Electronic book push method, electronic device and storage medium

Abstract

The present invention discloses an electronic book push method, electronic device and storage medium, the method comprising: determining a book user cluster corresponding to a target user; for the book user cluster corresponding to the target user, determining a candidate book pool corresponding to the book user cluster; calculating the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool; calculating the interest of the target user corresponding to each candidate book according to the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster, and selecting a number of candidate books according to the calculation result and pushing them to the target user. This method can broaden the reading range of the current user and enable the user to read more valuable books.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to an electronic book push method, electronic equipment and storage medium. Background Art

[0002] Books in the form of e-books are loved by a large number of users due to their advantages such as easy access. Most book reading platforms recommend books based on the similarity of the full text of the book. In the prior art, several books with high similarity in content to books that the user has read before are generally presented to the user as recommended books.

[0003] However, in the process of implementing the present invention, the inventors found that the above recommendation method has at least the following defects: it only makes relevance recommendations based on the historical reading behavior of the current reading user, resulting in too high similarity between multiple books read by the current reading user, which in turn limits the user's reading range and is not conducive to expanding the user's reading range based on interests. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide an electronic book push and book sort push method, electronic device and storage medium that overcome the above problems or at least partially solve the above problems.

[0005] According to one aspect of the present invention, a method for pushing electronic books and sorting and pushing electronic books is provided, comprising:

[0006] Determine a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book;

[0007] For the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool;

[0008] According to the cluster interest scores of the candidate books in the candidate book pool corresponding to the book user cluster, the interest of the target user corresponding to each candidate book is calculated, and several candidate books are selected as target books according to the calculation results and pushed to the target user.

[0009] According to another aspect of the present invention, there is provided an electronic device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0010] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations:

[0011] Determine a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book;

[0012] For the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool;

[0013] According to the cluster interest scores of the candidate books in the candidate book pool corresponding to the book user cluster, the interest of the target user corresponding to each candidate book is calculated, and several candidate books are selected as target books according to the calculation results and pushed to the target user.

[0014] According to another aspect of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables the processor to perform the following operations:

[0015] Determine a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book;

[0016] For the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool;

[0017] According to the cluster interest scores of the candidate books in the candidate book pool corresponding to the book user cluster, the interest of the target user corresponding to each candidate book is calculated, and several candidate books are selected as target books according to the calculation results and pushed to the target user.

[0018] In the electronic book push method, electronic device and storage medium provided by the present invention, first, each reading user is added to the book user cluster aggregated by the central book according to the reading behavior data of each reading user, and then the book user cluster corresponding to the target user is determined; then, for the book user cluster, the candidate book pool corresponding to the book user cluster is determined, and the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster is calculated according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool, and then the interest of the target user corresponding to each candidate book is calculated, and a number of candidate books are selected as target books according to the calculation results and pushed to the target user. It can be seen that this method aggregates similar users by means of book user clusters, and recommends books based on the reading preferences of similar users, thereby ensuring that the recommended books not only match the reading preferences of the current user, but also can broaden the reading range of the current user, so that the user can read more valuable books.

[0019] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0021] Figure 1 A flow chart showing a method for pushing electronic books and sorting and pushing books provided by an embodiment of the present invention;

[0022] Figure 2 A flowchart of a method for pushing electronic books and sorting and pushing books provided by another embodiment of the present invention is shown;

[0023] Figure 3 A schematic structural diagram of an electronic device according to another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0025] Embodiment 1

[0026] Figure 1 FIG. 1 is a flow chart showing a method for pushing electronic books and sorting and pushing books provided by an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0027] Step S110: determining a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book.

[0028] Specifically, in this embodiment, multiple book user clusters aggregated by central books are provided. Each book user cluster corresponds to a central book, and each reading user in the book user cluster has a deep interaction with the central book. The method for determining the central book can be flexibly set. For example, for any electronic book, when the number of reading users who have a deep interaction with the electronic book is greater than a preset number threshold, the electronic book is taken as a central book and a book user cluster corresponding to the central book is established to aggregate multiple reading users who have a deep interaction with the electronic book.

[0029] Accordingly, the current reading user to be recommended is taken as the target user, and a book user cluster corresponding to the target user is determined, specifically based on the reading behavior data of the target user. The number of book user clusters corresponding to the target user may be one or more, specifically depending on the number of books deeply interacted with by the target user.

