Book traffic distribution method and device, electronic equipment and storage medium

The book traffic distribution method addresses the issue of inaccurate user-based content pushing by using user and book data to set scoring thresholds and weights, enhancing traffic utilization and user engagement.

CN119066264APending Publication Date: 2024-12-03WUTONG ZHONGWENWANG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411068496.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing book distribution methods fail to accurately push content based on user preferences, leading to disinterest among users and inefficient resource utilization.

Method used

A book traffic distribution method that determines a user's interest in a target book using user information, book classification, and exposure scene, and sets scoring thresholds and weights based on historical data to decide whether to push the book, ensuring refined traffic allocation.

Benefits of technology

This method enhances the accuracy of book distribution, improving overall traffic utilization and avoiding resource waste by ensuring that books reach more interested users.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066264A_ABST
    Figure CN119066264A_ABST
Patent Text Reader

Abstract

The invention provides a book traffic distribution method and device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps of determining a current score of a target book according to acquired user information, book information and exposure scene information, and determining a score threshold value according to a historical score corresponding to each exposure of each book under a target classification in a target time slice of a previous time period under a target scene; determining a score weight according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scene and the actual exposure times of each book under the target classification in each time slice of the previous time period in the target scene, whether to push to the user is judged by combining the current score, the score weight and the score threshold value of the book, so that refined flow distribution is realized, the book is ensured to accurately reach more valuable flow, the overall flow utilization rate is improved, and the waste of exposure resources is effectively avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a book flow distribution method, device, electronic device and storage medium. Background Art

[0002] With the continuous development of online reading, the output and stock of e-books are increasing, which puts higher requirements on the push of books.

[0003] The traditional way of pushing books is to select some or all users at a fixed position on the page and import a large amount of traffic to ensure the reading volume of the book. However, different users have different interests in books. This method cannot accurately push books based on the preferences of each user, resulting in some users not being interested in the pushed content, resulting in a waste of exposure resources and low overall traffic utilization. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a book traffic distribution method, device, electronic device and storage medium to solve the problem in the prior art that it is impossible to accurately push content according to the preferences of each user, resulting in some users not being interested in the pushed content, thereby causing a waste of exposure resources and low overall traffic utilization.

[0005] In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows:

[0006] In a first aspect, the present invention provides a book flow distribution method, the method comprising:

[0007] When entering a current time slice of a current time period, determining a current score of the target book according to the acquired user information, book information of the target book, and exposure scene information; the current score represents the user's interest in the target book, the book information includes a target classification, and the exposure scene information includes a target scene;

[0008] Determine a score threshold corresponding to the target book in the current time slice according to the historical scores corresponding to each exposure of each book under the target category in the target scene in the target time slice of the previous time period; the target time slice corresponds to the current time slice;

[0009] Determine the score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario;

[0010] It is determined whether to push the target book to the user in the current time slice according to the score weight corresponding to the target book in the current time slice, the current score, and the score threshold.

[0011] In an optional implementation manner, determining the score threshold corresponding to the target book in the current time slice according to the historical score corresponding to each exposure of each book under the target classification in the target time slice of the previous time period under the target scene includes:

[0012] Determine a first reference score based on the historical scores corresponding to each exposure of each book under the target category within the target time slice under the target scene; the first reference score is the average of the historical scores corresponding to each book under the target category or a value at a preset quantile after sorting the historical scores corresponding to each book under the target category;

[0013] Determine a second reference score according to the historical score corresponding to each exposure of the target book in the target time slice under the target scene; the second reference score is the average of the historical scores corresponding to the target book or a value at a preset quantile after sorting the historical scores corresponding to the target book;

[0014] The score threshold corresponding to the target book in the current time slice is calculated according to the first reference score and the second reference score.

[0015] In an optional implementation manner, calculating the score threshold corresponding to the target book in the current time slice according to the first reference score and the second reference score includes:

[0016] Calculating a score difference between the second reference score and the first reference score;

[0017] The product of the score difference and the preset score coefficient is added to the first reference score to obtain the score threshold corresponding to the target book in the current time slice.

[0018] In an optional implementation manner, determining the score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario includes:

[0019] Determine, according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scene, the actual cumulative exposure times of the target book in the target scene up to the first time slice of the current time period; the first time slice is the time slice before the current time slice;

[0020] Determine, according to the actual exposure times of each book under the target category in each time slice of the previous time period in the target scene, the estimated exposure times of the target book in the current time slice in the target scene, the estimated exposure times in the first time slice, the estimated exposure times in the second time slice, and the estimated cumulative exposure times up to the first time slice; the second time slice is the previous time slice of the first time slice;

[0021] Calculate the exposure compensation value of the target book in the current time slice in the target scene according to the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene, the estimated exposure times and the actual exposure times of the target book in the second time slice in the target scene, and the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice;

[0022] Obtaining an intermediate weight according to the exposure compensation value, the estimated exposure times of the target book in the current time slice in the target scene, the actual exposure times of the target book in the first time slice in the target scene, and the score weight corresponding to the target book in the first time slice;

[0023] The minimum value between the intermediate weight and the preset maximum weight is determined as the scoring weight corresponding to the target book in the current time slice.

