Book recommendation method, terminal and storage medium

By obtaining the user collection and reading intensity information of the target books and books to be recommended, calculating the similarity and determining the recommendation score, the problem of low book recommendation accuracy in the prior art is solved, and higher recommendation accuracy and user interests are achieved Spend.

CN113836430BActive Publication Date: 2024-11-26ZHANGYUE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111194482.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-13
Publication Date
2024-11-26
Estimated Expiration
2041-10-13

AI Technical Summary

Technical Problem

The existing book recommendation method calculates similarity based on a single book, with low accuracy and cannot meet user needs.

Method used

By obtaining the user collection and reading intensity information of the target book and the book to be recommended, the similarity between the target book and the book to be recommended is calculated, and the recommendation score is determined based on the similarity.

Benefits of technology

Improve the accuracy of book recommendations and enhance users' reading stickiness and interest.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113836430B_ABST
    Figure CN113836430B_ABST
Patent Text Reader

Abstract

The present invention relates to a book recommendation method, terminal and storage medium. The book recommendation method includes: obtaining a target book and multiple books to be recommended, wherein the number of target books is multiple; determining user sets corresponding to the target book and the books to be recommended, respectively, and reading intensity information corresponding to multiple users included in each user set; based on the user set and the reading intensity information, respectively determining multiple target similarities between the target book and the multiple books to be recommended; determining the recommended books based on the recommendation scores of each book to be recommended determined by the multiple target similarities, and recommending the recommended books. Since the number of target books is multiple and the recommended books are determined based on the unified recommendation score calculated based on the similarity, the present invention can screen out books that are more interesting to the user for recommendation compared to the related art based on a single book, thereby improving the accuracy of book recommendations, and further improving the reading stickiness and interest of the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to a book recommendation method, a terminal and a storage medium. Background Art

[0002] With the rapid development of Internet technology, electronic books are increasingly used and paid more attention to. Users can choose books of interest to read based on recommended books.

[0003] Currently, recommended books can be determined based on individual books by calculating the similarities between different books, but the accuracy of the above book recommendation method is low and cannot meet the needs. Summary of the invention

[0004] In order to solve the technical problem of low accuracy of book recommendations, the present disclosure provides a book recommendation method, a terminal, and a storage medium to improve the accuracy of book recommendations.

[0005] In a first aspect, an embodiment of the present disclosure provides a book recommendation method, comprising:

[0006] Obtain a target book and multiple books to be recommended, where the number of the target books is multiple;

[0007] Determine the user sets corresponding to the target book and the book to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set;

[0008] Based on the user set and the reading intensity information, respectively determine a plurality of target similarities between the target book and the plurality of books to be recommended;

[0009] Determine recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities, and recommend the recommended books.

[0010] In a second aspect, an embodiment of the present disclosure provides a terminal, including:

[0011] processor;

[0012] A memory for storing executable instructions;

[0013] The processor is used to read the executable instructions from the memory and execute the executable instructions to perform the following operations:

[0014] Obtain a target book and multiple books to be recommended, where the number of the target books is multiple;

[0015] Determine the user sets corresponding to the target book and the book to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set;

[0016] Based on the user set and the reading intensity information, respectively determine a plurality of target similarities between the target book and the plurality of books to be recommended;

[0017] Determine recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities, and recommend the recommended books.

[0018] In a third aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the book recommendation method of the first aspect.

[0019] One of the above technical solutions has the following advantages or beneficial effects:

[0020] According to the book recommendation method, terminal and storage medium of the embodiment of the present disclosure, it is possible to obtain a target book and multiple books to be recommended, determine the user sets corresponding to the target book and the books to be recommended, and the reading intensity information corresponding to the multiple users included in each user set, and then determine multiple target similarities between the target book and the multiple books to be recommended based on the user sets and the reading intensity information, and determine the recommended books based on the recommendation scores of each book to be recommended determined by the multiple target similarities, and recommend the recommended books. The embodiment of the present disclosure can determine the similarity between the target book and other books through the reading intensity information, and then recommend books according to the recommendation scores determined by the similarities. Since there are multiple target books and the recommended books are determined based on the unified recommendation scores calculated based on the similarities, compared with the related art based on a single book, it is possible to screen out books that are more interesting to the user for recommendation, thereby improving the accuracy of book recommendations and thus improving the user's reading stickiness and interest. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A flowchart of a book recommendation method provided by an embodiment of the present disclosure;

[0023] Figure 2 A flowchart of another book recommendation method provided by an embodiment of the present disclosure;

[0024] Figure 3 A flowchart of another book recommendation method provided by an embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of a book recommendation provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the structure of a terminal provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain 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 construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] In order to solve the problem of low accuracy in the related art of recommending books based on a single book by calculating the similarities between different books, the present disclosure provides a book recommendation method, which is introduced below in conjunction with a specific embodiment.

[0034] Figure 1 The flowchart of a book recommendation method provided by the embodiment of the present disclosure is shown in FIG. 1 , which can be executed by a book recommendation device, wherein the device can be implemented by software and / or hardware and can generally be integrated in a terminal or a server. Figure 1 As shown, the method includes:

[0035] Step 101: Obtain a target book and multiple books to be recommended.

[0036] Among them, the target book can be a book related to the current user, and is also the basis for determining the recommended book. In the embodiment of the present disclosure, the number of target books is multiple, and the target books can include multiple historical books read in history. The books to be recommended can be some books that are related to the target book. In the embodiment of the present disclosure, the books to be recommended can have at least one attribute information that is the same as that of the target book, and the attribute information can include information such as the book type, writing time, and author, that is, the books to be recommended can be some books with the same attribute information as that of the target book. The multiple books to be recommended corresponding to different target books can be different, can be partially the same and partially different, or can be the same.

[0037] In the embodiment of the present disclosure, the book recommendation apparatus may obtain a plurality of target books and a plurality of books to be recommended that are related to the current user.

[0038] Step 102: Determine the user sets corresponding to the target book and the book to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set.

[0039] The user set corresponding to a book may be a set of multiple users who have read the book. The reading intensity information may be information that characterizes the depth and interest of the user in reading the book. The reading intensity information may include one or more types of information. For example, the reading information may include reading time, interaction data, and payment status, etc. The specific information may be determined according to actual conditions.

