A topic recommendation method and device, computer equipment and storage medium

Abstract

This disclosure provides a topic recommendation method, apparatus, computer device, and storage medium. The method includes: responding to conditions for displaying recommended topics, determining at least one topic to be recommended, the topic to be recommended including multiple books; for the topic to be recommended, obtaining topic attribute information based on at least one dimension of the topic to be recommended as a recommendation reason matching the topic to be recommended; wherein the dimension includes a topic dimension and / or a book dimension; and displaying the at least one topic to be recommended and the recommendation reason matching the topic to be recommended.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular, to a topic recommendation method and device, computer device and storage medium. BACKGROUND

[0002] In an electronic reading platform, a user can be shown a recommended topic including books, so as to recommend the user to find a book of interest more quickly according to a discussion on the book under the recommended topic.

[0003] Since the recommended topic itself presents relatively general or abstract content, the user generally cannot directly determine whether the recommended topic contains a book of interest through the recommended topic itself, and can only trigger each recommended topic in turn to view the detail information of each topic post under the recommended topic to make a further determination, thereby resulting in a low efficiency of finding a book of interest. SUMMARY

[0004] The present disclosure provides at least a topic recommendation method, device, computer device and storage medium.

[0005] In a first aspect, the present disclosure provides a topic recommendation method, comprising: determining at least one to-be-recommended topic in response to a recommended topic display condition being met, the to-be-recommended topic including a plurality of books; obtaining, for the to-be-recommended topic, a recommendation reason matched for the to-be-recommended topic based on topic attribute information of at least one dimension of the to-be-recommended topic; wherein the dimension includes a topic dimension and / or a book dimension; and displaying the at least one to-be-recommended topic and the recommendation reason matched for the to-be-recommended topic.

[0006] In an optional implementation, the topic attribute information of the book dimension includes at least one of the following: book attribute information; the book attribute information indicating whether the to-be-recommended topic includes a first target book; the target book being a book corresponding to reading data satisfying a first condition; category attribute information; the category attribute information being used to indicate whether the to-be-recommended topic includes a second target book whose recommendation times and / or discussion times in a target category satisfy a preset requirement, the target category being a category of books corresponding to reading data satisfying a second condition; the topic attribute information of the topic dimension including consumption attribute information; and the consumption attribute information being used to indicate a number of topic posts corresponding to the to-be-recommended topic and / or a converted reading user number, the converted reading user number being a number of new users reading the target book after reading the to-be-recommended topic.

[0007] In an alternative implementation, the recommendation reason matched with the topic to be recommended is determined by: determining, from topic attribute information of the topic to be recommended in at least one dimension, a recommendation reason template matched with the topic to be recommended from a candidate recommendation reason template corresponding to the at least one dimension respectively; the recommendation reason template containing filling indication information and recommendation word information; extracting information matched with the filling indication information from the topic attribute information of the topic to be recommended, replacing the filling indication information in the recommendation reason template, and obtaining the recommendation reason matched with the topic to be recommended.

[0008] In an alternative implementation, the method further comprises: in response to the recommendation reason matched with the topic to be recommended including multiple, selecting a target recommendation reason from the multiple recommendation reasons based on a priority order corresponding to the multiple recommendation reasons; and taking the target recommendation reason as the recommendation reason matched with the topic to be recommended displayed.

[0009] In an alternative implementation, the at least one topic to be recommended is determined by: determining, based on reading attribute features and / or topic heat features, the at least one topic to be recommended from multiple topics to be recommended.

[0010] In an alternative implementation, before displaying the at least one topic to be recommended and the recommendation reason matched with each of the topics to be recommended, the method further comprises: in a case where the topic attribute information of the topic to be recommended indicates a target book, obtaining preview information of the target book; and the displaying the at least one topic to be recommended and the recommendation reason matched with the topic to be recommended comprises: displaying the at least one topic to be recommended, the recommendation reason matched with the topic to be recommended, and the preview information of the target book matched with the topic to be recommended.

[0011] In an alternative implementation, the displaying the at least one topic to be recommended, the recommendation reason matched with the topic to be recommended, and the preview information of the target book matched with the topic to be recommended comprises: displaying multiple topic cards in a topic recommendation area; and in each of the topic cards, the topic to be recommended is displayed in a first format, the recommendation reason matched with the topic to be recommended is displayed in a second format below the topic to be recommended, and the preview information of the target book is displayed in a third format in a case where the target book exists.

[0012] In a second aspect, the embodiments of the present disclosure further provide a topic recommendation apparatus, comprising: a determination module configured to determine at least one topic to be recommended in response to a recommendation topic display condition being met, the topic to be recommended comprising a plurality of books; an acquisition module configured to acquire, for the topic to be recommended, a recommendation reason matched by the topic to be recommended based on topic attribute information of at least one dimension of the topic to be recommended; wherein the dimension comprises a topic dimension and / or a book dimension; and a display module configured to display the at least one topic to be recommended and the recommendation reason matched by the topic to be recommended.

