Book recommendation system and method

Abstract

The invention relates to the technical field of books, and discloses a book recommendation system which comprises an acquisition module, an analysis module and a feedback adjustment module. According to the book recommendation system, keyword classification tags are arranged in tag units, book keyword numbering is carried out on books and the keyword classification tags, and reading features of users are calculated and analyzed according to a user basic information set, a user historical reading information set and a user reading interest set; user keyword numbering is carried out on the reading features and keyword classification labels, then keyword comparison sorting marking is carried out on book keyword numbers and user keyword numbers, the book keyword numbers and the user keyword numbers are sent to a feedback adjustment module, reading feedback is carried out according to recommended sorting marks, and multi-dimensional information of the user is comprehensively analyzed; according to the method and the system, personal interests and demands of the user can be captured more accurately, more personalized book recommendation is provided, the user can find books meeting own interests more quickly, and the system can adjust the books through a feedback mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of books, and in particular to a book recommendation system and method. Background Art

[0002] Books are a medium that records information in the form of text or images. They are usually bound by multiple pages and are used to spread knowledge and culture. Books are carriers that record human knowledge, information and ideas in the form of text, pictures or other symbols. They are usually printed on paper and bound into volumes for reading and reference. Any book contains four basic elements: the knowledge information being disseminated, the symbols (text or images) that record this information, the material carrier, and the production technology and process. Books are not only tools for recording and disseminating information, but also bridges that connect the past and the future and communicate different cultures and ideas. Whether it is traditional paper books or modern electronic books, they are constantly influencing the way people think and the world view. The library management system is a software system used to manage library resources, including multiple functional modules such as library information, book classification, book borrowing, and announcement release.

[0003] The existing book recommendation system is difficult to comprehensively integrate various user situations for accurate push, and the recommendation accuracy is not high, which leads to a poor reading experience for users. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a book recommendation system and method, which have the advantages of comprehensively analyzing the multi-dimensional information of users, more accurately capturing the personal interests and needs of users, and providing more personalized book recommendations, so that users can find books that suit their interests more quickly, and the system can be adjusted through a feedback mechanism to improve satisfaction, etc.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a book recommendation system, comprising a collection module, an analysis module and a feedback adjustment module;

[0008] The acquisition module is composed of a user basic information acquisition unit, a user history reading information acquisition unit, and a user reading interest acquisition unit. The user basic information acquisition unit is used to acquire a user basic information set, and the user basic information set includes multiple basic information of the user. The user history reading information acquisition unit is used to acquire a user history reading information set, and the user history reading information set includes multiple historical reading information of the user. The user reading interest acquisition unit is used to acquire a user reading interest set, and the user reading interest set includes multiple reading interests of the user. The acquisition module sends the user basic information set, the user reading information set, and the user reading interest set to the analysis module;

[0009] The analysis module is composed of a label unit, a book feature classification unit, and a user reading feature analysis unit. A keyword classification label is set inside the label unit. The book feature classification unit connects the book library to the book and the keyword classification label to perform book keyword numbering. The user reading feature analysis unit calculates and analyzes the user's reading feature YDtz according to the user's basic information set, the user's historical reading information set, and the user's reading interest set, and performs user keyword numbering on the reading feature YDtz and the keyword classification label. The analysis module performs a keyword comparison Db on the book keyword number and the user keyword number, and performs a recommendation sorting mark based on the keyword criticality of Db obtained by the keyword comparison and sends it to the feedback adjustment module;

[0010] The feedback adjustment module performs reading feedback according to the recommended sorting mark.

[0011] Preferably, the expression of the user basic information set is: Among them, Yj1~Yj n represents the basic information of the 1st to nth users, r represents the basic information of the corresponding user, and the basic information includes the user's age information, user gender, user occupation, and user educational background information.

[0012] Preferably, the expression of the user's historical reading information set is: {Ly1, Ly2, Ly3, . . . , Ly n}, among which Ly1~Ly n Corresponding to the user basic information set Yj1~Yj n of users read the message.