[0040] In an embodiment of the present disclosure, determining the user sets corresponding to the target book and the books to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set may include: determining, based on pre-acquired target relationship data, a first user set corresponding to the target book and the reading intensity information corresponding to the multiple users included in the first user set, and determining a second user set corresponding to each book to be recommended and the reading intensity information corresponding to the multiple users included in the second user set.

[0041] The target relationship data can be obtained from a database, and the target relationship data can include information such as the corresponding relationship between users and books and the reading intensity information of each user for each book. The book recommendation device can obtain the target relationship data from the database, and search for multiple users corresponding to each target book and the reading intensity information corresponding to each user according to the target relationship data to obtain a first user set, and search for multiple users corresponding to each book to be recommended and the reading intensity information corresponding to each user according to the target relationship data to obtain a second user set. The number of the first user set is the same as the number of target books, and the number of the second user set is the same as the number of books to be recommended. The number of the first user set and the second user set can both be multiple.

[0042] Step 103: Based on the user set and the reading intensity information, multiple target similarities between the target book and multiple books to be recommended are determined respectively.

[0043] The target similarity may include unidirectional similarity, which may represent the similarity calculated with the target book as the reference direction. The unidirectional similarity may be a similarity with a reference direction, that is, it has a tendency and emphasis when calculating the similarity. The unidirectional similarity in the embodiment of the present disclosure takes the target book as the reference direction, that is, it screens the books of interest to users who have read the target book.

[0044] In an optional embodiment of the present disclosure, based on the user set and the reading intensity information, determining multiple target similarities between the target book and multiple books to be recommended respectively may include: determining a first user subset in the first user set according to a first selection condition, and determining a second user subset in the second user set according to a second selection condition; determining the intersection between the first user subset and the second user subset to obtain a third user set; determining multiple unidirectional similarities between the target book and multiple books to be recommended according to the third user set, the number of books read by two users in the third user set, and a preset similarity formula.

[0045] The first selection condition and the second selection condition can be two selection ranges or two selection conditions with different selection strictness, and the difference is relatively large. Since this solution selects books of interest to users who have read the target book, the first selection condition for the target book has a low degree of strictness, while the second selection condition for the recommended book has a high degree of strictness, that is, the second selection condition has a much higher degree of strictness than the first selection condition.

[0046] The first selection condition can be used to select users whose reading intensity information of the target book is greater than or equal to the first threshold, and the second selection condition can be used to select users whose reading intensity information of each to-be-recommended book is greater than or equal to the second threshold, and the second threshold is much greater than the first threshold. The first threshold and the second threshold can be values ​​that respectively characterize the strictness of the selection of the first selection condition and the second selection condition. The first threshold is relatively low and can cover most of the users who have read the target book as much as possible, and the second threshold is relatively high and can select most of the interested users as much as possible.

[0047] The first threshold and the second threshold can be set and adjusted according to the actual situation. For example, when the reading intensity information is the reading time, the first threshold can be 0.1 hours and the second threshold can be 10 hours. When the first threshold is increased, the number of users in the first user subset decreases, the traffic is concentrated, and the quality becomes higher. When the second threshold is lowered, the number of users in the second user subset increases, the traffic is not concentrated, and the quality becomes lower. If you want to recommend books that users are more interested in, increase the second threshold. If you want to recommend more books to users, lower the second threshold.

[0048] Specifically, the book recommendation device can compare the reading intensity information of each user in the first user set with the first threshold according to the first selection condition, select the users whose reading intensity information is greater than or equal to the first threshold, and obtain the first user subset; and can compare the reading intensity information of each user in the second user set with the second threshold according to the second selection condition, select the users whose reading intensity information is greater than or equal to the second threshold, and obtain the second user subset. Then, the book recommendation device can determine the intersection of the first user subset and the second user subset, that is, determine the users included in both the first user subset and the second user subset, and obtain the third user set.

[0049] After the book recommendation device determines the third user set, it can combine multiple users in the third user set in pairs to obtain user pairs, determine the number of books read by the two users in each user pair, and then determine the one-way similarity between the target book and each book to be recommended according to a preset similarity formula to obtain multiple one-way similarities.

[0050] The above preset similarity formula can be:

[0051]

[0052] Among them, i represents the target book, j represents a book to be recommended, and U i represents users who have read the target book, U j Indicates users who have read the recommended books. u represents the number of books read by user u, I vrepresents the number of books read by user v, U i ∩U j represents the third user set, I u ∩I v represents the number of books read by user u and user v together, where user u and user v may be any two users in the third user set.

[0053] Exemplarily, assuming that the reading intensity information is the reading time, taking the first book and the second book as examples, the first threshold in the first selection condition can be 0.1 hours, and the second threshold in the second selection condition can be 10 hours. When the first book is the target book and the second book is a book to be recommended, the number of users whose reading time for the first book is determined to be greater than or equal to 0.1 hours is 20,000, and the number of users whose reading time for the second book is determined to be greater than or equal to 10 hours is 1,000. According to the above preset similarity formula, sim(first book, second book) is determined; when the second book is the target book and the first book is a book to be recommended, the number of users whose reading time for the second book is determined to be greater than or equal to 0.1 hours is 20,000, and the number of users whose reading time for the first book is determined to be greater than or equal to 10 hours is 10. According to the above preset similarity formula, sim(second book, first book) is determined, sim(first book, second book) is lower, and sim(second book, first book) is higher. Therefore, a user will not recommend the second book when reading the first book, but will recommend the first book when reading the second book. Compared with the related art, sim (first book, second book) is the same as sim (second book, first book), and there is no indiscriminate recommendation caused by directionality. The recommended books of this solution are more accurate.

[0054] Step 104: Determine recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities, and recommend the recommended books.

[0055] The recommended books may be the books that are finally determined to be recommended to the current user. Since the target books may include multiple historical books that have been read historically, the recommendation scores of the books to be recommended may be determined based on multiple target similarities between the multiple historical books and the multiple books to be recommended, and then the recommended books may be recommended based on the recommendation scores, and the recommendation may be implemented by displaying the recommendation information including the recommended books.

[0056] For example, Figure 2 A flowchart of another book recommendation method provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, when the target similarity is a one-way similarity, determining the recommended books based on the recommendation scores of each to-be-recommended book determined based on multiple target similarities may include the following steps:

[0057] Step 201: Determine a recommendation score of a first recommended book among multiple books to be recommended based on multiple one-way similarities.

[0058] The first recommended book may be a recommended book obtained through initial screening based on a similarity threshold, and the recommended score may be a comprehensive score calculated based on a one-way similarity.