[0024] In an optional implementation manner, determining the estimated exposure times of the target book in the current time slice in the target scene, the estimated exposure times in the first time slice, the estimated exposure times in the second time slice, and the estimated cumulative exposure times up to the first time slice according to the actual exposure times of each book under the target classification in each time slice of the previous time period in the target scene includes:

[0025] Calculate the actual total exposure times of each book under the target category in the previous time period under the target scene according to the actual exposure times of each book under the target category in each time slice of the previous time period under the target scene;

[0026] Calculate the average number of exposures for each book based on the actual total number of exposures and the total number of books under the target category;

[0027] Determine the estimated exposure times of the target book in the current time period in the target scenario according to the average exposure times of each book and the actual exposure times of the target book in the previous time period in the target scenario;

[0028] Determine the estimated exposure times of the target book in the current time slice in the target scene according to the estimated exposure times of the target book in the current time period in the target scene, and the ratio between the actual exposure times of each book in the target category in the target time slice in the target scene and the actual total exposure times;

[0029] Determine the estimated exposure times of the target book in the first time slice in the target scene according to the estimated exposure times of the target book in the current time period in the target scene, the actual exposure times of each book under the target category in the first target time slice in the previous time period in the target scene, and the ratio of the actual total exposure times; the first target time slice corresponds to the first time slice;

[0030] Determine the estimated exposure times of the target book in the second time slice in the target scene according to the estimated exposure times of the target book in the current time period in the target scene, the actual exposure times of each book under the target category in the second target time slice of the previous time period in the target scene, and the ratio of the actual total exposure times; the second target time slice corresponds to the second time slice;

[0031] The estimated cumulative exposure number of the target book in the target scenario up to the first time slice is determined according to the estimated exposure number of the target book in the current time period in the target scenario and the ratio between the actual cumulative exposure number of each book under the target category in the target scenario up to the first target time slice and the actual total exposure number.

[0032] In an optional implementation manner, calculating the exposure compensation value of the target book in the current time slice in the target scene according to the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene, the estimated exposure times and the actual exposure times of the target book in the second time slice in the target scene, and the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice includes:

[0033] Calculating a first error according to the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene;

[0034] Calculating a second error according to the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice;

[0035] Calculate a third error according to the actual exposure times of the target book in the first time slice in the target scene, the actual exposure times of the target book in the second time slice in the target scene, the estimated exposure times of the target book in the first time slice in the target scene, and the estimated exposure times of the target book in the second time slice in the target scene;

[0036] The product of the first error and the first preset control coefficient, the product of the second error and the second preset control coefficient, and the product of the third error and the third preset control coefficient are added together to obtain the exposure compensation value of the target book in the current time slice in the target scene.

[0037] In an optional implementation manner, determining whether to push the target book to the user in the current time slice according to the score weight corresponding to the target book in the current time slice, the current score, and the score threshold, includes:

[0038] When the product of the score weight corresponding to the target book in the current time slice and the current score is greater than or equal to the score threshold, determine to push the target book to the user in the current time slice;

[0039] When the product of the score weight corresponding to the target book in the current time slice and the current score is less than the score threshold, it is determined not to push the target book to the user in the current time slice.

[0040] In a second aspect, the present invention provides a book flow distribution device, the device comprising:

[0041] A scoring module is used to determine the current score of the target book according to the acquired user information, the book information of the target book and the exposure scene information when entering the current time slice of the current time period; the current score represents the user's interest in the target book, the book information includes the target classification, and the exposure scene information includes the target scene;

[0042] A threshold determination module, configured to determine a score threshold corresponding to the target book in the current time slice according to the historical scores corresponding to each exposure of each book under the target classification in the target time slice of the previous time period under the target scene; the target time slice corresponds to the current time slice;

[0043] A weight determination module, configured to determine a score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario;

[0044] The traffic distribution module is used to determine whether to push the target book to the user in the current time slice according to the score weight corresponding to the target book in the current time slice, the current score and the score threshold.

[0045] In a third aspect, the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of book flow distribution as described in any one of the aforementioned embodiments are implemented.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of book flow distribution as described in any one of the aforementioned embodiments.

[0047] The book flow distribution method, device, electronic device and storage medium provided by the embodiment of the present invention determine the current score of the target book according to the acquired user information, the book information of the target book and the exposure scene information when entering the current time slice of the current time period; the current score represents the user's interest in the target book, the book information includes the target classification, and the exposure scene information includes the target scene; the score threshold corresponding to the target book in the current time slice is determined according to the historical scores corresponding to each exposure of each book under the target classification in the target time slice of the previous time period under the target scene; the target time slice corresponds to the current time slice; the score weight corresponding to the target book in the current time slice is determined according to the actual number of exposures of the target book in each time slice before the current time slice in the current time period under the target scene, and the actual number of exposures of each book under the target classification in each time slice of the previous time period under the target scene; and whether to push the target book to the user in the current time slice is determined according to the score weight corresponding to the target book in the current time slice, the current score and the score threshold. The embodiment of the present invention determines the user's interest in the book based on user information, book information and exposure scenario information, and determines the scoring threshold and scoring weight based on the historical exposure of the book. Finally, the current score, scoring weight and scoring threshold of the book are combined to determine whether to push the book to the user, thereby realizing refined traffic allocation, ensuring that the book can accurately reach more valuable traffic, improving the overall traffic utilization rate, and effectively avoiding the waste of exposure resources.

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A schematic diagram of a flow chart of a book flow distribution method provided by an embodiment of the present invention is shown;

[0051] Figure 2 Another schematic diagram of a flow chart of a book flow distribution method provided by an embodiment of the present invention is shown;

[0052] Figure 3 Another schematic diagram of a flow chart of a method for distributing book flow provided by an embodiment of the present invention is shown;

[0053] Figure 4A functional module diagram of a book flow distribution device provided by an embodiment of the present invention is shown;

[0054] Figure 5 A structural block diagram of an electronic device provided by an embodiment of the present invention is shown.

[0055] Icons: 100 - electronic device; 110 - memory; 120 - processor; 130 - communication module; 600 - book flow distribution device; 610 - scoring module; 620 - threshold determination module; 630 - weight determination module; 640 - flow distribution module. DETAILED DESCRIPTION

[0056] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0057] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0058] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0059] In view of the problem that the existing book push method cannot accurately push books according to the preferences of each user, resulting in some users not being interested in the pushed content, thereby causing a waste of exposure resources and low overall traffic utilization, the embodiments of the present invention propose a book traffic distribution method, device, electronic device and storage medium, which determine the user's interest in the book according to user information, book information and exposure scene information, and determine the scoring threshold and scoring weight based on the historical exposure of the book, and finally determine whether to push the book to the user based on the current score, scoring weight and scoring threshold of the book, thereby realizing refined traffic distribution, ensuring that the book can accurately reach more valuable traffic, improving the overall traffic utilization, and effectively avoiding the waste of exposure resources.