[0013] Preferably, the expression of the user reading interest set is:

[0014] {Rx1, Rx2, Rx3,···,Rx n}, where Rx1~Rx n Corresponding to Ly1~Ly in the user's historical reading information set n, user basic information is concentrated in Yj1~Yj n of users’ reading interests.

[0015] Preferably, the method for numbering book keywords is as follows:

[0016] A1. The keyword classification labels are set to x, namely: Gb1, Gb2, ···, Gb x ;

[0017] A2. Before each book is put into the library, the corresponding book is matched with multiple related keyword classification tags in the keyword classification tag, and the book keyword numbers are arranged according to the keyword matching degree: Gt1, Gt2, ···, Gt y , Gt1 represents the highest keyword matching degree, Gt y It represents the lowest keyword matching degree, and y represents that the book matches y related keywords in the keyword classification label.

[0018] Preferably, the calculation method of the user's reading feature YDtz is as follows:

[0019] B1. Mark the i-th user basic information in the user basic information set as

[0020] B2. Mark the i-th user historical reading information in the user historical reading information set as Ly i ;

[0021] B3. Mark the reading interest of the i-th user in the user reading interest set as Rx i ;

[0022] B4. Calculate the reading feature YDtz using the following formula:

[0023]

[0024] In the above formula, the sum of the basic information, historical reading information, and user reading interests of the i-th user is the reading feature YDtz of the user.

[0025] Preferably, the user keyword numbering method is as follows:

[0026] Will read the characteristics

[0027] YDtz matches multiple related keyword classification tags in the keyword classification tag and arranges them according to the keyword matching degree to form user keyword numbers: Gh1, Gh2, ···, Gh y , Gh1 represents the highest keyword matching degree, Gh yrepresents the lowest keyword match, and y represents that the reading feature YDtz matches y related keywords in the keyword classification label.

[0028] Preferably, the keyword is compared with Db in the following manner:

[0029] Number the user keywords: Gh1, Gh2, ···, Gh y Book keyword number: Gt1, Gt2, ···, Gt y Compare with Gh1, Gh2, ···, Gh y The books are ranked by keyword priority according to the degree of match, and the books with high and low keyword similarity are ranked and recommended first.

[0030] Preferably, the feedback adjustment module is internally provided with a satisfied port and an unsatisfied port, and the user makes comments at the satisfied port or the unsatisfied port according to the book priority recommendation, and the unsatisfied port is connected to the analysis module, which can make new recommendations after re-analysis.

[0031] A book recommendation method comprises the following steps:

[0032] S1. Collect multiple basic information of users to form a basic user information set;

[0033] S2. Collect multiple historical reading information of the user to form a user historical reading information set;

[0034] S3. Collect multiple reading interests of users to form a user reading interest set;

[0035] S4. A keyword classification tag is provided inside the tag unit, and the book keyword classification tag is numbered for the book keyword;

[0036] S5. Calculate and analyze the user's reading characteristics YDtz based on the user's basic information set, the user's historical reading information set, and the user's reading interest set;

[0037] S6. Number the reading feature YDtz and the keyword classification label for user keywords;

[0038] S7. Compare the book keyword number with the user keyword number and send the Db sort mark to the feedback adjustment module;

[0039] S8. Provide reading feedback based on the recommended sorting marks.

[0040] Compared with the prior art, the present invention provides a book recommendation system and method, which has the following features:

[0041] Beneficial effects:

[0042] 1. The present invention comprehensively considers the user's age information, user gender, user occupation, user educational background information, user historical reading information, and user historical reading information, and comprehensively analyzes the user's multi-dimensional information, so as to more accurately understand the user's reading preferences and needs, thereby providing more personalized book recommendations, which can better meet the user's personalized needs and improve user experience, while also providing valuable market insights for publishers and sellers.