[0059] In an embodiment of the present disclosure, determining a recommendation score of a first recommended book among multiple books to be recommended based on multiple one-way similarities may include: for each target book, determining a first recommended book among multiple books to be recommended based on multiple one-way similarities and a similarity threshold; constructing a similarity matrix based on the one-way similarities between the multiple target books and the first recommended book respectively; and determining a recommendation score of each first recommended book according to the similarity matrix.

[0060] When there are multiple target books, for each target book, the first recommended book among multiple books to be recommended can be determined based on the comparison result of the one-way similarity and the similarity threshold, each target book has a corresponding first recommended book, and the number of first recommended books is multiple; then, a similarity matrix can be constructed based on the one-way similarities between multiple target books and each book in the corresponding first recommended books, each row of the similarity matrix corresponds to the one-way similarity between a target book and each book in the first recommended books, and different columns represent different target books; based on the above similarity matrix, the recommendation score of each first recommended book can be determined. The above similarity threshold can be set according to actual conditions.

[0061] Optionally, determining the recommendation score of each first recommended book according to the similarity matrix may include: determining each first recommended book as a book to be processed in turn; extracting multiple one-way similarities between multiple target books and the books to be processed in the similarity matrix; determining the sum of the multiple one-way similarities between the multiple target books and the books to be processed as the recommendation score of the book to be processed; or determining the sum of the multiple first similarity values ​​between the multiple target books and the books to be processed as the recommendation score of the book to be processed, wherein the first similarity value is the product of the reading intensity information of each target book and the one-way similarity between each target book and the book to be processed.

[0062] Among them, the books to be processed can be books that are currently being determined for recommendation scores. Since there can be multiple first recommended books, the book recommendation device can determine the recommendation score for each first recommended book in turn, that is, determine the recommendation score of each first recommended book in turn as a book to be processed and then determine the recommendation score.

[0063] Specifically, the book recommendation device can extract the one-way similarity between each target book and the book to be processed in the similarity matrix, obtain multiple one-way similarities, and then perform summation to obtain a first comprehensive score, which is the recommended score of the book to be processed. Alternatively, the book processing device can first calculate the product of the reading intensity information of each target book and the one-way similarity between each target book and the book to be processed in the similarity matrix, and determine the product as the first similarity value between the target book and the book to be processed; since there are multiple target books, multiple first similarity values ​​can be obtained, and then summation is performed to obtain a second comprehensive score, and the second comprehensive score is determined as the recommended score of the book to be processed. Each first recommended book is used as a book to be processed and the above-mentioned recommended score is determined once, and finally the recommended score of each first recommended book is obtained.

[0064] For example, assuming that the current user's history books include book 1 and book 2, that is, the target books include book 1 and book 2, the first recommended books corresponding to book 1 include book A and book B, and the reading intensity information of book 1 is L1, and the first recommended books corresponding to book 2 include book A and book C, and the reading intensity information of book 1 is L2, then the constructed similarity matrix can be:

[0065] Book 1: s1 with Book A; s2 with Book B;

[0066] Book 2: s3 with Book A; s4 with Book C;

[0067] The above s1 represents the one-way similarity between book 1 and book A, s2 represents the one-way similarity between book 1 and book B, s3 represents the one-way similarity between book 2 and book A, and s4 represents the one-way similarity between book 2 and book C.

[0068] Then the recommendation score of book A = s1+s3, the recommendation score of book B = s2, and the recommendation score of book C = s4; or, the recommendation score of book A = L1*s1+L2*s3, the recommendation score of book B = L1*s2, and the recommendation score of book C = L2*s4. Both of the above methods of determining the recommendation scores are applicable, and the final recommended books are then determined based on the recommendation scores of book A, book B, and book C.

[0069] Step 202: Determine the first recommended book whose recommendation score is greater than or equal to the first preset score as the second recommended book.

[0070] The second recommended book may be a recommended book finally determined when the target similarity is a one-way similarity. The first preset score may be a preset minimum threshold of the recommended score, which may be set according to actual conditions.

[0071] Specifically, after determining the recommendation score of the first recommended book, the book recommendation device may sequentially compare each recommendation score with the first preset score, and determine the first recommended book whose recommendation score is greater than or equal to the first preset score as the second recommended book.

[0072] Optionally, after determining the recommendation score of each first recommended book, the first recommended books can also be sorted in descending order according to the recommendation score, and a preset number of first recommended books with a higher ranking can be determined as second recommended books based on the sorting result. The preset number corresponds to the above-mentioned first preset score, and the recommendation score of the first recommended books corresponding to the preset number sorting position can be the above-mentioned first preset score. For example, when the preset number is 100, the recommendation score corresponding to the 100th first recommended book is the first preset score.

[0073] According to the book recommendation method, terminal and storage medium of the embodiment of the present disclosure, it is possible to obtain a target book and multiple books to be recommended, determine the user sets corresponding to the target book and the books to be recommended, and the reading intensity information corresponding to the multiple users included in each user set, and then determine multiple target similarities between the target book and the multiple books to be recommended based on the user sets and the reading intensity information, and determine the recommended books based on the recommendation scores of each book to be recommended determined by the multiple target similarities, and recommend the recommended books. The embodiment of the present disclosure can determine the similarity between the target book and other books through the reading intensity information, and then recommend books according to the recommendation scores determined by the similarities. Since there are multiple target books and the recommended books are determined based on the unified recommendation scores calculated based on the similarities, compared with the related art based on a single book, it is possible to screen out books that are more interesting to the user for recommendation, thereby improving the accuracy of book recommendations and thus improving the user's reading stickiness and interest.

[0074] In some embodiments, the target similarity includes non-directional similarity. Based on the user set and reading intensity information, multiple target similarities between the target book and multiple books to be recommended are determined respectively, which can include: determining the intersection between the first user set and the second user set to obtain a fourth user set; determining multiple non-directional similarities between the target book and multiple books to be recommended based on the fourth user set, the number of books read by two users in the fourth user set, and a preset similarity formula.

[0075] The non-directional similarity can be understood as a similarity without a reference direction, which is different from the above-mentioned unidirectional similarity and has no tendency or emphasis when calculating the similarity. The preset similarity formula can be the same as the formula for determining the above-mentioned unidirectional similarity.