[0060] Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0061] Please refer to Figure 1 , is a flow chart of a method for distributing book traffic provided by an embodiment of the present invention. It should be noted that the method for distributing book traffic provided by an embodiment of the present invention is not based on Figure 1 The specific order below is a limitation. It should be understood that in other embodiments, the order of some steps in the book traffic distribution method of the embodiment of the present invention can be interchanged according to actual needs, or some steps can be omitted or deleted. The book traffic distribution method can be applied to electronic devices such as smart phones, tablet computers, personal computers (personal computers, PCs), mobile Internet devices (mobile Internet devices, MIDs), personal digital assistants (personal digital assistants, PDAs), and e-book readers. The following will describe the book traffic distribution method in detail. Figure 1 The specific process shown is described in detail.

[0062] Step S101, when entering the current time slice of the current time period, determine the current score of the target book according to the acquired user information, the book information of the target book and the exposure scene information; the current score represents the user's interest in the target book, the book information includes the target classification, and the exposure scene information includes the target scene.

[0063] In this embodiment, the time period and time slice can be set according to actual needs, for example, one day, one week, or one month is a time period, and one hour, five minutes, or ten minutes is a time slice. Assuming that one time period is one day and one time slice is one hour, each time period can be divided into 24 time slices, and the current time slice of the current time period can be understood as a specific time slice of the day, such as 0 to 1 o'clock, 1 to 2 o'clock, etc. of the day.

[0064] An electronic device may be installed with an application program related to book reading. When entering the current time slice of the current time period, user information, book information, and exposure scene information may be obtained from the data system according to the user ID currently accessing the application program and the book ID of the target book. The user information may include information such as the user's age, gender, and region; the book information may include information such as the title, author, and category (target category) of the target book, which may be a secondary category, a tertiary category, and the like, such as fantasy, suspense, and the like; the exposure scene information may include information such as the current time, the exposure scene (target scene), and the like, wherein the exposure scene may be understood as the exposure location, such as a recommendation list, a completion list, and the like. The obtained user information, book information, and exposure scene information may be passed to a preset scoring service (model / rule), and the current score of the target book may be obtained, and the current score may represent the user's interest in the target book when the target book is exposed in the current time slice and the target scene.

[0065] Step S102, determining a score threshold corresponding to the target book in the current time slice according to the historical scores corresponding to each exposure of each book under the target category in the target scene in the target time slice of the previous time period; the target time slice corresponds to the current time slice.

[0066] In this embodiment, each book will be scored by the above-mentioned scoring service before each exposure. Assuming that the target book belongs to the suspense category, the target scene is the recommendation list, a time period is one day, a time slice is one hour, and the current time slice is 1 to 2 o'clock, then the scores (historical scores) corresponding to each exposure of each book of the suspense category under the recommendation list in the time slice of 1 to 2 o'clock of the previous day can be obtained. Based on these historical scores, the score threshold corresponding to the time slice of 1 to 2 o'clock of the current day is determined, and the score threshold is used for subsequent judgment on whether the target book is exposed to the user.

[0067] Step S103, determining the score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario.

[0068] In this embodiment, the scoring weight can be determined based on the historical exposure of the target book and the historical exposure of each book in the category to which the target book belongs. Still taking the case that the target book belongs to the suspense category, the target scene is the recommendation list, a time period is one day, and a time slice is one hour as an example, assuming that the current time slice is 3 to 4 o'clock, then the historical exposure of the target book can include the actual exposure times of the target book in the three time slices of 0 to 1 o'clock, 1 to 2 o'clock, and 2 to 3 o'clock on the same day under the recommendation list; the historical exposure times of each book in the category to which the target book belongs can include the actual exposure times of each book in the suspense category under the recommendation list in each time slice of the previous day.

[0069] Step S104: determining whether to push the target book to the user in the current time slice according to the score weight, current score and score threshold corresponding to the target book in the current time slice.

[0070] In this embodiment, the current score can be weighted calculated according to the score weight, and the weighted calculation result can be compared with the score threshold. According to the comparison result, it can be determined whether the target book needs to be exposed in the current time slice, that is, whether it should be pushed to the user.

[0071] It can be seen that the book traffic distribution method provided by the embodiment of the present invention determines the current score of the target book according to the acquired user information, the book information of the target book and the exposure scene information when entering the current time slice of the current time period; the current score represents the user's interest in the target book, the book information includes the target classification, and the exposure scene information includes the target scene; the score threshold corresponding to the target book in the current time slice is determined according to the historical scores corresponding to each exposure of each book under the target classification in the target time slice of the previous time period under the target scene; the target time slice corresponds to the current time slice; the score weight corresponding to the target book in the current time slice is determined according to the actual number of exposures of the target book in each time slice before the current time slice in the current time period under the target scene, and the actual number of exposures of each book under the target classification in each time slice of the previous time period under the target scene; and whether to push the target book to the user in the current time slice is determined according to the score weight corresponding to the target book in the current time slice, the current score and the score threshold. The embodiment of the present invention determines the user's interest in the book based on user information, book information and exposure scenario information, and determines the scoring threshold and scoring weight based on the historical exposure of the book. Finally, the current score, scoring weight and scoring threshold of the book are combined to determine whether to push the book to the user, thereby realizing refined traffic allocation, ensuring that the book can accurately reach more valuable traffic, improving the overall traffic utilization rate, and effectively avoiding the waste of exposure resources.

[0072] In one embodiment, step S104 includes: when the product of the score weight corresponding to the target book in the current time slice and the current score is greater than or equal to the score threshold, determining to push the target book to the user in the current time slice; when the product of the score weight corresponding to the target book in the current time slice and the current score is less than the score threshold, determining not to push the target book to the user in the current time slice.

[0073] For example, the current time slice is N+1, and the score weight of the target book in the current time slice is W. N+1 , the current rating of the target book is p ctcvr , the score threshold corresponding to the target book in the current time slice is P N+1 , then when W N+1 *p ctcvr ≥P N+1 When , it is determined that the target book is normally mixed with other books in the algorithm queue, that is, the target book is exposed to the user; when W N+1 *p ctcvr <P N+1 When the target book is filtered, the target book is not exposed to the user.