[0013] In an optional implementation, the topic attribute information of the book dimension comprises at least one of the following: book attribute information, the book attribute information indicating whether the topic to be recommended comprises a first target book, the target book being a book whose corresponding reading data satisfies a first condition; category attribute information, the category attribute information being used to indicate whether the topic to be recommended comprises a second target book whose recommendation times and / or discussion times in a target category satisfy a preset requirement, the target category being a category of books whose corresponding reading data satisfies a second condition; and the topic attribute information of the topic dimension comprises consumption attribute information, the consumption attribute information being used to indicate a number of topic posts corresponding to the topic to be recommended and / or a number of converted reading users, the number of converted reading users being a number of new users who read the target book after reading the topic to be recommended.

[0014] In an optional implementation, the topic recommendation apparatus further comprises a processing module, and the recommendation reason matched by the topic to be recommended is determined by the processing module in the following manner: according to the topic attribute information of the topic to be recommended in at least one dimension, a recommendation reason template matched by the topic to be recommended is determined from a candidate recommendation reason template corresponding to the at least one dimension respectively; the recommendation reason template comprises filling instruction information and recommendation word information; information matched by the filling instruction information is extracted from the topic attribute information of the topic to be recommended, and the filling instruction information in the recommendation reason template is replaced to obtain the recommendation reason matched by the topic to be recommended.

[0015] In an optional implementation, the processing module is further configured to: in response to the recommendation reason matched by the topic to be recommended comprising a plurality of recommendation reasons, select a target recommendation reason from the plurality of recommendation reasons based on a priority order corresponding to the plurality of recommendation reasons; and use the target recommendation reason as the recommendation reason matched by the topic to be recommended displayed.

[0016] In an optional implementation, the determination module determines the at least one topic to be recommended in the following manner: at least one topic to be recommended is determined from a plurality of topics to be recommended based on reading attribute features and / or topic heat features.

[0017] In an optional implementation, before displaying the at least one recommended topic and the recommendation reason matched by each of the recommended topics, the display module is further configured to: in a case where the topic attribute information of the recommended topic indicates a target book, acquire preview information of the target book; and when displaying the at least one recommended topic and the recommendation reason matched by each of the recommended topics, the display module is configured to: display the at least one recommended topic, the recommendation reason matched by each of the recommended topics, and the preview information of the target book matched by each of the recommended topics.

[0018] In an optional implementation, when displaying the at least one recommended topic, the recommendation reason matched by each of the recommended topics, and the preview information of the target book matched by each of the recommended topics, the display module is configured to: display a plurality of topic cards in a topic recommendation area; and in each of the topic cards, display the recommended topic in a first format, display the recommendation reason matched by the recommended topic in a second format below the recommended topic, and display the preview information in a third format in a case where the target book exists.

[0019] In a third aspect, the optional implementation of the present disclosure further 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 machine readable instructions stored in the memory, and when the machine readable instructions are executed by the processor, the machine readable instructions perform the steps of the first aspect or any possible implementation of the first aspect.

[0020] In a fourth aspect, the optional implementation of the present disclosure further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and when the computer program is executed, the computer program performs the steps of the first aspect or any possible implementation of the first aspect.

[0021] The topic recommendation method and device, the computer device and the storage medium provided by the embodiments of the present disclosure can acquire the recommendation reason matched by the topic attribute information of at least one dimension of the recommended topic in a case where the recommended topic is determined, so that the recommendation reason matched by the recommended topic is displayed together when the recommended topic is displayed. In this way, the recommended topic can be further described and explained specifically by the displayed recommendation reason, the user can select the recommended topic of interest more specifically according to the recommendation reason, and then view the book recommendation information under the recommended topic, thereby improving the efficiency of finding the book of interest.

[0022] In order to make the above objectives, characteristics and advantages of the present disclosure more apparent and easy to understand, the following preferred embodiments are specifically described below with reference to the attached drawings. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0024] Figure 1 A flowchart of a topic recommendation method provided by an embodiment of this disclosure is shown;

[0025] Figure 2 This illustration shows a schematic diagram of a recommendation page displaying topics to be recommended, provided by an embodiment of this disclosure;

[0026] Figure 3 A schematic diagram of another recommendation page provided by an embodiment of this disclosure is shown;

[0027] Figure 4 A schematic diagram of a topic recommendation device provided in an embodiment of this disclosure is shown;

[0028] Figure 5 A schematic diagram of a computer device provided in an embodiment of the present disclosure is shown. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown herein can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0030] Research has found that displaying recommended topics, including books, to users can help them find books of interest after browsing these topics. While recommended topics can contain discussions about various books, they are typically displayed by simply showing the title. The topics themselves are relatively general or abstract, making it difficult for users to directly determine whether a recommended topic contains books of interest. Users must sequentially access each recommended topic and view the details of each post to make a further judgment, resulting in low efficiency in finding books of interest.