[0030] Step S120: for the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool.

[0031] When there are multiple book user clusters corresponding to the target user, the following processing needs to be performed for each book user cluster respectively: determine the candidate book pool corresponding to the book user cluster based on the historical interaction books of each reading user contained in the book user cluster, count the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool, and calculate the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster based on the statistical results. The cluster interest score of the candidate book corresponding to the book user cluster is determined based on the interaction depth of each reading user in the book user cluster with the candidate book. For example, it can be determined by the average, maximum and / or minimum value of the interaction depth of each reading user in the book user cluster with the candidate book. Accordingly, the cluster interest score of the candidate book corresponding to the book user cluster is used to reflect the preference of each reading user in the book user cluster for the candidate book.

[0032] Step S130: Calculate the interest of the target user for each candidate book according to the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster, and select several candidate books as target books according to the calculation results and push them to the target user.

[0033] Specifically, the interest of the target user corresponding to each candidate book is calculated according to the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster. When a candidate book only appears in one book user cluster, the cluster interest score of the candidate book corresponding to the book user cluster can be directly used as the interest of the target user corresponding to the candidate book.

[0034] In addition, when there are multiple book user clusters corresponding to the target user and the candidate book appears in multiple book user clusters at the same time, the target user's interest in the candidate book can be comprehensively determined based on the cluster interest scores of the candidate book corresponding to each book user cluster and the target user's interaction depth with the central book of each book user cluster.

[0035] Through the above processing, the interest of the target user in each candidate book in each candidate book pool can be obtained. Accordingly, the candidate books are sorted in descending order of interest, and a number of candidate books are pushed to the target user according to the sorting result.

[0036] It can be seen that this method aggregates similar users through book user clusters and recommends books based on the reading preferences of similar users, thereby ensuring that the recommended books not only match the reading preferences of the current user, but also broaden the reading range of the current user, allowing the user to read more valuable books.

[0037] Embodiment 2

[0038] Figure 2 FIG. 2 is a flow chart showing a method for pushing an e-book provided by another embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0039] Step S200: adding each reading user to a book user cluster aggregated by a central book in advance according to the reading behavior data of each reading user.

[0040] A book user cluster refers to a user set composed of multiple reading users aggregated by a central book. Each book user cluster corresponds to a central book. Therefore, in order to distinguish each book user cluster, the cluster identifier of each book user cluster can be set to a form related to the book identifier of the central book.

[0041] In specific implementation, book user clusters are determined in the following ways:

[0042] First, the interactive books corresponding to each reading user are determined based on the reading behavior data of each reading user. The reading behavior data includes various types of behavior data triggered by the user during the reading process, including: the behavior of adding books to the bookshelf, the behavior of performing download operations on books, the behavior of reading books, etc. When determining the interactive books, it can be determined based on the interaction type and interaction duration of the interactive operations performed by the reading user on each book. For example, books on which the user has performed reading operations can be regarded as interactive books; for another example, in order to improve the quality of interactive books, books that the user has read for longer than a preset time can also be regarded as interactive books. The present invention does not limit the specific method of determining interactive books.

[0043] Then, the interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth are determined, and the interactive book with an interaction value greater than a preset threshold is determined as the central book. Since the same reading user usually corresponds to multiple interactive books, in order to determine the user's preference for each interactive book, it is necessary to determine the interaction depth of the reading user corresponding to each interactive book. Specifically, according to the interaction duration, number of interactions and / or interaction type of the reading user corresponding to each interactive book, the interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth are determined. Among them, the longer the interaction duration and the higher the interaction frequency, the deeper the interaction depth and the larger the corresponding interaction value; conversely, the shorter the interaction duration and the lower the interaction frequency, the lower the interaction depth and the smaller the corresponding interaction value. In addition, in addition to judging according to the interaction duration and interaction frequency, it can also be further combined with the interaction type, for example, different interaction weights are set in advance for various interaction types, and the interaction duration or interaction frequency is weighted by the interaction weight, so as to determine the interaction value according to the weighted result. For example, the interaction weights of the following interaction types decrease in descending order: paid interaction type, download type, add to bookshelf type, browse free chapter type, etc. The interactive books with higher user preference can be determined as the central books through the interaction value.