[0074] In one embodiment, see Figure 2 , the above step S102 may include:

[0075] Sub-step S1021, determining a first reference score based on the historical scores corresponding to each exposure of each book under the target category within the target scene and the target time slice; the first reference score is the average of the historical scores corresponding to each book under the target category or the value at a preset percentile after sorting the historical scores corresponding to each book under the target category.

[0076] In this embodiment, by calculating the average of the historical scores corresponding to each exposure in each time slice k of each book under the target category in the target scene in the previous time period, or sorting and obtaining the value at the preset quantile, the first reference score corresponding to each time slice k in the previous time period can be obtained. Since the first reference score is determined by calculating the mean or presetting the quantile, the first reference score can reflect the average popularity of books in the target category in the target scenario and within the target time slice, or the distribution of book scores.

[0077] Assume that the target book belongs to the suspense category, the target scene is the recommendation list, a time period is one day, a time slice is one hour, and the current time slice is 1 to 2 o'clock. Then the target time slice is 1 to 2 o'clock of the previous day (the second time slice of the previous day, k = 2). The books in the suspense category under the recommendation list have a total of 50 exposures in the time slice of 1 to 2 o'clock of the previous day. The historical scores corresponding to the 50 exposures are added up and then divided by 50. The average score of the suspense category books on the recommendation list in the second time slice of the previous day can be obtained. The average score is used as the first reference score. The historical scores corresponding to the 50 exposures may also be sorted, and the historical scores at a preset quantile (such as 50%) are determined as the first reference scores.

[0078] Sub-step S1022, determining a second reference score according to the historical score corresponding to each exposure of the target book in the target scene and the target time slice; the second reference score is the mean of the historical scores corresponding to the target books or a value at a preset quantile after sorting the historical scores corresponding to the target books.

[0079] For example, if target book i has 10 exposures in the second time slot of the previous day, the historical scores corresponding to the 10 exposures are added up and then divided by 10 to get the average score of target book i in the second time slot of the previous day. This average score is used as the second reference score. The historical scores corresponding to the 10 exposures may also be sorted, and the historical scores at a preset quantile (such as 50%) are determined as the second reference scores. Therefore, the second reference score can reflect the average popularity of the target book in the target time slice in the target scenario or the distribution of book scores.

[0080] Sub-step S1023, calculating the score threshold corresponding to the target book in the current time slice according to the first reference score and the second reference score.

[0081] In this embodiment, since the first reference score can reflect the average popularity of books under the target category in the target scenario within the target time slice or the distribution of book ratings, the second reference score can reflect the average popularity of the target book in the target scenario within the target time slice or the distribution of book ratings, the score threshold of the target book in the current time slice is estimated based on the first reference score and the second reference score for subsequent judgment on whether the target book is exposed to the user.

[0082] Specifically, sub-step S1023 may include: calculating the score difference between the second reference score and the first reference score; adding the product of the score difference and a preset score coefficient to the first reference score to obtain a score threshold corresponding to the target book in the current time slice.

[0083] The preset scoring coefficient can be set for different books. For example, the preset scoring coefficient corresponding to the target book i can be set to β i , the score threshold corresponding to the target book in the current time slice k If the current time slice is the 2nd (k=2) time slice of the day, the score threshold corresponding to the second time slice of the target book can be expressed as

[0084] In one embodiment, see Figure 3 , the above step S103 may include:

[0085] Sub-step S1031, determining the actual cumulative exposure times of the target book in the target scene up to the first time slice of the current time period according to the actual exposure times of the target book in each time slice before the current time slice in the current time period under the target scene; the first time slice is the time slice before the current time slice.

[0086] Assume S k is the actual exposure times of the target book in the kth time slice of the current time period in the target scenario. When the current time slice is the N+1th time slice of the current time period, the first time slice is the Nth time slice of the current time period. The actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario are S1, S2, …, S N , then the actual cumulative exposure times of the target book in the target scenario up to the first time slice of the current time period can be expressed as

[0087] Sub-step S1032, based on the actual exposure times of each book under the target category in each time slice of the previous time period in the target scene, determine the estimated exposure times of the target book in the current time slice in the target scene, the estimated exposure times in the first time slice, the estimated exposure times in the second time slice, and the estimated cumulative exposure times up to the first time slice; the second time slice is the previous time slice of the first time slice.

[0088] In this embodiment, by counting the actual exposure times of each book under the target classification in each time slice of the previous time period in the target scene, the estimated exposure times of the target book in the current time slice in the target scene, the estimated exposure times in the first time slice, the estimated exposure times in the second time slice and the estimated cumulative exposure times up to the first time slice can be estimated.

[0089] In one embodiment, sub-step S1032 specifically includes: calculating the actual total exposure times of each book under the target classification in the previous time period under the target scene according to the actual exposure times of each book under the target classification in each time slice of the previous time period under the target scene; calculating the average exposure times of each book according to the actual total exposure times and the total number of books under the target classification; determining the estimated exposure times of the target book in the current time period under the target scene according to the average exposure times of each book and the actual exposure times of the target book in the previous time period under the target scene; determining the estimated exposure times of the target book in the current time slice under the target scene according to the ratio between the estimated exposure times of the target book in the current time period under the target scene, the actual exposure times of each book under the target classification in the target time slice under the target scene, and the actual total exposure times; determining the estimated exposure times of the target book in the current time slice under the target scene according to the estimated exposure times of the target book in the current time period under the target scene, the target classification, and the actual exposure times of each book under the target classification. The estimated exposure number of the target book in the first time slice in the target scene is determined by the ratio of the actual exposure number of each book in the target category in the first target time slice of the previous time period in the target scene to the actual total exposure number; the first target time slice corresponds to the first time slice; the estimated exposure number of the target book in the second time slice in the target scene is determined according to the estimated exposure number of the target book in the current time period in the target scene and the ratio of the actual exposure number of each book in the target category in the second target time slice of the previous time period in the target scene to the actual total exposure number; the second target time slice corresponds to the second time slice; the estimated cumulative exposure number of the target book in the target scene up to the first time slice is determined according to the estimated exposure number of the target book in the current time period in the target scene and the ratio of the actual cumulative exposure number of each book in the target category in the target scene up to the first target time slice to the actual total exposure number.