[0031] Based on the above research, this disclosure provides a topic recommendation method. Given a topic to be recommended, it can obtain matching recommendation reasons under at least one dimension of topic attribute information for the topic to be recommended. These matching recommendation reasons are then displayed along with the topic itself. By utilizing the displayed recommendation reasons, the topic to be recommended can be further described in a more targeted manner. Users can then more effectively select recommended topics of interest based on these reasons and view book recommendations under those topics, thereby improving the efficiency of finding books of interest.

[0032] The shortcomings of the above solutions are the result of the inventor's practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed in this disclosure below should be considered as the inventor's contribution to this disclosure.

[0033] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0034] To facilitate understanding of this embodiment, a topic recommendation method disclosed in this disclosure will first be described in detail. The execution entity of the topic recommendation method provided in this disclosure is generally a computer device with a certain computing capability. This computer device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. In some possible implementations, this topic recommendation method can be implemented by a processor calling computer-readable instructions stored in memory.

[0035] The topic recommendation method provided in this embodiment will be described below using the user as the execution subject as an example.

[0036] See Figure 1 The diagram shows a flowchart of a topic recommendation method provided in an embodiment of this disclosure. The method includes steps S101 to S103, wherein:

[0037] S101: In response to meeting the conditions for displaying recommended topics, at least one topic to be recommended is determined, and the topic to be recommended includes multiple books;

[0038] S102: For the topic to be recommended, obtain topic attribute information based on at least one dimension of the topic to be recommended as a recommendation reason for matching the topic to be recommended; wherein, the dimension includes the topic dimension and / or the book dimension;

[0039] S103: Display the at least one topic to be recommended and the reasons for recommending the topic.

[0040] The above S101 to S103 are explained in detail below.

[0041] Regarding S101 above, the topic recommendation method provided in this disclosure can be applied to different scenarios such as e-reading platforms. Taking an e-reading platform as an example, the platform may include a recommendation page displaying topics to be recommended. See [link to relevant documentation] Figure 2 The diagram illustrates a recommendation page displaying topics to be recommended, provided by an embodiment of this disclosure. The recommendation page specifically includes the topics to be recommended and the reasons for recommending them. In one possible scenario, the information recommendation page is displayed in response to a user opening an e-reading platform; or in response to a trigger operation for displaying the recommendation page, at least one topic to be recommended is displayed on that page.

[0042] The topics to be recommended generally revolve around the common attributes and characteristics of a type of book, and therefore can include multiple books. The title or post of the topic to be recommended can contain book information such as book titles. For example, the topic itself might use certain books as its text title, such as "Recommend Book A and Book B by Author A." In this case, multiple books can be identified from the topic itself, such as Book A and Book B in the example above.

[0043] In another possible scenario, since the topic to be recommended also includes topic threads created around the topic, different users can comment and communicate about the books involved in the topic. For example, if the topic to be recommended is "the most worthwhile science fiction novels to read," the specific books cannot be determined based on the topic itself. However, under this topic, users can participate in discussions in topic threads, such as creating a topic thread titled "Recommend Science Fiction Novel C," or commenting on a topic thread, such as "I recommend Science Fiction Novel D." Accordingly, multiple books included in the topic to be recommended can be determined from the topic threads and their comments, such as Science Fiction Novel C and Science Fiction Novel D as described above.

[0044] In addition to displaying the books included in the topic to be recommended in text form, you can also display the book covers, reading pages, and reading links in the topic and / or the topic posts under the topic to be recommended. Specific details can be determined based on the actual situation and will not be elaborated further here.

[0045] In specific implementation, when determining at least one topic to be recommended for display, the following method can be adopted: based on reading attribute characteristics and / or topic popularity characteristics, at least one topic to be recommended is determined from multiple topics to be recommended.

[0046] Among these, reading attribute features indicate user preferences while reading, specifically including preferred book categories (e.g., a preference for classical or modern literature); reading habits (e.g., a preference for speed reading or slow reading); and browsing preferences for topics (e.g., a preference for discussions with spoilers or without spoilers). Topic popularity features are determined based on the number of times a topic to be recommended has been viewed, indicating the total number of times the topic has been viewed.

[0047] In one possible scenario, multiple pre-created topics for recommendation can be retrieved from the e-reading platform. These topics may be created by users on the platform or by the platform itself. When determining at least one topic for recommendation from multiple topics using reading attribute features, more suitable topics can be provided to users based on their reading preferences. Conversely, when determining at least one topic for recommendation from multiple topics using topic popularity features, more timely and popular topics can be displayed.