[0076] When the target similarity is a non-directional similarity, the book recommendation device can determine the intersection between the first user set and the second user set, that is, determine the users included in both the first user set and the second user set, and obtain a fourth user set; then, multiple users in the fourth user set can be combined in pairs to obtain user pairs, and the number of books read by the two users in each user pair can be determined. Then, according to a preset similarity formula, the non-directional similarity between the target book and each book to be recommended can be determined to obtain multiple non-directional similarities.

[0077] The above preset similarity formula can be:

[0078]

[0079] Among them, i represents the target book, j represents a book to be recommended, and U i represents users who have read the target book, U j Indicates users who have read the recommended books. u represents the number of books read by user u, I v represents the number of books read by user v, U i ∩U j represents the fourth user set, I u ∩I v represents the number of books read by user u and user v together, where user u and user v may be any two users in the fourth user set.

[0080] For example, Figure 3 A flowchart of another book recommendation method provided by the embodiment of the present disclosure is shown as follows: Figure 3 As shown, when the target similarity is a non-directional similarity, determining the recommended books based on the recommendation scores of each to-be-recommended book determined based on multiple target similarities may include the following steps:

[0081] Step 301: Determine the recommendation score of each book to be recommended based on multiple non-directional similarities.

[0082] When the current target similarity is non-directional similarity, the recommendation score may be a comprehensive score calculated based on the non-directional similarity.

[0083] In an embodiment of the present disclosure, determining the recommendation score of each to-be-recommended book based on multiple non-directional similarities may include: for each to-be-recommended book, determining the corresponding recommendation score as the sum of multiple non-directional similarities between multiple target books and each to-be-recommended book; or, for each to-be-recommended book, determining the corresponding recommendation score as the sum of multiple second similarity values ​​between multiple target books and each to-be-recommended book, wherein the second similarity value is the product of the reading intensity information of each target book and the non-directional similarity between each target book and each to-be-recommended book.

[0084] For each book to be recommended, the book recommendation device may sum up multiple non-directional similarities between the book to be recommended and multiple target books to obtain a third comprehensive score, which is the recommendation score of the book to be recommended. Alternatively, for each book to be recommended, the book recommendation device may first determine the second similarity values ​​between the book to be recommended and multiple target books, and then sum up the sum of the multiple second similarity values ​​to obtain a fourth comprehensive score, which is determined as the recommendation score of the book to be recommended; the above determination of the second similarity value between the book to be recommended and a target book may be to multiply the reading intensity information of the target book by the non-directional similarity between the target book and the book to be recommended, and determine the obtained product as the second similarity value. Since there are multiple target books, multiple second similarity values ​​may be obtained.

[0085] Exemplarily, assuming that the current user's historical books include book 1 and book 2, that is, the target books include book 1 and book 2, the first recommended books corresponding to book 1 include book A and book B, the reading intensity information of book 1 is L1, and the first recommended books corresponding to book 2 include book A and book C, and the reading intensity information of book 1 is L2, then s1 represents the non-directional similarity between book 1 and book A, s2 represents the non-directional similarity between book 1 and book B, s3 represents the non-directional similarity between book 2 and book A, and s4 represents the non-directional similarity between book 2 and book B. Then the recommendation score of book A = s1+s3, and the recommendation score of book B = s2+s4; or, the recommendation score of book A = L1*s1+L2*s3, and the recommendation score of book B = L1*s2+L2×s4. Both of the above methods of determining the recommendation scores are applicable, and then the final recommended books are determined according to the recommendation scores of book A, book B and book C.

[0086] Step 302: Determine the to-be-recommended books whose recommendation scores are greater than or equal to the second preset score as third recommended books.

[0087] The third recommended book may be the recommended book finally determined when the target similarity is non-directional similarity. The second preset score may be the minimum threshold of the recommended score preset when the target similarity is non-directional similarity, and the first preset score may be the same as or different from the first preset score, and may be set according to actual conditions.

[0088] Specifically, after determining the recommendation score of each to-be-recommended book, the book recommendation device may sequentially compare each recommendation score with the second preset score, and determine the to-be-recommended book whose recommendation score is greater than or equal to the second preset score as the third recommended book.

[0089] Optionally, after determining the recommendation score of each book to be recommended, the first recommended books can also be sorted in descending order according to the recommendation score, and a preset number of books to be recommended with a higher ranking can be determined as the third recommended books based on the sorting result. The preset number corresponds to the above-mentioned second preset score, and the recommendation score of the books to be recommended corresponding to the preset number sorting position can be the above-mentioned second preset score. For example, when the preset number is 100, the recommendation score corresponding to the 100th book to be recommended is the second preset score.

[0090] In the disclosed embodiment, when the target similarity is non-directional similarity, a unified recommendation score can be determined based on the non-directional similarity, and recommended books can be determined based on the recommendation score. Compared with the related art of directly recommending books based on non-directional similarity, the accuracy of book recommendations is improved.

[0091] In some embodiments, the reading intensity information may include at least one of the following:

[0092] Total reading time;

[0093] The number of interactions includes at least one of the number of likes, the number of comments, and the number of shares;

[0094] Total reading level, which includes the sum of reading levels of each reading. The reading level is determined based on the reading time, the time difference between the reading time and the current time, and the decay value;

[0095] Total number of payments or total payment amount;

[0096] The decay value of the reading time.

[0097] The total reading time may be the sum of the reading time of a book read by a user at different times. The number of interactions may be at least one of the number of likes, comments, and shares of a book by a user.

[0098] The reading degree can be understood as the depth of a user's reading of a book, which can be determined based on the reading time, the time difference between the reading time and the current time, the decay value and the reading degree formula. The reading degree formula can be expressed as x = t*a y , where x represents the reading degree of a single reading, t represents the reading time, a represents the decay value, which can be a fixed value, for example, the decay value can be set to 0.95, and y represents the time difference between the reading time and the current time. For example, the current user read a book for 3 hours 50 days ago, and the decay value is set to 0.95, then the reading degree x = 3*0.95 50 , which means 3 times 0.95 raised to the power of 50. The total reading degree may be equal to the sum of the reading degrees of multiple readings of a book by the user, that is, the total reading degree may be obtained by adding up the reading degrees of multiple readings.

[0099] The total number of payments and the total payment amount may be representations related to payment, and the reading intensity information may be the sum of the number of payments made by the user for a book, or the sum of the amounts paid by the user for multiple times for a book.

[0100] The decay value of reading time may be the decay value corresponding to the most recent reading time of a book by the user. The decay value may be inversely proportional to the reading time. The earlier the reading time, the smaller the decay value. For example, if the reading time is from the current time to one month ago, the decay value is 0.95; if the reading time is from one month to one year ago, the decay value is 0.5; if the reading time is any time before one year ago, the decay value is 0.1. The above are only examples. And the change of the decay value may follow a certain rule. For example, the decay value may decay in a linear, broken line, or exponential manner.