[0090] It can be understood that by adding up the actual exposure times of each book in the target category in each time slice of the previous time period in the target scenario, the actual total exposure times of each book in the target category in the previous time period in the target scenario can be obtained, and the actual total exposure times are divided by the total number of books in the target category to obtain the average exposure times of each book. For example, by adding up the actual exposure times of the suspense category books in the recommendation list in 24 time slices of the previous day, the total exposure times obtained is 1000 times, and the total number of suspense category books is 100 books, then the average exposure times of each book is 1000 / 100=10 times / book.

[0091] By counting the actual exposure times of the target book i in the previous time period in the target scene, and combining it with the calculated average exposure times of each book, the exposure times of the target book i in the current time period in the target scene can be estimated. For example, the average exposure times of each book in the target category in the previous day (previous time period) in the target scene is s. c , the actual exposure times s of the target book i in the target scenario in the previous day i , we can determine the estimated exposure times s′ of the target book i in the target scenario on that day (current time period) i =s c +α i *(s i -s c ), α i A constant set for different books i.

[0092] In this embodiment, according to the actual exposure times and the actual cumulative exposure times of each book under the target category in each time slice of the previous time period in the target scene, the exposure distribution of each book under the target category in each time slice of the previous time period in the target scene can be statistically obtained, mainly including the time slice proportion and the cumulative proportion. Then, combined with the estimated exposure times of the target book in the current time period in the target scene, the traffic distribution of the target book in the current time period in the target scene can be obtained, mainly including the estimated exposure times E of each time slice k of the target book in the current time period in the target scene. k and the estimated cumulative exposure times A up to this time period k .

[0093] For example, the current time slice is the N+1th time slice of the current time period, the first time slice is the Nth time slice of the current time period, and the second time slice is the N-1th time slice of the current time period. Then the target time slice is the N+1th time slice of the previous time period, the first target time slice is the Nth time slice of the previous time period, and the second target time slice is the N-1th time slice of the previous time period. The estimated number of exposures of target book i in the current time period in the target scene is s′ i The ratio of the actual exposure times of each book in the target category in the target scene in the target time slice to the actual total exposure times (time slice ratio) is B N+1 The ratio of the actual exposure times of each book under the target category in the first target time slice of the previous time period under the target scenario to the actual total exposure times (time slice ratio) is B N The ratio of the actual exposure times of each book under the target category in the second target time slice of the previous time period under the target scenario to the actual total exposure times (time slice ratio) is B N-1 The ratio (cumulative proportion) between the actual cumulative exposure times of each book in the target category up to the first target time slice in the target scenario and the actual total exposure times is C N , then the estimated exposure times of the target book in the current time slice in the target scenario is E N+1 =s′ i ×B N+1 , the estimated exposure times of the target book in the first time slice in the target scenario E N =s′ i ×B N , the estimated exposure times E of the target book in the second time slice in the target scene N-1 =s i 1×B N-1 , the estimated cumulative exposure times A of the target book in the target scenario up to the first time slice N =s i ′×C N .

[0094] Below, the calculation method of time slice proportion and cumulative proportion is explained by example. Assuming that the total exposure times of suspense books in the recommendation list the day before is 1,000 times, of which the actual exposure times in the time slice of 0-1 o'clock is 200, the actual exposure times in the time slice of 1-2 o'clock is 100, and the actual exposure times in the time slice of 2-3 o'clock is 50, then the ratio between the actual exposure times in the time slice of 0-1 o'clock and the actual total exposure times is 0.2, and the cumulative proportion is 0.2; the ratio between the actual exposure times in the time slice of 1-2 o'clock and the actual total exposure times is 0.1, and the cumulative proportion is 0.3; the ratio between the actual exposure times in the time slice of 2-3 o'clock and the actual total exposure times is 0.05, and the cumulative proportion is 0.35.

[0095] Sub-step S1033, calculates the exposure compensation value of the target book in the current time slice in the target scene based on the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene, the estimated exposure times and the actual exposure times of the target book in the second time slice in the target scene, and the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice.

[0096] In this embodiment, the exposure compensation value indicates the exposure that needs to be compensated in the current time slice, which may be negative. The exposure that needs to be compensated in the current time slice is obtained by combining the actual exposure conditions and the estimated exposure conditions of the first time slice and the second time slice.

[0097] In one embodiment, sub-step S1033 may specifically include: calculating a first error based on an estimated exposure number and an actual exposure number of the target book in a first time slice in a target scene; calculating a second error based on an estimated cumulative exposure number and an actual cumulative exposure number of the target book in the target scene up to the first time slice; calculating a third error based on an actual exposure number of the target book in the first time slice in the target scene, an actual exposure number of the target book in the second time slice in the target scene, an estimated exposure number of the target book in the first time slice in the target scene, and an estimated exposure number of the target book in the second time slice in the target scene; adding the product of the first error and a first preset control coefficient, the product of the second error and the second preset control coefficient, and the product of the third error and the third preset control coefficient to obtain an exposure compensation value of the target book in the current time slice in the target scene.

[0098] Assuming that the current time slice is the N+1th time slice of the current time period, the exposure compensation value R of the target book in the current time slice under the target scene is N+1 It can be expressed as K p , K l , KD represent the first preset control coefficient, the second preset control coefficient and the third preset control coefficient respectively; E N , S N They represent the estimated exposure times and actual exposure times of the target book in the first time slice in the target scenario, respectively. (E N -S N ) represents the first error; A N , They represent the estimated cumulative exposure times and actual cumulative exposure times of the target book in the target scenario up to the first time slice, respectively. Represents the second error; E N-1 , S N-1 They represent the estimated exposure times and actual exposure times of the target book in the second time slice in the target scenario, respectively. (E N -E N-1 +S N-1 -S N ) represents the third error.