[0048] Regarding S102 above, and for the at least one topic to be recommended identified in S101 above, in order to further describe and explain the topic to be recommended in a more targeted manner, so that users can more easily select and view the displayed topics to be recommended based on the recommendation reasons, recommendation reasons matching the topic to be recommended can be obtained based on topic attribute information of at least one dimension of the topic to be recommended; wherein, the dimension includes topic dimension and / or book dimension. Specifically, the topic attribute information of the book dimension includes at least one of the following: book attribute information and category attribute information; the topic attribute information of the topic dimension includes consumption attribute information.

[0049] Below, we will introduce the three different topic attribute information described above.

[0050] (a) Book attribute information.

[0051] Book attribute information is used to indicate whether the topic to be recommended includes a first target book; the first target book is a book whose corresponding reading data meets the first condition. Here, based on the user's historical reading data obtained with user authorization, multiple books read by the user and the reading data corresponding to each of the multiple books can be determined. By determining whether the reading data corresponding to each of the multiple books read by the user meets the first condition, the first target book can be determined from the multiple books.

[0052] When determining the first target book based on the first condition, in one possible scenario, the first condition may include the user's reading data over a period of time indicating that the current number of chapters read exceeds a preset number. For example, if more than 10 chapters have been read in the last 30 days, then books with more than 10 chapters read in only 30 days can be selected as the first target books based on the user's historical reading data obtained with the user's authorization. In another possible scenario, the first condition may also include the user's historical reading data, obtained with the user's authorization, indicating that the current number of chapters read for a certain book exceeds a preset number, and the existence of another user of the same type (e.g., users with similar reading attributes are considered as the same type of user), whose historical reading data, obtained with the authorization of this other user, also indicates that they have read the same book. In this case, other books read by this user in the historical reading data of this user of the same type of user can be selected as the first target books. As can be seen from the above explanation, the methods for obtaining the first target books included in the topic to be recommended are different in the two different scenarios.

[0053] In this case, the book attribute information of the topic to be recommended can be determined by checking whether the topic to be recommended includes the primary target book. Here, "the topic to be recommended includes the primary target book" specifically includes mentions or recommendations of the primary target book within the topic.

[0054] For example, for a topic to be recommended, if the topic contains a first-target book that this user has read more than 10 chapters of in the past 30 days, then the book attribute information corresponding to the topic to be recommended indicates that the topic to be recommended includes the first-target book. Alternatively, if the topic to be recommended contains a first-target book that other users of the same type as this user have read more than 10 chapters of in the past 30 days, then the book attribute information corresponding to the topic to be recommended indicates that the topic to be recommended includes the first-target book.

[0055] (b) Category attribute information.

[0056] Category attribute information is used to indicate whether the topic to be recommended includes a second target book within the target category whose recommendation frequency and / or discussion frequency meet preset requirements. The target category is the book category whose corresponding reading data meets the second condition. Category refers to the classification of books; the specific classification method can be determined according to the actual situation, such as classifying books into science fiction, romance novels, historical classics, etc.

[0057] Specifically, when using reading data to determine the target category to meet the second condition, the target category can be determined from the books read by the user over a period of time based on the user's authorized historical reading data, identifying the categories to which the books that meet the high-frequency reading criteria belong. For example, based on the user's authorized historical reading data, the top three most popular books in the past 30 days can be identified, and their categories can be determined as the target categories.

[0058] In this case, the category attribute information of the topic to be recommended can be determined by checking whether it includes books in the target category that meet a preset requirement for the number of recommendations. Here, if a target category is identified, multiple books within that category can be identified. When determining a second target book that meets preset requirements, these requirements could include, for example, the book with the most recommendations or the book with the most discussions.

[0059] For example, for a topic to be recommended, if it includes books in the target category that have the most recommendations and / or the most discussions among the top three books read by users in the past 30 days, then the category attribute information corresponding to the topic to be recommended can be determined to indicate that the topic to be recommended includes a second target book in the target category whose recommendation and / or discussion counts meet the preset requirements.

[0060] (c) Consumption attribute information.

[0061] Consumer attribute information is used to indicate the number of topic posts and / or the number of converted readers corresponding to the topic to be recommended. The number of converted readers refers to the number of new users who read the target book after reading the topic to be recommended.

[0062] Specifically, the topics to be recommended include topic posts, which are web pages created around the topic to facilitate user discussion and exchange about books. The number of topic posts corresponding to the topic to be recommended is the statistical count of topic posts under the topic to be recommended. These topic posts can include discussions and recommendations of books. These books are considered target books in this method. Since users may further read these books after viewing the topic to be recommended, the number of users who start reading the target books included in the topic after viewing it can be determined as the converted readership for the topic to be recommended.