[0044] Finally, multiple reading users whose interaction values ​​corresponding to the central book are greater than a preset threshold are aggregated into a book user cluster corresponding to the central book. Specifically, for each central book, multiple reading users whose interaction values ​​corresponding to the central book are greater than a preset threshold are determined, so that the multiple reading users are aggregated into a book user cluster corresponding to the central book.

[0045] It can be seen that through this step, the central book can be used as an aggregation element to aggregate multiple reading users with a deep interaction depth with the central book into a book user cluster corresponding to the central book.

[0046] Optionally, when determining the central book, a list of interactive books corresponding to the interactive period of each reading user is obtained. The reading user is uniquely identified by a user identification (such as a user ID), and the interactive period is determined by a starting time point and an ending time point. The list of interactive books corresponding to the interactive period of the reading user can be determined based on the reading behavior information of the reading user during the interactive period. The interactive book list is used to store at least one e-book that the reading user has interacted with during the interactive period. Accordingly, the central book mentioned above is determined based on the interactive book lists of each reading user. The advantage of this method is that it can determine the books that the user incrementally interacts with during the interactive period in units of interactive periods, thereby mining the user's latest interest preferences.

[0047] In addition, considering that books are long-interaction business objects, users need to interact with a book continuously for many times, and it is impossible to determine the user's interest preference for the book based on the interaction situation in a short period of time (such as one day). Therefore, considering the long-interaction characteristics of books, for an interactive book, the interaction duration and interaction type of the interactive operations triggered by the user on the interactive book within a preset time are continuously monitored, and the user's interaction value for the interactive book is calculated based on the monitoring results.

[0048] Step S210: determining a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book.

[0049] Specifically, the current reading user to be recommended is used as the target user, and the book user cluster corresponding to the target user is determined, which is specifically determined according to the reading behavior data of the target user. The number of book user clusters corresponding to the target user can be one or more, depending on the number of books that the target user has deeply interacted with. In this embodiment, the number of book user clusters corresponding to the target user is multiple as an example for explanation.

[0050] Step S220: for the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool.

[0051] Among them, when there are multiple book user clusters corresponding to the target user, each book user cluster corresponds to a candidate book pool. Specifically, the candidate book pool corresponding to each book user cluster is determined in the following manner: the interactive books corresponding to each reading user in the book user cluster are obtained, and the candidate book pool corresponding to the book user cluster is determined according to the interactive books corresponding to each reading user. For example, for the book user cluster A1' corresponding to the book A1, each reading user in the book user cluster has interacted with the book A1, and the interaction value with the book A1 (determined by the interaction depth) is greater than a preset threshold (for example, 0.5). Assuming that the book user cluster A1' contains N reading users, N can be any natural number, wherein each of the N reading users has corresponding other interactive books, and the interactive books of each of the N reading users are summarized into the candidate book pool corresponding to the book user cluster A1'. It can be seen that the candidate book pool corresponds to the book user cluster one by one, and the number of books contained in each candidate book pool depends on the number of interactive books corresponding to each reading user in the corresponding book user cluster.

[0052] Since there are a large number of candidate books in the candidate book pool, in order to facilitate the determination of the attractiveness of each candidate book to each reading user in the book user cluster, it is necessary to calculate the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster. Among them, the cluster interest score is used to reflect the preference of all users in the book user cluster for a candidate book in the candidate book pool. Therefore, the cluster interest score of the candidate book corresponding to the book user cluster should be determined based on the interaction depth of all users in the book user cluster for the candidate book. In specific implementation, the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster is calculated according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool.

[0053] Specifically, when calculating the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool, the score is determined in the following manner: first, for any candidate book in the candidate book pool, the interaction value of each reading user corresponding to the candidate book is determined according to the interaction depth of each reading user in the book user cluster corresponding to the candidate book, and the sum of the interaction values ​​of each reading user in the book user cluster corresponding to the candidate book is calculated. Then, according to the sum of the interaction values ​​of the candidate book and the total number of reading users included in the book user cluster, the average interaction value of each reading user in the book user cluster corresponding to the candidate book is calculated, and the average interaction value is determined as the cluster interest score of the candidate book corresponding to the book user cluster.