[0043] 2. The present invention first numbers books and keyword classification labels by book keyword numbers, then calculates and analyzes the user's reading characteristics YDtz according to the user's basic information set, the user's historical reading information set, and the user's reading interest set, and then numbers the reading characteristics YDtz and the keyword classification labels for user keywords, and then performs keyword comparison Db. This can more accurately capture the user's personal interests and needs, thereby providing more personalized book recommendations. Users can find books that suit their interests more quickly, which improves user satisfaction and loyalty to the platform. At the same time, irrelevant books are filtered out by keyword numbers, alleviating the problem of information overload when users are faced with a large number of choices. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a step diagram of the method of the present invention;

[0045] Figure 2 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1-2 ,A book recommendation system, including a collection module, an analysis module and a feedback adjustment module;

[0048] The collection module is composed of a user basic information collection unit, a user history reading information collection unit, and a user reading interest collection unit. The user basic information collection unit is used to collect a user basic information set, which includes multiple basic information of the user;

[0049] The expression of the user basic information set is: Among them, Yj1~Yj nRepresents the basic information of the 1st to nth users, r represents the basic information of the corresponding user, including the user's age, gender, occupation, and educational background;

[0050] The user history reading information collection unit is used to collect a user history reading information set, and the user history reading information set includes a plurality of historical reading information of the user;

[0051] The expression of the user's historical reading information set is: {Ly1, Ly2, Ly3, ···, Ly n}, among which Ly1~Ly n Corresponding to the user basic information set Yj1~Yj n of users read the information;

[0052] The user history reading information collection unit is used to collect the user's reading interest set, and the user reading interest set includes multiple reading interests of the user;

[0053] The expression of the user's historical reading information set is: {Rx1, Rx2, Rx3, ···, Rx n}, where Rx1~Rx n Corresponding to Ly1~Ly in the user's historical reading information set n , user basic information is concentrated in Yj1~Yj n User reading interests;

[0054] By comprehensively considering the user's age information, gender, occupation, educational background information, historical reading information, and comprehensive analysis of the user's multi-dimensional information, we can more accurately understand the user's reading preferences and needs, thereby providing more personalized book recommendations, which can better meet the user's personalized needs and improve user experience. At the same time, it also provides valuable market insights for publishers and sellers;

[0055] The collection module sends the user basic information set, the user reading information set, and the user reading interest set to the analysis module;

[0056] The analysis module consists of a label unit, a book feature classification unit, and a user reading feature analysis unit. The label unit is internally provided with a keyword classification label. The book feature classification unit connects the book library to the book and the keyword classification label to perform book keyword numbering.

[0057] The method of book keyword numbering is as follows:

[0058] A1. Set x keyword classification labels, namely: Gb1, Gb2, ···, Gb x ;

[0059] A2. Before each book is put into the library, the corresponding book is matched with multiple related keyword classification tags in the keyword classification tag, and the book keyword numbers are arranged according to the keyword matching degree: Gt1, Gt2, ···, Gt y , Gt1 represents the highest keyword matching degree, Gt y represents the lowest keyword match, and y represents that the book matches y related keywords in the keyword classification tag;

[0060] The user reading feature analysis unit calculates and analyzes the user's reading feature YDtz based on the user's basic information set, the user's historical reading information set, and the user's reading interest set;

[0061] The calculation method of the user's reading feature YDtz is as follows:

[0062] B1. Mark the i-th user basic information in the user basic information set as

[0063] B2. Mark the i-th user historical reading information in the user historical reading information set as Ly i ;

[0064] B3. Mark the reading interest of the i-th user in the user reading interest set as Rx i ;

[0065] B4. Calculate the reading feature YDtz using the following formula:

[0066]

[0067] In the above formula, the sum of the basic information, historical reading information, and reading interests of the i-th user is the reading feature YDtz of the user;

[0068] The reading feature YDtz and the keyword classification label are used to perform user keyword numbering;

[0069] User keyword numbering is as follows:

[0070] Will read the characteristics

[0071] YDtz matches multiple related keyword classification tags in the keyword classification tag and arranges them according to the keyword matching degree to form user keyword numbers: Gh1, Gh2, ···, Gh y , Gh1 represents the highest keyword matching degree, Gh y represents the lowest keyword match, and y represents that the reading feature YDtz matches y related keywords in the keyword classification label;

[0072] The analysis module compares the book keyword number with the user keyword number Db;

[0073] The way to compare keywords to Db is as follows:

[0074] Number the user keywords: Gh1, Gh2, ···, Gh y Book keyword number: Gt1, Gt2, ···, Gt y Compare with Gh1, Gh2, ···, Gh y The books are ranked by keyword priority based on the matching degree, and the books with high and low keyword similarity are ranked and recommended first;

[0075] And compare the key words of Db according to the key words, make a recommendation and sort the mark, and send it to the feedback adjustment module;

[0076] By first numbering books and keyword classification tags, and then calculating and analyzing the user's reading features YDtz based on the user's basic information set, user's historical reading information set, and user's reading interest set, and then numbering the reading features YDtz and keyword classification tags, and then performing keyword comparison Db, the user's personal interests and needs can be captured more accurately, thereby providing more personalized book recommendations. Users can find books that meet their interests more quickly, which improves user satisfaction and loyalty to the platform. At the same time, irrelevant books are filtered out through keyword numbers, which reduces the information overload problem when users are faced with a large number of choices.

[0077] The feedback adjustment module is internally provided with a satisfied port and an unsatisfied port. Users can comment on the satisfied port or unsatisfied port according to the priority ranking of books. The unsatisfied port is connected to the analysis module, which can be re-analyzed and re-recommended.

[0078] Users can comment on books in the satisfied or dissatisfied ports according to the priority ranking of books. The system can understand users' needs and preferences more accurately, and re-analyze and recommend books to improve the accuracy of recommendations. When users are dissatisfied with the recommendation results, they can use the feedback mechanism to let the system make adjustments, so that users are more likely to find books they are interested in, thereby improving satisfaction.

[0079] The specific method of the above book recommendation system is as follows:

[0080] S1. Collect multiple basic information of users to form a basic user information set;

[0081] S2. Collect multiple historical reading information of the user to form a user historical reading information set;

[0082] S3. Collect multiple reading interests of users to form a user reading interest set;

[0083] S4. A keyword classification tag is provided inside the tag unit, and the book keyword classification tag is numbered for the book keyword;

[0084] S5. Calculate and analyze the user's reading characteristics YDtz based on the user's basic information set, the user's historical reading information set, and the user's reading interest set;

[0085] S6. Number the reading feature YDtz and the keyword classification label for user keywords;

[0086] S7. Compare the book keyword number with the user keyword number and send the Db sort mark to the feedback adjustment module;

[0087] S8. Provide reading feedback based on the recommended sorting marks.

[0088] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A book recommendation system, characterized in that: It includes a collection module, an analysis module and a feedback adjustment module; The acquisition module is composed of a user basic information acquisition unit, a user history reading information acquisition unit, and a user reading interest acquisition unit. The user basic information acquisition unit is used to acquire a user basic information set, and the user basic information set includes multiple basic information of the user. The user history reading information acquisition unit is used to acquire a user history reading information set, and the user history reading information set includes multiple historical reading information of the user. The user reading interest acquisition unit is used to acquire a user reading interest set, and the user reading interest set includes multiple reading interests of the user. The acquisition module sends the user basic information set, the user reading information set, and the user reading interest set to the analysis module; The analysis module is composed of a label unit, a book feature classification unit, and a user reading feature analysis unit. A keyword classification label is set inside the label unit. The book feature classification unit connects the book library to the book and the keyword classification label to perform book keyword numbering. The user reading feature analysis unit calculates and analyzes the user's reading feature YDtz according to the user's basic information set, the user's historical reading information set, and the user's reading interest set, and performs user keyword numbering on the reading feature YDtz and the keyword classification label. The analysis module performs a keyword comparison Db on the book keyword number and the user keyword number, and performs a recommendation sorting mark based on the keyword criticality of Db obtained by the keyword comparison and sends it to the feedback adjustment module; The feedback adjustment module performs reading feedback according to the recommended sorting mark.