[0101] The reading intensity information in the disclosed embodiment may be represented by various types of information, which improves the richness and diversity of the reading intensity information and facilitates subsequent book recommendations.

[0102] For example, Figure 4 A schematic diagram of a book recommendation provided by an embodiment of the present disclosure, such as Figure 4 As shown in the figure, a recommendation page 400 including multiple recommended books is shown. The recommendation page 400 may include recommendation information of book C, book D, book E and book F as shown in the figure. The multiple recommended books can be determined based on the historical books read by the current user. Each recommendation information may include information such as the name and cover of the book to arouse the user's interest and encourage reading.

[0103] Above Figure 4 The corresponding recommendation scenario is that the target book is a recommended book of multiple historical books. Figure 4The recommendation methods in the article are only examples, and other methods of recommending books are applicable.

[0104] The embodiment of the present disclosure also provides a terminal, which may include a processor and a memory, and the memory may be used to store executable instructions. The processor may be used to read the executable instructions from the memory, and execute the executable instructions to perform the following operations: obtain a target book and multiple books to be recommended, where the number of target books is multiple; determine the user sets corresponding to the target book and the books to be recommended, and the reading intensity information corresponding to the multiple users included in each user set; based on the user set and the reading intensity information, determine multiple target similarities between the target book and the multiple books to be recommended; determine the recommended books based on the recommendation scores of each book to be recommended determined by the multiple target similarities, and recommend the recommended books.

[0105] Figure 5 The terminal 500 in the embodiment of the present disclosure may be the electronic device described above. It should also be noted that: Figure 5 The terminal 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0106] The terminal 500 conventionally includes a processor 510 and a computer program product or computer-readable medium in the form of a memory 520. The memory 520 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 520 has a storage space 521 for executable instructions (or program codes) 5211 for executing any method steps in the above-mentioned book recommendation method. For example, the storage space 521 for executable instructions may include individual executable instructions 5211 respectively used to implement various steps in the above-mentioned book recommendation method. These executable instructions may be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a compact disk (CD), a memory card or a floppy disk. Such a computer program product is typically a portable or fixed storage unit. The storage unit may have a storage device having a storage medium ... Figure 5 The memory 520 in the terminal is similarly arranged as a storage segment or storage space, etc. The executable instructions can be compressed, for example, in an appropriate form. Generally, the storage unit includes executable instructions for executing the steps of the book recommendation method according to the present invention, that is, codes that can be read by a processor such as the processor 510, and when these codes are executed by the terminal, the terminal executes the various steps in the book recommendation method described above.

[0107] An embodiment of the present invention further provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the book recommendation method provided by each embodiment of the present invention.

[0108] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0109] The computer-readable medium may be included in the terminal, or may exist independently without being installed in the terminal.

[0110] In an embodiment of the present invention, computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The various component embodiments of the present invention may be implemented in hardware in all or part of the steps, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the book recommendation device according to an embodiment of the present invention. The present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0112] According to one or more embodiments of the present disclosure, the present disclosure provides a book recommendation method, comprising:

[0113] Obtain a target book and multiple books to be recommended, where the number of the target books is multiple;

[0114] Determine the user sets corresponding to the target book and the book to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set;

[0115] Based on the user set and the reading intensity information, respectively determine a plurality of target similarities between the target book and the plurality of books to be recommended;

[0116] Determine recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities, and recommend the recommended books.

[0117] Optionally, the user sets corresponding to the target book and the book to be recommended, and the reading intensity information corresponding to the multiple users included in each user set, include:

[0118] According to the pre-acquired target relationship data, the first user set corresponding to the target book and the reading intensity information corresponding to the multiple users included in the first user set are determined, and the second user set corresponding to each of the books to be recommended and the reading intensity information corresponding to the multiple users included in the second user set are determined.

[0119] Optionally, the target relationship data includes the corresponding relationship between users and books and the reading intensity information of each user for each book.

[0120] Optionally, the target similarity includes a one-way similarity, and based on the user set and the reading intensity information, multiple target similarities between the target book and the multiple books to be recommended are determined respectively, including:

[0121] Determine a first user subset in the first user set according to a first selection condition, and determine a second user subset in the second user set according to a second selection condition;

[0122] Determine an intersection between the first user subset and the second user subset to obtain a third user set;

[0123] A plurality of one-way similarities between the target book and the plurality of books to be recommended are determined according to the third user set, the number of books read together by two users in the third user set, and a preset similarity formula.

[0124] Optionally, the first selection condition is used to select users whose reading intensity information for the target book is greater than or equal to a first threshold, and the second selection condition is used to select users whose reading intensity information for each of the recommended books is greater than or equal to a second threshold, and the second threshold is much larger than the first threshold.

[0125] Optionally, determining the recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities includes:

[0126] Determining a recommendation score of a first recommended book among the plurality of books to be recommended based on the plurality of one-way similarities;

[0127] The first recommended book whose recommendation score is greater than or equal to the first preset score is determined as the second recommended book.

[0128] Optionally, determining a recommendation score of a first recommended book among the multiple books to be recommended based on the multiple one-way similarities includes:

[0129] For each of the target books, determining a first recommended book among the multiple books to be recommended based on the multiple one-way similarities and similarity thresholds;

[0130] constructing a similarity matrix based on the one-way similarities between the plurality of target books and the first recommended book respectively;

[0131] The recommendation score of each of the first recommended books is determined according to the similarity matrix.

[0132] Optionally, determining the recommendation score of each of the first recommended books according to the similarity matrix includes:

[0133] sequentially determining each of the first recommended books as books to be processed;

[0134] Extracting multiple one-way similarities between the multiple target books and the books to be processed in the similarity matrix;

[0135] Determining the sum of multiple one-way similarities between the multiple target books and the book to be processed as the recommendation score of the book to be processed;

[0136] Alternatively, the sum of multiple first similarity values ​​between the multiple target books and the books to be processed is determined as the recommendation score of the book to be processed, wherein the first similarity value is the product of the reading intensity information of each target book and the one-way similarity between each target book and the book to be processed.

