CN115033805A - Preschool children picture book intelligent recommendation method and picture book management system - Google Patents
Preschool children picture book intelligent recommendation method and picture book management system Download PDFInfo
- Publication number
- CN115033805A CN115033805A CN202210676391.3A CN202210676391A CN115033805A CN 115033805 A CN115033805 A CN 115033805A CN 202210676391 A CN202210676391 A CN 202210676391A CN 115033805 A CN115033805 A CN 115033805A
- Authority
- CN
- China
- Prior art keywords
- book
- user
- picture
- picture book
- books
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 88
- 239000011159 matrix material Substances 0.000 claims abstract description 41
- 238000010422 painting Methods 0.000 claims description 37
- 238000011156 evaluation Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims description 3
- 230000037431 insertion Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims 1
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 description 8
- 238000001914 filtration Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the field of data analysis, and particularly relates to an intelligent picture book recommendation method for preschool children, a picture book management system and reading equipment thereof. The recommendation method recommends a new book which is suitable and meets the preference of the current user to the current user according to the recorded personal information and reading records of all users; the recommendation method comprises the following steps: s1: acquiring all the pictures and the grading records thereof which have been watched or shared by the current user to obtain a watched list and a grading list; s2: acquiring all the picture books which have been watched or shared by all the similar users and grading records thereof to obtain a reference list and a grading table; s3: constructing a label similarity matrix; s4: generating a user preference matrix; s5: calculating the final preference score of the current user to each drawing book in the reference list; s6: and reordering the reference list to obtain the recommended book pocket. The invention solves the problem that the existing picture book recommendation method is not suitable for recommending the books of preschool children.
Description
Technical Field
The invention belongs to the field of data analysis, and particularly relates to an intelligent picture book recommendation method for preschool children, a picture book management system and reading equipment thereof.
Background
Researches show that the cultivation of the early reading habit of preschool children is important for the subsequent learning and growth of children, and from the viewpoint of protecting the eyesight of children, the preschool children are generally recommended to select paper domain paintings for reading paintings, so that the early browsing of electronic books is avoided. Meanwhile, the picture books of preschool children are generally short in content, high in reading speed and large in reading demand. Parents need to provide new paintings for children to read frequently in early education, and how to select the paintings suitable for the early development of the children is a common concern of parents of most infants.
There are many methods for recommending the existing picture books, and there are two types of methods based on user preference and picture book content. The method based on user preference is usually developed based on collaborative filtering algorithm, and such method can be generally divided into two collaborative filtering recommendation methods based on user and based on picture book. The user-based method aims at completing the picture book recommendation of a specified user according to the picture book preference of a known user and the similarity of the preferences among different users; the collaborative filtering method based on the drawing books generally evaluates similarity between a plurality of drawing books based on user preference or inherent attributes, and recommends more related drawing books according to the drawing books which specify the existing preference of the user. Another content-based approach typically obtains other paintings with similar characteristics based on the characteristics, attributes, or text and other characteristics of the paintings themselves.
The existing book recommendation algorithm and system can effectively recommend books which are useful or interesting to the user to adult users to a certain extent, but the attention of the algorithm is generally focused on book recommendation which is mainly based on characters. The picture book of the preschool children is different from general books in characteristics, and because the preschool children are more sensitive to pictures usually, and in the process of guiding the children to read by the preschool children, the characters can more efficiently convey the subject contents of the picture book to parents, so that the parents are helped to better assist the children in completing the reading of the picture book. On the other hand, the selection and recommendation of the picture books of preschool children need to be combined with the growth characteristics of the children, for example, in the early period of the infant vocalization, the children are insensitive to the colors of the books, so that the children cannot read the color picture books; in a specific period, the human face structure is greatly interested; in addition, the picture books can be used for guiding the children to realize cognition on the children or the environment around the children, culture of emotional emotion, development of living habits and the like in different stages of preschool child growth. The invention mainly considers the characteristics of the children picture book recommendation when constructing the system, and improves the recommendation performance.
Disclosure of Invention
The invention provides an intelligent picture book recommendation method for preschool children, a picture book management system and reading equipment thereof, aiming at the problem that the existing book recommendation method is not suitable for book recommendation of preschool children.
In order to achieve the purpose, the invention is realized by the following technical scheme:
an intelligent preschool children picture book recommendation method is used for recommending a new book which is suitable and meets the preference of a current user to the current user according to reading records of the current user and other similar users in a recorded picture book database.