2. A book recommendation system according to claim 1, characterized in that: The expression of the user basic information set is: Among them, Yj1~Yj n represents the basic information of the 1st to nth users, r represents the basic information of the corresponding user, and the basic information includes the user's age information, user gender, user occupation, and user educational background information.

3. A book recommendation system according to claim 2, characterized in that: The expression of the user's historical reading information set is: {Ly1, Ly2, Ly3, . . . , Ly n }, among which Ly1~Ly n Corresponding to the user basic information set Yj1~Yj n of users read the message.

4. A book recommendation system according to claim 3, characterized in that: The expression of the user reading interest set is: {Rx1, Rx2, Rx3, . . . , Rx n }, where Rx1~Rx n Corresponding to Ly1~Ly in the user's historical reading information set n , user basic information is concentrated in Yj1~Yj n of users’ reading interests.

5. A book recommendation system according to claim 4, characterized in that: The method of book keyword numbering is as follows: A1. The keyword classification labels are set to x, namely: Gb1, Gb2, ···, Gb x ; A2. Before each book is put into the library, the corresponding book is matched with multiple related keyword classification tags in the keyword classification tag, and the book keyword numbers are arranged according to the keyword matching degree: Gt1, Gt2, ···, Gt y , Gt1 represents the highest keyword matching degree, Gt y It represents the lowest keyword matching degree, and y represents that the book matches y related keywords in the keyword classification label.

6. A book recommendation system according to claim 5, characterized in that: The calculation method of the user's reading feature YDtz is as follows: B1. Mark the i-th user basic information in the user basic information set as B2. Mark the i-th user historical reading information in the user historical reading information set as Ly i ; B3. Mark the reading interest of the i-th user in the user reading interest set as Rx i ; B4. Calculate the reading feature YDtz using the following formula: In the above formula, the sum of the basic information, historical reading information, and user reading interests of the i-th user is the reading feature YDtz of the user.

7. A book recommendation system according to claim 6, characterized in that: The method of user keyword numbering is as follows: Will read the characteristics YDtz matches multiple related keyword classification tags in the keyword classification tag and arranges them according to the keyword matching degree to form user keyword numbers: Gh1, Gh2, ···, Gh y , Gh1 represents the highest keyword matching degree, Gh y represents the lowest keyword match, and y represents that the reading feature YDtz matches y related keywords in the keyword classification label.

8. A book recommendation system according to claim 7, characterized in that: The method of comparing the keywords to Db is as follows: Number the user keywords: Gh1, Gh2, ···, Gh y Book keyword number: Gt1, Gt2, ···, Gt y Compare with Gh1, Gh2, ···, Gh y The books are ranked by keyword priority according to the degree of match, and the books with high and low keyword similarity are ranked and recommended first.

9. A book recommendation system according to claim 8, characterized in that: The feedback adjustment module is internally provided with a satisfied port and an unsatisfied port. Users can comment on the satisfied port or the unsatisfied port according to the book priority recommendation. The unsatisfied port is connected to the analysis module, which can perform re-analysis and re-recommendation.

10. A book recommendation method, comprising the following steps: S1. Collect multiple basic information of users to form a basic user information set; S2. Collect multiple historical reading information of the user to form a user historical reading information set; S3. Collect multiple reading interests of users to form a user reading interest set; S4. A keyword classification tag is provided inside the tag unit, and the book keyword classification tag is numbered for the book keyword; S5. Calculate and analyze the user's reading characteristics YDtz based on the user's basic information set, the user's historical reading information set, and the user's reading interest set; S6. Number the reading feature YDtz and the keyword classification label for user keywords; S7. Compare the book keyword number with the user keyword number and send the Db sort mark to the feedback adjustment module; S8. Provide reading feedback based on the recommended sorting marks.

Images