[0099] Sub-step S1034, obtaining an intermediate weight according to the exposure compensation value, the estimated exposure times of the target book in the current time slice in the target scene, the actual exposure times of the target book in the first time slice in the target scene, and the score weight corresponding to the target book in the first time slice.

[0100] In this embodiment, it is assumed that the current time slice is the N+1th time slice of the current time period, and the intermediate weight W tmp It can be expressed as Among them, E N+1 represents the estimated exposure times of the target book in the current time slice in the target scenario, R N+1 Indicates the exposure compensation value, S N represents the actual exposure times of the target book in the first time slice in the target scene, W N Indicates the scoring weight corresponding to the target book in the first time slice. For each book, the initial scoring weight (ie, the scoring weight corresponding to the starting time slice of the current time period) can be set to a preset value, for example, W1=1.

[0101] It can be understood that in the Nth time slice, the scoring weight is W N When the actual number of exposures is S N Ideally, if the exposure and weight are linear, then the final expected exposure for the next time slice is R N+1 +E N+1 , the scoring weight should be In this embodiment, considering that exposure and weight are generally not linear and are very sensitive to weight, the amplitude is appropriately scaled. N+1 +EN+1 <0, the expected weight of W is reduced, because the form of continuous multiplication is used, even if R N+1 +E N+1 is much smaller than 0, and W cannot be set to 0. Considering the above reasons, in this embodiment, the intermediate weight W is calculated. tmp Use the exp function.

[0102] Sub-step S1035: determining the minimum value between the intermediate weight and the preset maximum weight as the scoring weight corresponding to the target book in the current time slice.

[0103] In this embodiment, considering that the scoring weight should not be too large or too small, the range of the scoring weight can be preset. min , W max ], and calculate the intermediate weight W tmp Then, the intermediate weight W tmp With the maximum weight W set max Compare them and select the smaller one as the score weight corresponding to the target book in the current time slice, that is, W N+1 =min(W tmp , W max ).

[0104] In order to execute the corresponding steps in the above embodiments and various possible methods, a method for implementing a book flow distribution device is given below. Figure 4 , which is a functional module diagram of a book flow distribution device 600 provided in an embodiment of the present invention. It should be noted that the basic principle and technical effects of the book flow distribution device 600 provided in this embodiment are the same as those of the above embodiments. For the sake of brief description, for parts not mentioned in this embodiment, reference can be made to the corresponding contents in the above embodiments. The book flow distribution device 600 includes a scoring module 610, a threshold determination module 620, a weight determination module 630 and a flow distribution module 640.

[0105] The scoring module 610 is used to determine the current score of the target book based on the acquired user information, the book information of the target book and the exposure scene information when entering the current time slice of the current time period; the current score represents the user's interest in the target book, the book information includes the target classification, and the exposure scene information includes the target scene.

[0106] It can be understood that the scoring module 610 can execute the above step S101.

[0107] The threshold determination module 620 is used to determine the score threshold corresponding to the target book in the current time slice according to the historical score corresponding to each exposure of each book under the target category in the target time slice of the previous time period under the target scene; the target time slice corresponds to the current time slice.

[0108] It can be understood that the threshold determination module 620 can execute the above step S102.

[0109] The weight determination module 630 is used to determine the score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario.

[0110] It can be understood that the weight determination module 630 can execute the above step S103.

[0111] The traffic distribution module 640 is used to determine whether to push the target book to the user in the current time slice according to the score weight, current score and score threshold corresponding to the target book in the current time slice.

[0112] It can be understood that the traffic distribution module 640 can execute the above step S104.

[0113] Optionally, the threshold determination module 620 can be used to determine a first reference score based on the historical scores corresponding to each exposure of each book under the target category within the target time slice in the target scene; the first reference score is the average of the historical scores corresponding to each book under the target category or the value of the historical scores corresponding to each book under the target category at a preset percentile after sorting; determine a second reference score based on the historical scores corresponding to each exposure of the target book within the target time slice in the target scene; the second reference score is the average of the historical scores corresponding to the target book or the value of the historical scores corresponding to the target book at a preset percentile after sorting; calculate the score threshold corresponding to the target book in the current time slice based on the first reference score and the second reference score.

[0114] Among them, the threshold determination module 620 can be specifically used to calculate the score difference between the second reference score and the first reference score; add the product of the score difference and the preset score coefficient to the first reference score to obtain the score threshold corresponding to the target book in the current time slice.

[0115] It can be understood that the threshold determination module 620 can execute the above sub-steps S1021 to S1023.

[0116] Optionally, the weight determination module 630 may be used to determine the actual cumulative exposure times of the target book in the first time slice up to the current time period in the target scene according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scene; the first time slice is the time slice before the current time slice; according to the actual exposure times of each book under the target classification in each time slice of the previous time period in the target scene, determine the estimated exposure times in the current time slice, the estimated exposure times in the first time slice, the estimated exposure times in the second time slice, and the estimated cumulative exposure times up to the first time slice of the target book in the target scene; the second time slice is the time slice before the first time slice; According to the estimated exposure times and actual exposure times of the target book in the first time slice in the target scene, the estimated exposure times and actual exposure times of the target book in the second time slice in the target scene, and the estimated cumulative exposure times and actual cumulative exposure times of the target book in the target scene up to the first time slice, calculate the exposure compensation value of the target book in the current time slice in the target scene; according to the exposure compensation value, the estimated exposure times of the target book in the current time slice in the target scene, the actual exposure times of the target book in the first time slice in the target scene, and the scoring weight corresponding to the target book in the first time slice, obtain the intermediate weight; and determine the minimum value between the intermediate weight and the preset maximum weight as the scoring weight corresponding to the target book in the current time slice.