[0063] For example, for a topic to be recommended, the corresponding consumption attribute information could be set to indicate the number of topic posts as 10; or it could indicate the number of converted readers as 3. Generally, since a larger number of topic posts for a topic to be recommended will result in a larger number of converted readers, in order to make the recommendation reasons for the topic to be recommended more sufficient, the corresponding consumption attribute information for the topic to be recommended can be determined when the number of topic posts reaches a certain number. For example, when the number of topic posts for a topic to be recommended exceeds 5, the corresponding consumption attribute information can be determined for the topic to be recommended.

[0064] For a topic to be recommended, the matching recommendation reason can be determined based on topic attribute information of at least one dimension of the topic. In specific implementation, a recommendation reason template matching the topic can be determined from the candidate recommendation reason templates corresponding to the topic in at least one dimension, based on the topic attribute information of the topic to be recommended in at least one dimension; the recommendation reason template includes fill instruction information and recommendation word information; information matching the fill instruction information is extracted from the topic attribute information of the topic to be recommended, and the fill instruction information in the recommendation reason template is replaced to obtain the recommendation reason matching the topic.

[0065] Below, using the topic attribute information under the different dimensions described above as examples, we will illustrate the reasons for determining the recommendation reasons that match the topic to be recommended.

[0066] Regarding the book attribute information in (a) above, specifically indicating whether the topic to be recommended includes the primary target book, possible scenarios include:

[0067] (a1) The first target book is the book that this user has read.

[0068] In this case, the recommendation reason template selected from the candidate recommendation reason templates is, for example, "Contains #fill in the title of the first target book#". Here, "Contains" is the recommendation word information, and "#fill in the title of the first target book#" is the filling instruction information. The filling instruction information indicates that the title of the first target book in this case should be filled in. The title of the first target book can be extracted based on the topic attribute information of the topic to be recommended, and the corresponding position in the filling instruction information of the recommendation reason template can be replaced.

[0069] For example, if the topic to be recommended is determined to be "Topic 1", and the book attribute information of the topic to be recommended indicates that it contains the first target book that the user has read, and the first target book is Book A, then according to the recommendation reason template listed in the example above, it can be determined that the recommendation reason matched by the topic to be recommended "Topic 1" is 1: "Contains Book A".

[0070] (a2) The first target book and the books read by other users who are similar to this user.

[0071] For example, in this case, the first target book is book A, and the book that this user and similar users have both read is book B. The recommendation reason template determined from the candidate recommendation reason template is, for example, "People who read #fill in the title of book B# are reading this." Here, "People who read XXX are reading this" is the recommendation word information, and "#fill in the title of book B#" is the filling instruction information. Unlike the case in (a1) above, when determining the topic recommendation reason, the first target book is not extracted and replaced, because the topic to be recommended actually aims to help users provide books that similar users have read.

[0072] Therefore, for example, if the topic to be recommended is determined to be "Topic 2", and the book attribute information of the topic to be recommended indicates the first target book that other users who are similar to this user have read, and the book filled in by the user is Book B, it can be determined that the recommendation reason matching the topic to be recommended "Topic 2" is 2: "People who read Book B are reading it".

[0073] Regarding the category attribute information in (b) above, specifically indicate whether the topic to be recommended includes a second target book within the target category whose recommendation count and / or discussion count meet preset requirements. Possible scenarios include:

[0074] (b1) Category attribute information indicates that the topics to be recommended include second target books in the target category whose recommendation frequency meets the preset requirements.

[0075] In this case, the recommendation reason template determined from the candidate recommendation reason template is, for example, "Category's Top Recommendation #Fill in the title of the second target book#". Here, "Category's Top Recommendation" is the recommendation keyword information, and "#Fill in the title of the second target book#" is the filling instruction information. The filling instruction information indicates that the title of the second target book in this case can be filled in. This can be done by extracting the title of the second target book based on the category attribute information of the topic to be recommended, and then replacing the corresponding position in the filling instruction information of the recommendation reason template.

[0076] For example, if the topic to be recommended is determined to be "Topic 3", and the corresponding category attribute information indicates that the topic to be recommended includes the second target book under the target category whose recommendation frequency meets the preset requirements, and the second target book is Book C, then according to the recommendation reason template listed in the example above, it can be determined that the recommendation reason matched by the topic to be recommended "Topic 3" is 3: "The first most popular book in the category is Book C".

[0077] (b2) Category attribute information indicates that the topics to be recommended include second target books in the target category whose number of discussions meets the preset requirements.

[0078] In this case, the recommendation reason template determined from the candidate recommendation reason template is, for example, "First place in category discussion #Fill in the title of the second target book#". Here, "First place in category discussion" is the recommendation keyword, and "#Fill in the title of the second target book#" is the filling instruction. The filling instruction indicates that the title of the second target book in this case can be filled in. This can be done by extracting the title of the second target book from the category attribute information of the topic to be recommended and replacing the corresponding position in the filling instruction information of the recommendation reason template.