[0054] It can be seen that the above method mainly determines the cluster interest score of the candidate book corresponding to the book user cluster by calculating the average interaction value of each reading user for the candidate book. For example, assuming that a certain book user cluster contains 10 reading users, for the candidate book 1 in the candidate book pool corresponding to the book user cluster, three reading users have read the candidate book 1, and the interaction values ​​of the three reading users for the candidate book 1 are 0.5, 0.8, and 0.2 respectively. Correspondingly, the interaction values ​​of the remaining reading users who have not read the candidate book 1 corresponding to the candidate book 1 are all 0. Therefore, the sum of the interaction values ​​of each reading user in the book user cluster corresponding to the candidate book 1 is 1.5, and the average interaction value of each reading user in the book user cluster corresponding to the candidate book 1 is 0.15. Therefore, the cluster interest score of the candidate book corresponding to the book user cluster is 0.15. It can be seen that the cluster interest score of the candidate book corresponding to the book user cluster can reflect the preference of most users in the book user cluster for the candidate book. In addition to calculating the average interaction value of each reading user corresponding to the candidate book 1, the cluster interest score can be further determined in combination with the maximum interaction value and / or minimum interaction value of each reading user corresponding to the candidate book 1. The present invention does not limit the specific calculation method of the cluster interest score, as long as it can reflect the preference of the majority of users in the book user cluster for the candidate book.

[0055] Step S230: Calculate the interest of the target user corresponding to each candidate book according to the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster.

[0056] In this embodiment, there are multiple book user clusters corresponding to the target user, and each book user cluster corresponds to a candidate book pool. Accordingly, when calculating the interest of the target user corresponding to each candidate book, for each book user cluster, according to the interaction depth of the target user corresponding to the central book of the book user cluster, the cluster interaction value of the target user corresponding to the book user cluster is determined; for the candidate book pool corresponding to each book user cluster, the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster is determined; according to the cluster interaction value of the target user corresponding to each book user cluster and the cluster interest score of each candidate book in each candidate book pool corresponding to the book user cluster to which it belongs, the interest of the target user corresponding to each candidate book is calculated.

[0057] Among them, the cluster interaction value of the target user corresponding to the book user cluster is used to reflect the target user's preference for the central book of the book user cluster. Specifically, the book user cluster corresponds to a central book, and the target user is added to the book user cluster because the target user has a deep interaction depth and a large interaction value for the central book. Therefore, the cluster interaction value of the target user corresponding to the book user cluster can be determined based on the target user's interaction depth with the central book of the book user cluster. In specific implementation, the interaction value of the target user corresponding to the central book of the book user cluster can be directly used as the cluster interaction value of the target user corresponding to the book user cluster to reflect the target user's interest in the central book.

[0058] In specific implementation, when calculating the interest of the target user corresponding to each candidate book according to the cluster interaction value of the target user corresponding to each book user cluster and the cluster interest score of each candidate book in each candidate book pool corresponding to the book user cluster to which it belongs, it is specifically implemented in the following way:

[0059] First, for any candidate book, determine the cluster interest scores of each book user cluster to which the candidate book belongs. A candidate book may belong to multiple book user clusters, depending on the reading history of the reading users in each book user cluster. Accordingly, when a candidate book corresponds to multiple book user clusters, determine the cluster interest scores of each book user cluster to which the candidate book belongs. The specific determination method can be referred to the above description and will not be repeated here.

[0060] Then, for each book user cluster to which the candidate book belongs, the interest score of the target user corresponding to the candidate book in the book user cluster is calculated according to the cluster interaction value of the target user corresponding to the book user cluster and the cluster interest score of the candidate book corresponding to the book user cluster. Specifically, for each book user cluster to which the candidate book belongs, the interest score of the target user corresponding to the candidate book in the book user cluster is calculated. The interest score is used to reflect the preference of the target user for the candidate book based on the current book user cluster. Therefore, the interest score of the candidate book corresponds to the book user cluster. When the candidate book belongs to multiple book user clusters at the same time, multiple interest scores corresponding to each book user cluster will be obtained for the candidate book. For each book user cluster, the interest score of the target user corresponding to the candidate book in the book user cluster mainly depends on the following two aspects of information: on the one hand, the interest score is related to the cluster interest score of the candidate book corresponding to the book user cluster; on the other hand, the interest score is related to the cluster interaction value of the target user corresponding to the book user cluster.