[0117] The weight determination module 630 is specifically used to calculate the actual total exposure times of each book under the target classification in the previous time period under the target scene according to the actual exposure times of each book under the target classification in each time slice of the previous time period under the target scene; calculate the average exposure times of each book according to the actual total exposure times and the total number of books under the target classification; determine the estimated exposure times of the target book in the current time period under the target scene according to the average exposure times of each book and the actual exposure times of the target book in the previous time period under the target scene; determine the estimated exposure times of the target book in the current time slice under the target scene according to the ratio between the estimated exposure times of the target book in the current time period under the target scene, the actual exposure times of each book under the target classification in the target time slice under the target scene and the actual total exposure times; determine the estimated exposure times of the target book in the current time slice under the target scene according to the estimated exposure times of the target book in the current time period under the target scene, the actual exposure times of each book under the target classification in the target time slice under the target scene, and the actual total exposure times. The estimated exposure number of the target book in the first time slice in the target scene is determined by the ratio of the actual exposure number of each book in the first target time slice of the previous time period in the target scene to the actual total exposure number; the first target time slice corresponds to the first time slice; the estimated exposure number of the target book in the second time slice in the target scene is determined according to the estimated exposure number of the target book in the current time period in the target scene and the ratio of the actual exposure number of each book under the target category in the second target time slice of the previous time period in the target scene to the actual total exposure number; the second target time slice corresponds to the second time slice; the estimated cumulative exposure number of the target book in the target scene up to the first time slice is determined according to the estimated exposure number of the target book in the current time period in the target scene and the ratio of the actual cumulative exposure number of each book under the target category in the target scene up to the first target time slice and the actual total exposure number.

[0118] The weight determination module 630 is also specifically used to calculate a first error according to the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene; calculate a second error according to the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice; calculate a third error according to the actual exposure times of the target book in the first time slice in the target scene, the actual exposure times of the target book in the second time slice in the target scene, the estimated exposure times of the target book in the first time slice in the target scene, and the estimated exposure times of the target book in the second time slice in the target scene; add the product of the first error and the first preset control coefficient, the product of the second error and the second preset control coefficient, and the product of the third error and the third preset control coefficient to obtain an exposure compensation value of the target book in the current time slice in the target scene.

[0119] It can be understood that the weight determination module 630 can also execute the above sub-steps S1031 to S1035.

[0120] Optionally, the traffic distribution module 640 can be used to determine that the target book is pushed to the user in the current time slice when the product of the score weight corresponding to the target book in the current time slice and the current score is greater than or equal to the score threshold; when the product of the score weight corresponding to the target book in the current time slice and the current score is less than the score threshold, determine not to push the target book to the user in the current time slice.

[0121] It can be seen that the book flow distribution device provided by the embodiment of the present invention includes a scoring module, a threshold determination module, a weight determination module and a flow distribution module. The scoring module is used to determine the current score of the target book according to the acquired user information, the book information of the target book and the exposure scene information when entering the current time slice of the current time period; the current score represents the user's interest in the target book, the book information includes the target classification, and the exposure scene information includes the target scene; the threshold determination module is used to determine the score threshold corresponding to the target book in the current time slice according to the historical score corresponding to each exposure of each book under the target classification in the target time slice of the previous time period under the target scene; the target time slice corresponds to the current time slice; the weight determination module is used to determine the score weight corresponding to the target book in the current time slice according to the actual number of exposures of the target book in each time slice before the current time slice in the current time period under the target scene, and the actual number of exposures of each book under the target classification in each time slice of the previous time period under the target scene; the flow distribution module is used to determine whether to push the target book to the user in the current time slice according to the score weight corresponding to the target book in the current time slice, the current score and the score threshold. The embodiment of the present invention determines the user's interest in the book based on user information, book information and exposure scenario information, and determines the scoring threshold and scoring weight based on the historical exposure of the book. Finally, the current score, scoring weight and scoring threshold of the book are combined to determine whether to push the book to the user, thereby realizing refined traffic allocation, ensuring that the book can accurately reach more valuable traffic, improving the overall traffic utilization rate, and effectively avoiding the waste of exposure resources.

[0122] Please refer to Figure 5 , is a block diagram of an electronic device 100 provided in an embodiment of the present invention. The electronic device 100 includes a memory 110, a processor 120, and a communication module 130. The memory 110, the processor 120, and the communication module 130 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0123] The memory 110 is used to store programs or data. The memory 110 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0124] The processor 120 is used to read / write data or programs stored in the memory 110 and execute corresponding functions. For example, when the computer program stored in the memory 110 is executed by the processor 120, the book flow distribution method disclosed in the above embodiments can be implemented.

[0125] The communication module 130 is used to establish a communication connection between the electronic device 100 and other devices through a network, and to send and receive data through the network.

[0126] It should be understood that Figure 5 The structure shown is only a schematic diagram of the structure of the electronic device 100. The electronic device 100 may also include Figure 5 More or fewer components as shown, or with Figure 5 Different configurations are shown. Figure 5 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0127] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 120, the book flow distribution method disclosed in the above embodiments is implemented.

[0128] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0129] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0130] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0131] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A book flow distribution method, characterized in that: The method comprises: When entering a current time slice of a current time period, determining a current score of the target book according to the acquired user information, book information of the target book, and exposure scene information; the current score represents the user's interest in the target book, the book information includes a target classification, and the exposure scene information includes a target scene; Determine a score threshold corresponding to the target book in the current time slice according to the historical scores corresponding to each exposure of each book under the target category in the target scene in the target time slice of the previous time period; the target time slice corresponds to the current time slice; Determine the score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario; It is determined whether to push the target book to the user in the current time slice according to the score weight corresponding to the target book in the current time slice, the current score, and the score threshold.

2. The book flow distribution method according to claim 1, characterized in that: Determining the score threshold corresponding to the target book in the current time slice according to the historical score corresponding to each exposure of each book under the target classification in the target time slice of the previous time period under the target scene includes: Determine a first reference score based on the historical scores corresponding to each exposure of each book under the target category within the target time slice under the target scene; the first reference score is the average of the historical scores corresponding to each book under the target category or a value at a preset quantile after sorting the historical scores corresponding to each book under the target category; Determine a second reference score according to the historical score corresponding to each exposure of the target book in the target time slice under the target scene; the second reference score is the average of the historical scores corresponding to the target book or a value at a preset quantile after sorting the historical scores corresponding to the target book; The score threshold corresponding to the target book in the current time slice is calculated according to the first reference score and the second reference score.