[0079] For example, if the topic to be recommended is determined to be "Topic 4", and the corresponding category attribute information indicates that the topic to be recommended includes the second target book under the target category whose discussion frequency meets the preset requirements, and the second target book is Book D, then according to the recommendation reason template listed in the example above, it can be determined that the recommendation reason matched for the topic to be recommended "Topic 4" is 4: "The No. 1 Hot Recommendation in the Category: Book D".

[0080] Regarding the aforementioned consumption attribute information (c), specifically indicating the number of topic posts and / or the number of converted readers for the topic to be recommended, in this case, the recommendation reason template determined from the candidate recommendation reason template is, for example, "#filling the number of topic posts# posts, saving #filling the number of converted readers# book droughts." Here, "XX posts, saving XX book droughts" is the recommendation keyword information, and "#filling the number of topic posts#" and "#filling the number of converted readers#" are the filling instruction information. The filling instruction information indicates the number of topic posts and the number of converted readers indicated in the consumption attribute information in this case. Therefore, based on the consumption attribute information of the topic to be recommended, the number of topic posts and the number of converted readers can be obtained, and the corresponding positions in the filling instruction information of the recommendation reason template can be replaced.

[0081] For example, if the topic to be recommended is determined to be "Topic 5", and the corresponding consumption attribute information indicates that the number of posts for the topic to be recommended is 10 and the number of converted readers is 5, then according to the recommendation reason template listed in the example above, the recommendation reason matched for the topic to be recommended "Topic 5" is 5: "10 posts saved 5 people from book drought".

[0082] Furthermore, the topic to be recommended may not match any of the topic attribute information listed above. For example, the number of posts in the topic to be recommended may be small, such as no more than 5 posts, and it may not include the target books described in (a) or books in the target category described in (b), nor may it meet the conditions for determining consumer attribute information. In this case, for example, the recommendation reason for the topic to be recommended could be determined as "New topic, waiting for you to recommend books".

[0083] For example, if the topic to be recommended is determined to be "Topic 6", the number of posts under Topic 6 is less than 5, and the conditions described above are met, the recommendation reason 6 that matches the topic to be recommended "Topic 6" can be determined as: "New topic, waiting for you to recommend books".

[0084] In one possible scenario, for any topic to be recommended, such as "Topic 1" to "Topic 6" as described above, it may possess topic attribute information under different dimensions. Therefore, there may be multiple recommendation reasons that can be matched under different topic attribute information. To make the display of recommendation reasons for the topic to be recommended more concise and clear, one of the recommendation reasons can be selected for display.

[0085] In specific implementation, the recommendation reasons for matching the topic to be recommended include multiple reasons. Based on the priority order of the multiple recommendation reasons, a target recommendation reason is selected from the multiple recommendation reasons. The target recommendation reason is then used as the recommendation reason for matching the topic to be recommended.

[0086] The priority order can be predetermined, for example, the order of recommendation reasons 1-6 as described above can be used as the priority order. Since the higher priority recommendation reasons are determined based on the user's authorized historical reading data, they better align with the user's actual reading needs; the lower priority recommendation reasons are determined based on the reading habits of more users, thus encouraging users to view more popular topics.

[0087] Regarding S103 above, after determining the topic to be recommended and the matching recommendation reason, it can be displayed.

[0088] In one possible scenario, if the topic attribute information of the topic to be recommended indicates that there is a target book, preview information of the target book can also be obtained, and the at least one topic to be recommended, the recommendation reason matching the topic to be recommended, and preview information of the target book matching the topic to be recommended can be displayed.

[0089] Specifically, when displaying the topic to be recommended, the reasons for recommendation, and the preview information of the target book, multiple topic cards can be displayed in the topic recommendation area; wherein, in each topic card, the topic to be recommended is displayed in a first format, and under the topic to be recommended, the reasons for recommendation matching the topic to be recommended are displayed in a second format, and if the target book exists, the preview information is displayed in a third format.

[0090] For example, when displaying recommended topics, reasons for recommendation, and preview information of target books, see [link to relevant documentation]. Figure 3 The image shown is a schematic diagram of another recommendation page provided in an embodiment of this disclosure. Figure 3 The document specifically displays multiple topics to be recommended, presented as topic cards, along with the matching reasons for each topic, and preview information when target books are mentioned. Target books can include one or more books; therefore, the preview information can be displayed for one or more target books individually.

[0091] To highlight the difference between the topic to be recommended and the reason for recommendation, the first format used when displaying the topic to be recommended is a large font, while the second format used when displaying the reason for recommendation is a small font. Alternatively, further differentiation can be achieved through bolding, underlining, or using symbols such as "#". If the reason for recommendation includes a target book as the first or second target book, a third format can be used to display a preview of the target book, such as its cover image.