[0061] Finally, the interest degree of the target user corresponding to the candidate book is calculated according to the interest score of the target user corresponding to the candidate book in each book user cluster. Since there are multiple book user clusters, the interest score of the same candidate book is also multiple. When calculating the interest degree of the target user corresponding to the candidate book according to multiple interest scores, the total score or average score corresponding to the multiple interest scores can be directly determined as the interest degree of the target user corresponding to the candidate book.

[0062] For ease of understanding, a specific example is used below to describe in detail how to calculate the interest level of a target user corresponding to a candidate book.

[0063] Assume that the target user belongs to three book user clusters, namely C1, C2, and C3, and each book user cluster corresponds to a candidate book pool, namely C1', C2', and C3'. Assume that the book user cluster C1 contains the candidate book B, and the candidate book B also appears in the book user cluster C2. Therefore, the cluster interest score of the candidate book B corresponding to the book user cluster C1 (assuming it is 0.5) and the cluster interest score of the candidate book B corresponding to the book user cluster C2 (assuming it is 0.8) can be calculated respectively by the method mentioned in step S220. In addition, the cluster interaction value of the target user corresponding to the book user cluster C1 (assuming it is 0.2) can be determined based on the target user's interaction value for the central book of the book user cluster C1; the cluster interaction value of the target user corresponding to the book user cluster C2 (assuming it is 0.6) can be determined based on the target user's interaction value for the central book of the book user cluster C2. Accordingly, when calculating the interest score of the candidate book for each book user cluster to which the candidate book belongs, the interest score of the target user corresponding to the candidate book in the book user cluster is calculated based on the product of the cluster interaction value of the target user corresponding to the book user cluster and the cluster interest score of the candidate book corresponding to the book user cluster. For example, the interest score of the target user corresponding to the candidate book in the book user cluster C1 is 0.2*0.5=0.1, the interest score of the target user corresponding to the candidate book in the book user cluster C2 is 0.6*0.8=0.48, and the interest score of the target user corresponding to the candidate book in the book user cluster C3 is 0 (because the candidate book does not appear in the book user cluster C3). Accordingly, the interest of the target user corresponding to the candidate book is 0.1+0.48+0=0.58.

[0064] It can be seen that, in this embodiment, the interest level P(u) of the target user corresponding to the candidate book u can be calculated by the following formula:

[0065]

[0066] Among them, the target user belongs to n book user clusters in total, pi represents the cluster interaction value of the target user corresponding to the i-th book user cluster, and ui represents the cluster interest score of the candidate book u corresponding to the i-th book user cluster.

[0067] Step S240: Select several candidate books as target books according to the calculation results and push them to the target user.

[0068] Specifically, the candidate books are sorted in descending order of interest according to the calculation results, and a number of candidate books are selected as target books according to the sorting results and pushed to the target user.

[0069] In order to prevent repeated push, in this embodiment, the candidate book pools corresponding to the book user clusters to which the target user belongs may be preliminarily selected, and the books that the target user has not interacted with may be selected from the candidate book pools as candidate books.

[0070] In summary, this method aggregates similar users through book user clusters and recommends books based on the reading preferences of similar users, thereby ensuring that the recommended books not only match the reading preferences of the current user, but also broaden the reading range of the current user, allowing the user to read more valuable books. Moreover, when the target user belongs to multiple book user clusters at the same time, the interest of the candidate books is further determined in combination with the cluster interaction value of the target user for each book user cluster, so that the interest of the candidate books finally determined can be more accurate. This method can recommend books through user collaboration, thereby mining the potential interest points of the target user based on the interests of similar users.

[0071] Embodiment 3

[0072] An embodiment of the present application provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the electronic book push and book sort push method in any of the above method embodiments.

[0073] The executable instructions may be specifically used to cause the processor to perform the following operations:

[0074] Determine a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book;

[0075] For the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool;

[0076] According to the cluster interest scores of the candidate books in the candidate book pool corresponding to the book user cluster, the interest of the target user corresponding to each candidate book is calculated, and several candidate books are selected as target books according to the calculation results and pushed to the target user.

