算机设备及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110717030B (zh) * 2019-09-12 2023-08-18 上海连尚网络科技有限公司 一种呈现电子书籍详情页的方法与设备
CN112507252A (zh) * 2020-12-17 2021-03-16 掌阅科技股份有限公司 书籍榜单的展示方法、计算设备及计算机存储介质
CN112667127A (zh) * 2020-12-23 2021-04-16 北京字节跳动网络技术有限公司 书籍信息显示方法、装置、计算机设备及可读存储介质
CN113778295B (zh) * 2021-09-28 2023-08-08 北京字跳网络技术有限公司 一种书籍推荐方法、装置、计算机设备及存储介质
CN113836429A (zh) * 2021-10-13 2021-12-24 掌阅科技股份有限公司 书籍推荐方法、终端及存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150227529A1 (en) * 2012-12-31 2015-08-13 Google Inc. Methods, systems, and media for recommending media content
US20170169498A1 (en) * 2015-12-15 2017-06-15 International Business Machines Corporation Identifying recommended electronic books with detailed comparisons
CN107783703A (zh) * 2017-09-26 2018-03-09 掌阅科技股份有限公司 电子书与电子书话题交互方法、计算设备、存储介质
CN107944033A (zh) * 2017-12-13 2018-04-20 北京百度网讯科技有限公司 关联话题推荐方法和装置
CN108255999A (zh) * 2017-12-29 2018-07-06 北京奇虎科技有限公司 内容推荐方法及装置
CN113378061A (zh) * 2021-07-02 2021-09-10 北京字节跳动网络技术有限公司 一种信息搜索方法、装置、计算机设备及存储介质
CN113987387A (zh) * 2021-10-29 2022-01-28 掌阅科技股份有限公司 页面展示方法、电子设备及计算机存储介质
CN114860919A (zh) * 2022-05-26 2022-08-05 北京字节跳动网络技术有限公司 一种话题推荐方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN114860919A (zh) 2022-08-05

Similar Documents

Publication Publication Date Title
WO2023226760A1 (zh) 一种话题推荐方法、装置、计算机设备及存储介质
CN107851092B (zh) 个人实体建模
US9886514B2 (en) System and method for customizing search results from user's perspective
US8972428B2 (en) Providing an answer to a question left unanswered in an electronic forum
US8769417B1 (en) Identifying an answer to a question in an electronic forum
US10469275B1 (en) Clustering of discussion group participants
EP4276659A1 (en) Method and apparatus for information display, and non-volatile computer storage medium
WO2022052817A1 (zh) 搜索处理方法、装置、终端及存储介质
US10061767B1 (en) Analyzing user reviews to determine entity attributes
US20140074828A1 (en) Systems and methods for cataloging consumer preferences in creative content
US11599822B1 (en) Generation and use of literary work signatures reflective of entity relationships
US10482142B2 (en) Information processing device, information processing method, and program
CN112069326A (zh) 知识图谱的构建方法、装置、电子设备及存储介质
WO2011159863A1 (en) A system and method for query temporality analysis
CN113038053A (zh) 一种数据合成方法、装置、电子设备以及存储介质
WO2023109323A1 (zh) 一种订阅内容处理方法、装置、计算机设备及存储介质
CN111639269A (zh) 一种地点推荐方法及装置
CN115080829A (zh) 一种搜索结果展示方法、装置、计算机设备及存储介质
JP2022145367A (ja) アイテムに関連した情報を提供する方法および電子装置
US11282122B1 (en) Evaluation and comparison of vendors according to structured capability models
CN113377975A (zh) 多媒体资源的处理方法、装置、计算机设备及存储介质
CN113297406A (zh) 图片搜索方法、系统及电子设备
JP5246309B2 (ja) 情報処理装置及び情報処理プログラム
CN112051951A (zh) 一种媒体内容展示方法、媒体内容的展示确定方法及装置
JP2014215633A (ja) インテント分類装置、方法及びプログラム、サービス選択支援装置、方法及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23810833

Country of ref document: EP

Kind code of ref document: A1