[0137] Optionally, the target similarity includes non-directional similarity, and based on the user set and the reading intensity information, multiple target similarities between the target book and the multiple books to be recommended are determined respectively, including:

[0138] Determine an intersection between the first user set and the second user set to obtain a fourth user set;

[0139] A plurality of non-directional similarities between the target book and the plurality of books to be recommended are determined according to the fourth user set, the number of books read by two users in the fourth user set, and a preset similarity formula.

[0140] Optionally, determining the recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities includes:

[0141] Determining a recommendation score for each of the books to be recommended based on the multiple non-directional similarities;

[0142] The books to be recommended whose recommendation scores are greater than or equal to the second preset score are determined as the third recommended books.

[0143] Optionally, determining the recommendation score of each of the books to be recommended based on the multiple non-directional similarities includes:

[0144] For each book to be recommended, determining the sum of multiple undirected similarities between the multiple target books and each book to be recommended as a corresponding recommendation score;

[0145] Alternatively, for each book to be recommended, the sum of multiple second similarity values ​​between the multiple target books and each book to be recommended is determined as the corresponding recommendation score, wherein the second similarity value is the product of the reading intensity information of each target book and the undirected similarity between each target book and each book to be recommended.

[0146] Optionally, the reading intensity information includes at least one of the following:

[0147] Total reading time;

[0148] The number of interactions includes at least one of the number of likes, the number of comments, and the number of shares;

[0149] A total reading degree, the total reading degree includes the sum of the reading degrees of each reading, and the reading degree is determined based on the reading time, the time difference between the reading time and the current time, and the decay value;

[0150] Total number of payments or total payment amount;

[0151] The decay value of the reading time.

[0152] Optionally, the target books include a plurality of historical books that have been read historically, and the books to be recommended have at least one attribute information identical to that of the target books.

[0153] According to one or more embodiments of the present disclosure, the present disclosure provides a terminal, including:

[0154] processor;

[0155] a memory for storing processor-executable instructions;

[0156] A processor that reads executable instructions from memory and executes the instructions to:

[0157] Obtain a target book and multiple books to be recommended, where the number of the target books is multiple;

[0158] Determine the user sets corresponding to the target book and the book to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set;

[0159] Based on the user set and the reading intensity information, respectively determine a plurality of target similarities between the target book and the plurality of books to be recommended;

[0160] Determine recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities, and recommend the recommended books.

[0161] Optionally, the executable instructions further cause the processor to perform the following operations:

[0162] The step of determining the user sets corresponding to the target book and the book to be recommended and the reading intensity information corresponding to the multiple users included in each user set includes:

[0163] According to the pre-acquired target relationship data, the first user set corresponding to the target book and the reading intensity information corresponding to the multiple users included in the first user set are determined, and the second user set corresponding to each of the books to be recommended and the reading intensity information corresponding to the multiple users included in the second user set are determined.

[0164] Optionally, the target relationship data includes the corresponding relationship between users and books and the reading intensity information of each user for each book.

[0165] Optionally, the executable instructions further cause the processor to perform the following operations:

[0166] The target similarity includes a one-way similarity, and based on the user set and the reading intensity information, multiple target similarities between the target book and the multiple books to be recommended are determined respectively, including:

[0167] Determine a first user subset in the first user set according to a first selection condition, and determine a second user subset in the second user set according to a second selection condition;

[0168] Determine an intersection between the first user subset and the second user subset to obtain a third user set;

[0169] A plurality of one-way similarities between the target book and the plurality of books to be recommended are determined according to the third user set, the number of books read together by two users in the third user set, and a preset similarity formula.

[0170] Optionally, the first selection condition is used to select users whose reading intensity information for the target book is greater than or equal to a first threshold, and the second selection condition is used to select users whose reading intensity information for each of the recommended books is greater than or equal to a second threshold, and the second threshold is much larger than the first threshold.

[0171] Optionally, the executable instructions further cause the processor to perform the following operations:

[0172] The step of determining the recommended books based on the recommendation scores of the books to be recommended determined based on the multiple target similarities includes:

[0173] Determining a recommendation score of a first recommended book among the plurality of books to be recommended based on the plurality of one-way similarities;

[0174] The second recommended book whose recommendation score is greater than or equal to the first preset score is determined as the second recommended book.

[0175] Optionally, the executable instructions further cause the processor to perform the following operations:

[0176] Wherein, determining the recommendation score of the first recommended book among the multiple books to be recommended based on the multiple one-way similarities includes:

[0177] For each of the target books, determining a first recommended book among the multiple books to be recommended based on the multiple one-way similarities and similarity thresholds;

[0178] constructing a similarity matrix based on the one-way similarities between the plurality of target books and the first recommended book respectively;

[0179] The recommendation score of each of the first recommended books is determined according to the similarity matrix.

[0180] Optionally, the executable instructions further cause the processor to perform the following operations:

[0181] Wherein, determining the recommendation score of each of the first recommended books according to the similarity matrix includes:

[0182] sequentially determining each of the first recommended books as books to be processed;

[0183] Extracting multiple one-way similarities between the multiple target books and the books to be processed in the similarity matrix;

[0184] Determining the sum of multiple one-way similarities between the multiple target books and the book to be processed as the recommendation score of the book to be processed;

[0185] Alternatively, the sum of multiple first similarity values ​​between the multiple target books and the books to be processed is determined as the recommendation score of the book to be processed, wherein the first similarity value is the product of the reading intensity information of each target book and the one-way similarity between each target book and the book to be processed.

[0186] Optionally, the executable instructions further cause the processor to perform the following operations:

[0187] The target similarity includes non-directional similarity, and based on the user set and the reading intensity information, multiple target similarities between the target book and the multiple books to be recommended are determined respectively, including:

[0188] Determine an intersection between the first user set and the second user set to obtain a fourth user set;

[0189] A plurality of non-directional similarities between the target book and the plurality of books to be recommended are determined according to the fourth user set, the number of books read by two users in the fourth user set, and a preset similarity formula.

[0190] Optionally, the executable instructions further cause the processor to perform the following operations:

[0191] The step of determining the recommended books based on the recommendation scores of the books to be recommended determined based on the multiple target similarities includes:

[0192] Determining a recommendation score for each of the books to be recommended based on the multiple non-directional similarities;

[0193] The books to be recommended whose recommendation scores are greater than or equal to the second preset score are determined as the third recommended books.