[0092] In this way, displaying different information in different formats can clearly distinguish the primary and secondary information, making it easier to differentiate and read. Additionally, in some cases, displaying preview information can be triggered, redirecting the user to the target book's reading page, which also makes it easier for the user to directly read the target book.

[0093] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0094] Based on the same inventive concept, this disclosure also provides a topic recommendation device corresponding to the topic recommendation method. Since the principle of the device in this disclosure for solving the problem is similar to that of the topic recommendation method described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0095] Reference Figure 4 The diagram shown is a schematic representation of a topic recommendation device provided in an embodiment of this disclosure. The device includes: a determining module 41, an acquiring module 42, and a display module 43; wherein,

[0096] The determination module 41 is used to determine at least one topic to be recommended in response to the conditions for displaying recommended topics, wherein the topics to be recommended include multiple books;

[0097] The acquisition module 42 is used to acquire, for the topic to be recommended, a recommendation reason matching the topic attribute information of at least one dimension of the topic to be recommended; wherein, the dimension includes the topic dimension and / or the book dimension;

[0098] The display module 43 is used to display the at least one topic to be recommended and the reasons for recommending the topic.

[0099] In one optional implementation, the topic attribute information of the book dimension includes at least one of the following: book attribute information; the book attribute information indicates whether the topic to be recommended includes a first target book; the target book is a book whose corresponding reading data meets a first condition; category attribute information; the category attribute information is used to indicate whether the topic to be recommended includes a second target book whose recommendation frequency and / or discussion frequency under the target category meets a preset requirement, the target category is a book category whose corresponding reading data meets a second condition; the topic attribute information of the topic dimension includes consumption attribute information; the consumption attribute information is used to indicate the number of topic posts and / or the number of converted readers corresponding to the topic to be recommended, the number of converted readers refers to the number of new users who read the target book after reading the topic to be recommended.

[0100] In an optional implementation, the topic recommendation device further includes a processing module 44, wherein the recommendation reason matching the topic to be recommended is determined by the processing module 44 in the following manner: based on the topic attribute information of the topic to be recommended in at least one dimension, a recommendation reason template matching the topic to be recommended is determined from the candidate recommendation reason templates corresponding to the at least one dimension; the recommendation reason template includes fill instruction information and recommendation word information; information matching the fill instruction information is extracted from the topic attribute information of the topic to be recommended, and the fill instruction information in the recommendation reason template is replaced to obtain the recommendation reason matching the topic to be recommended.

[0101] In an optional implementation, the processing module 44 is further configured to: in response to the fact that the recommendation reasons for matching the topic to be recommended include multiple reasons, select a target recommendation reason from the multiple recommendation reasons based on the priority order corresponding to the multiple recommendation reasons; and display the target recommendation reason as the recommendation reason for matching the topic to be recommended.

[0102] In one optional implementation, the determining module 41 determines at least one topic to be recommended in the following manner: based on reading attribute features and / or topic popularity features, it determines at least one topic to be recommended from multiple topics to be recommended.

[0103] In one optional implementation, before displaying the at least one topic to be recommended and the recommendation reasons matching each topic to be recommended, the display module 43 is further configured to: obtain preview information of the target book if the topic attribute information of the topic to be recommended indicates that there is a target book; when displaying the at least one topic to be recommended and the recommendation reasons matching the topic to be recommended, the display module 43 is configured to: display the at least one topic to be recommended, the recommendation reasons matching the topic to be recommended, and the preview information of the target book matching the topic to be recommended.

[0104] In one optional implementation, when displaying the at least one topic to be recommended, the recommendation reasons matching the topic to be recommended, and the preview information of the target book matching the topic to be recommended, the display module 43 is configured to: display multiple topic cards in the topic recommendation area; wherein, in each topic card, the topic to be recommended is displayed in a first format, and under the topic to be recommended, the recommendation reasons matching the topic to be recommended are displayed in a second format, and if the target book exists, the preview information is displayed in a third format.

[0105] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0106] This disclosure also provides a computer device, such as... Figure 5 The diagram shown is a schematic representation of a computer device structure provided in an embodiment of this disclosure, including:

[0107] Processor 10 and memory 20; the memory 20 stores machine-readable instructions executable by processor 10, and processor 10 executes the machine-readable instructions stored in memory 20. When the machine-readable instructions are executed by processor 10, processor 10 performs the following steps:

[0108] Upon meeting the conditions for displaying recommended topics, at least one topic to be recommended is identified, which includes multiple books. For each topic to be recommended, topic attribute information based on at least one dimension is obtained as a recommendation reason matching the topic. The dimension includes a topic dimension and / or a book dimension. The at least one topic to be recommended and the recommendation reason matching the topic are then displayed.