[0077] In an optional implementation, when there are multiple book user clusters corresponding to the target user, each book user cluster corresponds to a candidate book pool;

[0078] The executable instructions cause the processor to perform the following operations:

[0079] For each book user cluster, determine the cluster interaction value of the target user corresponding to the book user cluster according to the interaction depth of the target user corresponding to the central book of the book user cluster;

[0080] For each candidate book pool corresponding to each book user cluster, determine the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster;

[0081] The interest of the target user corresponding to each book user cluster is calculated according to the cluster interaction value of the target user corresponding to each book user cluster and the cluster interest score of each candidate book in each candidate book pool corresponding to the book user cluster to which it belongs.

[0082] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0083] For any candidate book, determine the cluster interest score of each book user cluster to which the candidate book belongs;

[0084] For each book user cluster to which the candidate book belongs, according to the cluster interaction value of the target user corresponding to the book user cluster and the cluster interest score of the candidate book corresponding to the book user cluster, calculate the interest score of the target user corresponding to the candidate book in the book user cluster;

[0085] The interest degree of the target user corresponding to the candidate book is calculated according to the interest score of the target user corresponding to the candidate book in each book user cluster.

[0086] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0087] For any candidate book in the candidate book pool, determine the interaction value of each reading user corresponding to the candidate book according to the interaction depth of each reading user in the book user cluster corresponding to the candidate book, and calculate the sum of the interaction values ​​of each reading user in the book user cluster corresponding to the candidate book;

[0088] According to the sum of the interaction values ​​of the candidate book and the total number of reading users included in the book user cluster, the average interaction value of each reading user in the book user cluster corresponding to the candidate book is calculated, and the average interaction value is determined as the cluster interest score of the candidate book corresponding to the book user cluster.

[0089] In an optional implementation, the executable instructions cause the processor to perform the following operations: obtain interactive books corresponding to each reading user in the book user cluster, and determine a candidate book pool corresponding to the book user cluster according to the interactive books corresponding to each reading user.

[0090] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0091] According to the calculation results, the candidate books are sorted in descending order of interest, and a number of candidate books are selected as target books according to the sorting results and pushed to the target user.

[0092] In an optional implementation, the executable instructions cause the processor to perform the following operations: adding each reading user to a book user cluster aggregated by a central book in advance based on the reading behavior data of each reading user.

[0093] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0094] Determine the interactive books corresponding to each reading user according to the reading behavior data of each reading user;

[0095] Determine the interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth, and determine the interactive book with an interaction value greater than a preset threshold as a core book;

[0096] A plurality of reading users whose interaction values ​​corresponding to the central book are greater than a preset threshold are aggregated into a book user cluster corresponding to the central book.

[0097] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0098] The interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth are determined according to the interaction duration, interaction number and / or interaction type of the reading user corresponding to each interactive book.

[0099] Embodiment 4

[0100] Figure 3 A schematic structural diagram of an electronic device according to another embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the electronic device.

[0101] like Figure 3 As shown, the electronic device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0102] The processor 302, the communication interface 304, and the memory 306 communicate with each other via the communication bus 308. The communication interface 304 is used to communicate with other devices such as a client or other server network elements. The processor 302 is used to execute the program 310, which can specifically execute the relevant steps in the above-mentioned electronic book push and book sorting push method embodiment.

[0103] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0104] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0105] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0106] The program 310 may be specifically configured to enable the processor 302 to perform the following operations:

[0107] Determine a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book;

[0108] For the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool;

[0109] According to the cluster interest scores of the candidate books in the candidate book pool corresponding to the book user cluster, the interest of the target user corresponding to each candidate book is calculated, and several candidate books are selected as target books according to the calculation results and pushed to the target user.

[0110] In an optional implementation, when there are multiple book user clusters corresponding to the target user, each book user cluster corresponds to a candidate book pool;

[0111] The executable instructions cause the processor to perform the following operations:

[0112] For each book user cluster, determine the cluster interaction value of the target user corresponding to the book user cluster according to the interaction depth of the target user corresponding to the central book of the book user cluster;

[0113] For each candidate book pool corresponding to each book user cluster, determine the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster;

[0114] The interest of the target user corresponding to each book user cluster is calculated according to the cluster interaction value of the target user corresponding to each book user cluster and the cluster interest score of each candidate book in each candidate book pool corresponding to the book user cluster to which it belongs.