3. The book flow distribution method according to claim 2, characterized in that: The calculating, according to the first reference score and the second reference score, a score threshold corresponding to the target book in the current time slice includes: Calculating a score difference between the second reference score and the first reference score; The product of the score difference and the preset score coefficient is added to the first reference score to obtain the score threshold corresponding to the target book in the current time slice.

4. The book flow distribution method according to claim 1, characterized in that: The step of determining the score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario includes: Determine, according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scene, the actual cumulative exposure times of the target book in the target scene up to the first time slice of the current time period; the first time slice is the time slice before the current time slice; Determine, according to the actual exposure times of each book under the target category in each time slice of the previous time period in the target scene, the estimated exposure times of the target book in the current time slice in the target scene, the estimated exposure times in the first time slice, the estimated exposure times in the second time slice, and the estimated cumulative exposure times up to the first time slice; the second time slice is the previous time slice of the first time slice; Calculate the exposure compensation value of the target book in the current time slice in the target scene according to the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene, the estimated exposure times and the actual exposure times of the target book in the second time slice in the target scene, and the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice; Obtaining an intermediate weight according to the exposure compensation value, the estimated exposure times of the target book in the current time slice in the target scene, the actual exposure times of the target book in the first time slice in the target scene, and the score weight corresponding to the target book in the first time slice; The minimum value between the intermediate weight and the preset maximum weight is determined as the scoring weight corresponding to the target book in the current time slice.

5. The book flow distribution method according to claim 4, characterized in that: The step of determining, based on the actual exposure times of each book under the target classification in each time slice of the previous time period in the target scene, the estimated exposure times of the target book in the current time slice in the target scene, the estimated exposure times in the first time slice, the estimated exposure times in the second time slice, and the estimated cumulative exposure times up to the first time slice, comprises: Calculate the actual total exposure times of each book under the target category in the previous time period under the target scene according to the actual exposure times of each book under the target category in each time slice of the previous time period under the target scene; Calculate the average number of exposures for each book based on the actual total number of exposures and the total number of books under the target category; Determine the estimated exposure times of the target book in the current time period in the target scenario according to the average exposure times of each book and the actual exposure times of the target book in the previous time period in the target scenario; Determine the estimated exposure times of the target book in the current time slice in the target scene according to the estimated exposure times of the target book in the current time period in the target scene, and the ratio between the actual exposure times of each book in the target category in the target time slice in the target scene and the actual total exposure times; Determine the estimated exposure times of the target book in the first time slice in the target scene according to the estimated exposure times of the target book in the current time period in the target scene, the actual exposure times of each book under the target category in the first target time slice in the previous time period in the target scene, and the ratio of the actual total exposure times; the first target time slice corresponds to the first time slice; Determine the estimated exposure times of the target book in the second time slice in the target scene according to the estimated exposure times of the target book in the current time period in the target scene, the actual exposure times of each book under the target category in the second target time slice of the previous time period in the target scene, and the ratio of the actual total exposure times; the second target time slice corresponds to the second time slice; The estimated cumulative exposure number of the target book in the target scenario up to the first time slice is determined according to the estimated exposure number of the target book in the current time period in the target scenario and the ratio between the actual cumulative exposure number of each book under the target category in the target scenario up to the first target time slice and the actual total exposure number.

6. The book flow distribution method according to claim 4, characterized in that: The step of calculating the exposure compensation value of the target book in the current time slice in the target scene according to the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene, the estimated exposure times and the actual exposure times of the target book in the second time slice in the target scene, and the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice includes: Calculating a first error according to the estimated exposure times and the actual exposure times of the target book in the first time slice in the target scene; Calculating a second error according to the estimated cumulative exposure times and the actual cumulative exposure times of the target book in the target scene up to the first time slice; Calculate a third error according to the actual exposure times of the target book in the first time slice in the target scene, the actual exposure times of the target book in the second time slice in the target scene, the estimated exposure times of the target book in the first time slice in the target scene, and the estimated exposure times of the target book in the second time slice in the target scene; The product of the first error and the first preset control coefficient, the product of the second error and the second preset control coefficient, and the product of the third error and the third preset control coefficient are added together to obtain the exposure compensation value of the target book in the current time slice in the target scene.

7. The book flow distribution method according to any one of claims 1 to 6, characterized in that:The determining, according to the score weight corresponding to the target book in the current time slice, the current score and the score threshold, whether to push the target book to the user in the current time slice comprises: When the product of the score weight corresponding to the target book in the current time slice and the current score is greater than or equal to the score threshold, determine to push the target book to the user in the current time slice; When the product of the score weight corresponding to the target book in the current time slice and the current score is less than the score threshold, it is determined not to push the target book to the user in the current time slice.

8. A book flow distribution device, characterized in that: The device comprises: A scoring module is used to determine the current score of the target book according to the acquired user information, the book information of the target book and the exposure scene information when entering the current time slice of the current time period; the current score represents the user's interest in the target book, the book information includes the target classification, and the exposure scene information includes the target scene; A threshold determination module, configured to determine a score threshold corresponding to the target book in the current time slice according to the historical scores corresponding to each exposure of each book under the target classification in the target time slice of the previous time period under the target scene; the target time slice corresponds to the current time slice; A weight determination module, configured to determine a score weight corresponding to the target book in the current time slice according to the actual exposure times of the target book in each time slice before the current time slice in the current time period in the target scenario and the actual exposure times of each book under the target category in each time slice of the previous time period in the target scenario; The traffic distribution module is used to determine whether to push the target book to the user in the current time slice according to the score weight corresponding to the target book in the current time slice, the current score and the score threshold.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of book flow distribution according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of book flow distribution according to any one of claims 1 to 7 are implemented.