[0109] The aforementioned memory 20 includes a main memory 210 and an external memory 220; the main memory 210, also known as internal memory, is used to temporarily store the computational data in the processor 10, as well as the data exchanged with external memory 220 such as a hard disk. The processor 10 exchanges data with the external memory 220 through the main memory 210.

[0110] The specific execution process of the above instructions can be referred to the steps of the topic recommendation method described in the embodiments of this disclosure, and will not be repeated here.

[0111] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the topic recommendation method described in the above method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0112] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the topic recommendation method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0113] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0114] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0117] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A topic recommendation method, characterized in that, include: If the conditions for displaying recommended topics are met, at least one topic to be recommended is determined. The topic to be recommended includes multiple books, wherein the topic to be recommended is a discussion about the common attributes and characteristics of a type of book. For the topic to be recommended, obtain the recommendation reason for matching the topic to be recommended based on topic attribute information of at least one dimension of the topic to be recommended; wherein, the dimension includes topic dimension and / or book dimension; wherein, the topic attribute information of the book dimension includes at least one of book attribute information and category attribute information, and the topic attribute information of the topic dimension includes consumption attribute information; Display at least one topic to be recommended and the reasons for recommending the topic.

2. The method according to claim 1, characterized in that, The book attribute information indicates whether the topic to be recommended includes a first target book; the first target book is a book whose corresponding reading data meets the first condition; The category attribute information is used to indicate whether the topic to be recommended includes a second target book under the target category whose recommendation frequency and / or discussion frequency meet the preset requirements. The target category is the book category whose corresponding reading data meets the second condition. The consumption attribute information is used to indicate the number of topic posts and / or the number of converted readers corresponding to the topic to be recommended. The number of converted readers refers to the number of new users who read the target book after reading the topic to be recommended.

3. The method according to claim 1 or 2, characterized in that, The recommendation reasons that match the topic to be recommended are determined in the following way: Based on the topic attribute information of the topic to be recommended in at least one dimension, a recommendation reason template that matches the topic to be recommended is determined from the candidate recommendation reason templates corresponding to the at least one dimension respectively; The recommendation reason template includes fill-in instructions and recommendation word information; Extract information that matches the fill instruction information from the topic attribute information of the topic to be recommended, and replace the fill instruction information in the recommendation reason template to obtain the recommendation reason matching the topic to be recommended.

4. The method according to claim 3, characterized in that, Also includes: The recommendation reasons for matching the topic to be recommended include multiple reasons. Based on the priority order of the multiple recommendation reasons, a target recommendation reason is selected from the multiple recommendation reasons. The target recommendation reason is used as the recommendation reason for the topic to be recommended.

5. The method according to claim 1, characterized in that, At least one topic to be recommended will be identified using the following method: Based on reading attribute characteristics and / or topic popularity characteristics, at least one topic to be recommended is determined from multiple topics to be recommended.

6. The method according to claim 1, characterized in that, Before displaying the at least one topic to be recommended and the recommendation reason matched for each topic to be recommended, the method further includes: If the topic attribute information of the topic to be recommended indicates that there is a target book, obtain the preview information of the target book; The display of the at least one topic to be recommended and the reasons for recommending the topic to be recommended includes: Display at least one topic to be recommended, the reasons for recommending the topic, and preview information of the target books that match the topic.

7. The method according to claim 6, characterized in that, Displaying at least one topic to be recommended, the reasons for recommending the topic, and preview information of target books matching the topic, including: Multiple topic cards are displayed in the topic recommendation area; In each of the topic cards, the topic to be recommended is displayed in a first format, and under the topic to be recommended, the recommendation reasons matching the topic to be recommended are displayed in a second format. If the target book exists, the preview information is displayed in a third format.

8. A topic recommendation device, characterized in that, include: The determination module is used to determine at least one topic to be recommended in response to the conditions for displaying recommended topics. The topic to be recommended includes multiple books, wherein the topic to be recommended is a topic that discusses the common attributes and characteristics of a type of book. The acquisition module is used to acquire, for the topic to be recommended, a recommendation reason matching the topic to be recommended, determined based on topic attribute information of at least one dimension of the topic to be recommended; wherein, the dimension includes a topic dimension and / or a book dimension; wherein, the topic attribute information of the book dimension includes at least one of book attribute information and category attribute information, and the topic attribute information of the topic dimension includes consumption attribute information; The display module is used to display the at least one topic to be recommended and the reasons for recommending the topic.

9. A computer device, characterized in that, include: A processor and a memory, the memory storing machine-readable instructions executable by the processor, the processor executing the machine-readable instructions stored in the memory, wherein when the machine-readable instructions are executed by the processor, the processor performs the steps of the topic recommendation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a computer device, performs the steps of the topic recommendation method as described in any one of claims 1 to 7.

Images