[0115] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0116] For any candidate book, determine the cluster interest score of each book user cluster to which the candidate book belongs;

[0117] For each book user cluster to which the candidate book belongs, according to the cluster interaction value of the target user corresponding to the book user cluster and the cluster interest score of the candidate book corresponding to the book user cluster, calculate the interest score of the target user corresponding to the candidate book in the book user cluster;

[0118] The interest degree of the target user corresponding to the candidate book is calculated according to the interest score of the target user corresponding to the candidate book in each book user cluster.

[0119] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0120] For any candidate book in the candidate book pool, determine the interaction value of each reading user corresponding to the candidate book according to the interaction depth of each reading user in the book user cluster corresponding to the candidate book, and calculate the sum of the interaction values ​​of each reading user in the book user cluster corresponding to the candidate book;

[0121] According to the sum of the interaction values ​​of the candidate book and the total number of reading users included in the book user cluster, the average interaction value of each reading user in the book user cluster corresponding to the candidate book is calculated, and the average interaction value is determined as the cluster interest score of the candidate book corresponding to the book user cluster.

[0122] In an optional implementation, the executable instructions cause the processor to perform the following operations: obtain interactive books corresponding to each reading user in the book user cluster, and determine a candidate book pool corresponding to the book user cluster according to the interactive books corresponding to each reading user.

[0123] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0124] According to the calculation results, the candidate books are sorted in descending order of interest, and a number of candidate books are selected as target books according to the sorting results and pushed to the target user.

[0125] In an optional implementation, the executable instructions cause the processor to perform the following operations: adding each reading user to a book user cluster aggregated by a central book in advance based on the reading behavior data of each reading user.

[0126] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0127] Determine the interactive books corresponding to each reading user according to the reading behavior data of each reading user;

[0128] Determine the interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth, and determine the interactive book with an interaction value greater than a preset threshold as a core book;

[0129] A plurality of reading users whose interaction values ​​corresponding to the central book are greater than a preset threshold are aggregated into a book user cluster corresponding to the central book.

[0130] In an optional implementation, the executable instruction causes the processor to perform the following operations:

[0131] The interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth are determined according to the interaction duration, interaction number and / or interaction type of the reading user corresponding to each interactive book.

[0132] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0133] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0134] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0135] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0136] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0137] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A method for pushing an e-book, comprising: Determine a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book; For the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool; When there are multiple book user clusters corresponding to the target user, each book user cluster corresponds to a candidate book pool; for each book user cluster, the cluster interaction value of the target user corresponding to the book user cluster is determined according to the interaction depth of the target user with the central book of the book user cluster; for the candidate book pool corresponding to each book user cluster, the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster is determined; for each book user cluster to which the candidate book belongs, the interest score of the target user corresponding to the candidate book in the book user cluster is calculated according to the cluster interaction value of the target user corresponding to the book user cluster and the cluster interest score of the candidate book corresponding to the book user cluster; the interest of the target user corresponding to the candidate book is calculated according to the interest score of the target user corresponding to the candidate book in each book user cluster, and a number of candidate books are selected as target books according to the calculation results and pushed to the target user.

2. The method according to claim 1, wherein: The step of calculating the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool comprises: For any candidate book in the candidate book pool, determine the interaction value of each reading user corresponding to the candidate book according to the interaction depth of each reading user in the book user cluster corresponding to the candidate book, and calculate the sum of the interaction values ​​of each reading user in the book user cluster corresponding to the candidate book; According to the sum of the interaction values ​​of the candidate book and the total number of reading users included in the book user cluster, the average interaction value of each reading user in the book user cluster corresponding to the candidate book is calculated, and the average interaction value is determined as the cluster interest score of the candidate book corresponding to the book user cluster.

3. The method according to any one of claims 1-2, wherein: The determining of the candidate book pool corresponding to the book user cluster includes: acquiring interactive books corresponding to each reading user in the book user cluster, and determining the candidate book pool corresponding to the book user cluster according to the interactive books corresponding to each reading user.

4. The method according to any one of claims 1-2, wherein: The selecting a number of candidate books as target books according to the calculation results and pushing them to the target user comprises: According to the calculation results, the candidate books are sorted in descending order of interest, and a number of candidate books are selected as target books according to the sorting results and pushed to the target user.