[0194] Optionally, the executable instructions further cause the processor to perform the following operations:

[0195] Wherein, determining the recommendation score of each of the books to be recommended based on the multiple non-directional similarities includes:

[0196] For each book to be recommended, determining the sum of multiple undirected similarities between the multiple target books and each book to be recommended as a corresponding recommendation score;

[0197] Alternatively, for each book to be recommended, the sum of multiple second similarity values ​​between the multiple target books and each book to be recommended is determined as the corresponding recommendation score, wherein the second similarity value is the product of the reading intensity information of each target book and the undirected similarity between each target book and each book to be recommended.

[0198] Optionally, the reading intensity information includes at least one of the following:

[0199] Total reading time;

[0200] The number of interactions includes at least one of the number of likes, the number of comments, and the number of shares;

[0201] A total reading degree, the total reading degree includes the sum of the reading degrees of each reading, and the reading degree is determined based on the reading time, the time difference between the reading time and the current time, and the decay value;

[0202] Total number of payments or total payment amount;

[0203] The decay value of the reading time.

[0204] Optionally, the target books include a plurality of historical books that have been read historically, and the books to be recommended have at least one attribute information identical to that of the target books.

[0205] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, the storage medium storing a computer program, and the computer program is used to execute any of the book recommendation methods provided by the present disclosure.

[0206] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

[0207] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0208] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A book recommendation method, characterized in that: include: Acquire a target book and a plurality of books to be recommended, wherein the number of the target books is a plurality, and the target books include a plurality of historical books of historical reading; Determine the user sets corresponding to the target book and the book to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set; Based on the user set and the reading intensity information, respectively determine a plurality of target similarities between the target book and the plurality of books to be recommended; Determining recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities, and recommending the recommended books; The target similarity includes a one-way similarity, and based on the user set and the reading intensity information, multiple target similarities between the target book and the multiple books to be recommended are determined respectively, including: Determine a first user subset in the first user set corresponding to the target book according to a first selection condition, and determine a second user subset in the second user set corresponding to each of the books to be recommended according to a second selection condition; Determine an intersection between the first user subset and the second user subset to obtain a third user set; Determine multiple one-way similarities between the target book and the multiple books to be recommended according to the third user set, the number of books read by two users in the third user set, and a preset similarity formula; The preset similarity formula is: Among them, i represents the target book, j represents a book to be recommended, and U i represents users who have read the target book, U j Indicates users who have read the recommended books. u represents the number of books read by user u, I v represents the number of books read by user v, U i ∩U j represents the third user set, I u ∩I v represents the number of books read by user u and user v together, where user u and user v are any two users in the third user set; Determining the recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities includes: Determining a recommendation score of a first recommended book among the plurality of books to be recommended based on the plurality of one-way similarities; The first recommended book whose recommendation score is greater than or equal to the first preset score is determined as the second recommended book.

2. The method according to claim 1, characterized in that Determining the user sets corresponding to the target book and the book to be recommended respectively and the reading intensity information corresponding to the multiple users included in each user set, including: According to the pre-acquired target relationship data, the first user set corresponding to the target book and the reading intensity information corresponding to the multiple users included in the first user set are determined, and the second user set corresponding to each of the books to be recommended and the reading intensity information corresponding to the multiple users included in the second user set are determined.

3. The method according to claim 2, characterized in that The target relationship data includes the corresponding relationship between users and books and the reading intensity information of each user for each book.

4. The method according to claim 1, characterized in that The first selection condition is used to select users whose reading intensity information for the target book is greater than or equal to a first threshold, and the second selection condition is used to select users whose reading intensity information for each of the recommended books is greater than or equal to a second threshold, and the second threshold is much greater than the first threshold.

5. The method according to claim 1, characterized in that Determining a recommendation score of a first recommended book among the plurality of books to be recommended based on the plurality of one-way similarities includes: For each of the target books, determining a first recommended book among the multiple books to be recommended based on the multiple one-way similarities and similarity thresholds; constructing a similarity matrix based on the one-way similarities between the plurality of target books and the first recommended books respectively; The recommendation score of each of the first recommended books is determined according to the similarity matrix.

6. The method according to claim 5, characterized in that Determining the recommendation score of each of the first recommended books according to the similarity matrix includes: sequentially determining each of the first recommended books as books to be processed; Extracting multiple one-way similarities between the multiple target books and the books to be processed in the similarity matrix; Determining the sum of multiple one-way similarities between the multiple target books and the book to be processed as the recommendation score of the book to be processed; Alternatively, the sum of multiple first similarity values ​​between the multiple target books and the books to be processed is determined as the recommendation score of the book to be processed, wherein the first similarity value is the product of the reading intensity information of each target book and the one-way similarity between each target book and the book to be processed.

7. The method according to claim 2, wherein the target similarity comprises a non-directional similarity, and based on the user set and the reading intensity information, determining a plurality of target similarities between the target book and the plurality of books to be recommended, respectively, comprising: Determine an intersection between the first user set and the second user set to obtain a fourth user set; Determine a plurality of non-directional similarities between the target book and the plurality of books to be recommended according to the fourth user set, the number of books read by two users in the fourth user set, and a preset similarity formula; The preset similarity formula is: Among them, i represents the target book, j represents a book to be recommended, and U i represents users who have read the target book, U j Indicates users who have read the recommended books. u represents the number of books read by user u, I v represents the number of books read by user v, U i ∩U j represents the fourth user set, I u ∩I v represents the number of books read by user u and user v together, where user u and user v are any two users in the fourth user set.

8. The method according to claim 7, characterized in that Determining the recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities includes: Determining a recommendation score for each of the books to be recommended based on the multiple non-directional similarities; The books to be recommended whose recommendation scores are greater than or equal to the second preset score are determined as the third recommended books.

9. The method according to claim 8, characterized in that Determining the recommendation score of each of the books to be recommended based on the multiple non-directional similarities includes: For each book to be recommended, determining the sum of multiple undirected similarities between the multiple target books and each book to be recommended as a corresponding recommendation score; Alternatively, for each book to be recommended, the sum of multiple second similarity values ​​between the multiple target books and each book to be recommended is determined as the corresponding recommendation score, wherein the second similarity value is the product of the reading intensity information of each target book and the undirected similarity between each target book and each book to be recommended.

10. The method according to claim 1, characterized in that The reading intensity information includes at least one of the following: Total reading time; The number of interactions includes at least one of the number of likes, the number of comments, and the number of shares; A total reading degree, the total reading degree includes the sum of the reading degrees of each reading, and the reading degree is determined based on the reading time, the time difference between the reading time and the current time, and the decay value; Total number of payments or total payment amount; The decay value of the reading time.