5. The method according to any one of claims 1-2, wherein: Before the method is executed, it further includes: adding each reading user to a book user cluster aggregated by a central book in advance according to the reading behavior data of each reading user.

6. The method according to claim 5, wherein: The step of adding each reading user to the book user cluster aggregated by the central book according to the reading behavior data of each reading user in advance includes: Determine the interactive books corresponding to each reading user according to the reading behavior data of each reading user; Determine the interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth, and determine the interactive book with an interaction value greater than a preset threshold as a core book; A plurality of reading users whose interaction values ​​corresponding to the central book are greater than a preset threshold are aggregated into a book user cluster corresponding to the central book.

7. The method according to claim 6, wherein: The step of determining the interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth comprises: The interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth are determined according to the interaction duration, interaction number and / or interaction type of the reading user corresponding to each interactive book.

8. An electronic device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations: Determine a book user cluster corresponding to the target user; wherein the book user cluster corresponds to a central book and is used to aggregate multiple reading users who have interactive behaviors with the central book; For the book user cluster corresponding to the target user, determine a candidate book pool corresponding to the book user cluster, and calculate a cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster according to the interaction depth of each reading user in the book user cluster corresponding to each candidate book in the candidate book pool; When there are multiple book user clusters corresponding to the target user, each book user cluster corresponds to a candidate book pool; for each book user cluster, the cluster interaction value of the target user corresponding to the book user cluster is determined according to the interaction depth of the target user with the central book of the book user cluster; for the candidate book pool corresponding to each book user cluster, the cluster interest score of each candidate book in the candidate book pool corresponding to the book user cluster is determined; for each book user cluster to which the candidate book belongs, the interest score of the target user corresponding to the candidate book in the book user cluster is calculated according to the cluster interaction value of the target user corresponding to the book user cluster and the cluster interest score of the candidate book corresponding to the book user cluster; the interest of the target user corresponding to the candidate book is calculated according to the interest score of the target user corresponding to the candidate book in each book user cluster, and a number of candidate books are selected as target books according to the calculation results and pushed to the target user.

9. The electronic device according to claim 8, wherein: The executable instructions cause the processor to perform the following operations: For any candidate book in the candidate book pool, determine the interaction value of each reading user corresponding to the candidate book according to the interaction depth of each reading user in the book user cluster corresponding to the candidate book, and calculate the sum of the interaction values ​​of each reading user in the book user cluster corresponding to the candidate book; According to the sum of the interaction values ​​of the candidate book and the total number of reading users included in the book user cluster, the average interaction value of each reading user in the book user cluster corresponding to the candidate book is calculated, and the average interaction value is determined as the cluster interest score of the candidate book corresponding to the book user cluster.

10. The electronic device according to any one of claims 8 to 9, wherein: The executable instructions enable the processor to perform the following operations: obtaining interactive books corresponding to each reading user in the book user cluster, and determining a candidate book pool corresponding to the book user cluster according to the interactive books corresponding to each reading user.

11. The electronic device according to any one of claims 8 to 9, wherein: The executable instructions cause the processor to perform the following operations: According to the calculation results, the candidate books are sorted in descending order of interest, and a number of candidate books are selected as target books according to the sorting results and pushed to the target user.

12. The electronic device according to any one of claims 8 to 9, wherein: The executable instructions enable the processor to perform the following operations: adding each reading user to a book user cluster aggregated by a central book in advance according to the reading behavior data of each reading user.

13. The electronic device according to claim 12, wherein: The executable instructions cause the processor to perform the following operations: Determine the interactive books corresponding to each reading user according to the reading behavior data of each reading user; Determine the interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth, and determine the interactive book with an interaction value greater than a preset threshold as a core book; A plurality of reading users whose interaction values ​​corresponding to the central book are greater than a preset threshold are aggregated into a book user cluster corresponding to the central book.

14. The electronic device according to claim 13, wherein: The executable instructions cause the processor to perform the following operations: The interaction depth of the reading user corresponding to each interactive book and the interaction value corresponding to the interaction depth are determined according to the interaction duration, interaction number and / or interaction type of the reading user corresponding to each interactive book.

15. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute the method according to any one of claims 1 to 7.

Images