11. The method according to claim 1, characterized in that: The to-be-recommended book has at least one attribute information identical to that of the target book.

12. A terminal, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to perform the following operations: Acquire a target book and a plurality of books to be recommended, wherein the number of the target books is a plurality, and the target books include a plurality of historical books of historical reading; Determine the user sets corresponding to the target book and the book to be recommended, respectively, and the reading intensity information corresponding to the multiple users included in each user set; Based on the user set and the reading intensity information, respectively determine a plurality of target similarities between the target book and the plurality of books to be recommended; Determining recommended books based on the recommendation scores of the books to be recommended determined by the multiple target similarities, and recommending the recommended books; The executable instructions further cause the processor to perform the following operations: The target similarity includes a one-way similarity, and based on the user set and the reading intensity information, multiple target similarities between the target book and the multiple books to be recommended are determined respectively, including: Determine a first user subset in the first user set corresponding to the target book according to a first selection condition, and determine a second user subset in the second user set corresponding to each of the books to be recommended according to a second selection condition; Determine an intersection between the first user subset and the second user subset to obtain a third user set; Determine multiple one-way similarities between the target book and the multiple books to be recommended according to the third user set, the number of books read by two users in the third user set, and a preset similarity formula; The preset similarity formula is: Among them, i represents the target book, j represents a book to be recommended, and U i represents users who have read the target book, U j Indicates users who have read the recommended books. u represents the number of books read by user u, I v represents the number of books read by user v, U i ∩U j represents the third user set, I u ∩I v represents the number of books read by user u and user v together, where user u and user v are any two users in the third user set; The executable instructions further cause the processor to perform the following operations: The step of determining the recommended books based on the recommendation scores of the books to be recommended determined based on the multiple target similarities includes: Determining a recommendation score of a first recommended book among the plurality of books to be recommended based on the plurality of one-way similarities; The second recommended book whose recommendation score is greater than or equal to the first preset score is determined as the second recommended book.

13. The terminal according to claim 12, characterized in that: The executable instructions further cause the processor to perform the following operations: The step of determining the user sets corresponding to the target book and the book to be recommended and the reading intensity information corresponding to the multiple users included in each user set includes: According to the pre-acquired target relationship data, the first user set corresponding to the target book and the reading intensity information corresponding to the multiple users included in the first user set are determined, and the second user set corresponding to each of the books to be recommended and the reading intensity information corresponding to the multiple users included in the second user set are determined.

14. The terminal according to claim 13, characterized in that: The target relationship data includes the corresponding relationship between users and books and the reading intensity information of each user for each book.

15. The terminal according to claim 12, characterized in that: The first selection condition is used to select users whose reading intensity information for the target book is greater than or equal to a first threshold, and the second selection condition is used to select users whose reading intensity information for each of the recommended books is greater than or equal to a second threshold, and the second threshold is much greater than the first threshold.

16. The terminal according to claim 12, characterized in that: The executable instructions further cause the processor to perform the following operations: Wherein, determining the recommendation score of the first recommended book among the multiple books to be recommended based on the multiple one-way similarities includes: For each of the target books, determining a first recommended book among the multiple books to be recommended based on the multiple one-way similarities and similarity thresholds; constructing a similarity matrix based on the one-way similarities between the plurality of target books and the first recommended books respectively; The recommendation score of each of the first recommended books is determined according to the similarity matrix.

17. The terminal according to claim 16, characterized in that: The executable instructions further cause the processor to perform the following operations: Wherein, determining the recommendation score of each of the first recommended books according to the similarity matrix includes: sequentially determining each of the first recommended books as books to be processed; Extracting multiple one-way similarities between the multiple target books and the books to be processed in the similarity matrix; Determining the sum of multiple one-way similarities between the multiple target books and the book to be processed as the recommendation score of the book to be processed; Alternatively, the sum of multiple first similarity values ​​between the multiple target books and the books to be processed is determined as the recommendation score of the book to be processed, wherein the first similarity value is the product of the reading intensity information of each target book and the one-way similarity between each target book and the book to be processed.

18. The terminal according to claim 13, characterized in that: The executable instructions further cause the processor to perform the following operations: The target similarity includes non-directional similarity, and based on the user set and the reading intensity information, multiple target similarities between the target book and the multiple books to be recommended are determined respectively, including: Determine an intersection between the first user set and the second user set to obtain a fourth user set; Determine a plurality of non-directional similarities between the target book and the plurality of books to be recommended according to the fourth user set, the number of books read by two users in the fourth user set, and a preset similarity formula; The preset similarity formula is: Among them, i represents the target book, j represents a book to be recommended, and U i represents users who have read the target book, U j Indicates users who have read the recommended books. u represents the number of books read by user u, I v represents the number of books read by user v, U i ∩U j represents the fourth user set, I u ∩I v represents the number of books read by user u and user v together, where user u and user v are any two users in the fourth user set.

19. The terminal according to claim 18, characterized in that: The executable instructions further cause the processor to perform the following operations: The step of determining the recommended books based on the recommendation scores of the books to be recommended determined based on the multiple target similarities includes: Determining a recommendation score for each of the books to be recommended based on the multiple non-directional similarities; The books to be recommended whose recommendation scores are greater than or equal to the second preset score are determined as the third recommended books.

20. The terminal according to claim 19, characterized in that The executable instructions further cause the processor to perform the following operations: Wherein, determining the recommendation score of each of the books to be recommended based on the multiple non-directional similarities includes: For each book to be recommended, determining the sum of multiple undirected similarities between the multiple target books and each book to be recommended as a corresponding recommendation score; Alternatively, for each book to be recommended, the sum of multiple second similarity values ​​between the multiple target books and each book to be recommended is determined as the corresponding recommendation score, wherein the second similarity value is the product of the reading intensity information of each target book and the undirected similarity between each target book and each book to be recommended.

21. The terminal according to claim 12, characterized in that: The reading intensity information includes at least one of the following: Total reading time; The number of interactions includes at least one of the number of likes, the number of comments, and the number of shares; A total reading degree, the total reading degree includes the sum of the reading degrees of each reading, and the reading degree is determined based on the reading time, the time difference between the reading time and the current time, and the decay value; Total number of payments or total payment amount; The decay value of the reading time.

22. The terminal according to claim 12, characterized in that: The to-be-recommended book has at least one attribute information identical to that of the target book.

23. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the book recommendation method according to any one of claims 1 to 11.