The intelligent recommendation method comprises the following steps:
s1: and acquiring all the picture books which have been watched or shared by the current user and grading records thereof. Further, a read list A ═ A is obtained, which includes all the pictures and books that the current user has viewed or shared i 1 … … m, and its score list S i }，i＝1……m。
Wherein A is i Indicating that the current user has read or shared a picture book, S i Indicating that the current user is working on drawing book A i Scoring of (4); m represents the number of drawing books in the read list.
S2: acquiring all the picture books which have been already viewed or shared by all similar users of the current user and grading records thereof, and rejecting the picture books which have been already viewed or shared by the current user and are contained in the picture books. Further, a reference list B ═ B containing drawings which have been viewed or shared by all similar users is obtained j }，j＝1 … … n, and its score list V ═ V j }，j＝1……n。
Wherein, B j A picture book, V, representing that a similar user has read or has been shared but the current user has not read j Representing all similar users to the drawing book B j The score mean of (2); n denotes the number of drawings in the reference list B.
S3: and acquiring the labels of all the paintbooks in the read list A and the reference list B, and constructing a label similarity matrix E according to the label content of each paintbook.
The tag similarity matrix E is used for representing the similarity degree of the types of the pictures and books between the read list A and the reference list B; the tag similarity E is as follows:
wherein, the element L in the label similarity matrix E ij Presentation painting book A i And B j The label weight sum of the owned common labels.
S4: and fusing the tag similarity matrix E and the user scoring data of all the pictures in the read list A and the reference list B to generate a user preference matrix F.
The user preference matrix F is used for representing the preference degree of the current user to the picture books in the reference list B; the user preference matrix F is as follows:
wherein, the element W in the user preference degree matrix F ij Representing the predicted score value of the current user for the picture book in the reference list B calculated in combination with the scores of the different users and the tag similarity E.
S5: calculating each picture book B in the current user pair reference list B according to the user preference matrix F j Final preference score G j ，G j The calculation formula of (a) is as follows:
G j ＝max i＝1,...,m {W ij }。
s6: based on the final preference score G for each picture book in the reference list B j And reordering the paintings, selecting K paintings with the final preference top in ranking name, and pushing the K paintings to the current user in sequence to form the required recommended book pocket.
As a further improvement of the present invention, in step S1, the drawing book that the current user has already viewed refers to the drawing book that has been recorded in the current drawing book database and that has been read by the current user. The picture book shared by the current user refers to a picture book which is not included in the current picture book database but is read and shared by the current user. When any user shares the picture book, the basic information of the picture book and the user rating of the picture book must be uploaded to the current picture book database. The basic information of the drawing book includes: name, author, drawing book number, publication information, label, and cover image.
As a further improvement of the invention, the tags are used for marking the type information of the paintbooks, and the tag of each paintbook comprises the category of the paintbook and the attribute description customized by the user and related to the contents of the paintbook. The types of the picture books comprise scientific exploration, non-character type, bilingual type, living habit type, character formation type, human art type and black and white picture books.
User-customized property descriptions may include:
(1) and the keywords represent the length of the text content of the picture book.
(2) Keywords describing the content of the drawing insert.
(3) And the keywords represent the difficulty degree of reading the drawing book.
(4) Keywords that characterize the attributes of a character or plot in a picture book.
(5) Keywords describing drawing book winning information, such as: international anderson award, cadik award, fengzi-water drawing award, etc.;
(6) keywords describing the information of the drawing book publishing house;
(7) keywords that characterize the style of the drawing book material, such as: cloth books, three-dimensional books, etc.
As a further improvement of the present invention, in step S2, the similar user refers to a user of the same age/age group and the same gender as the current user. The age and gender of the user are actively uploaded by the user when registering the user account for accessing the current picture book database.
As a further improvement of the invention, in step S3, in the label similarity matrix E, the label weight sum L ij The calculation formula of (c) is as follows:
in the above formula, c represents a drawing book A i Or drawing book B j The label of (1); c represents a drawing book A i And drawing book B j The set of all of the tags that are present,
is used for judging whether the label c is a picture book A or not i And drawing book B j A discrimination function of the common label; n is a radical of hydrogen c Indicates the number of paintings having a common label c; p is a radical of formula c The influence weight of the label c is shown, and the influence of the label c is smaller when the number of drawings with the label c is larger.
As a further improvement of the present invention, in step S4, in the user preference degree matrix F, the score value W is predicted ij The calculation formula of (a) is as follows:
W ij ＝S i *V j *L ij 。
as a further improvement of the present invention, in step S6, in the reordering stage of the reference sequence B, the final preference score G of each book is used j For the sorting benchmark, any one sorting method of a bubble sorting method, a selection sorting method, an insertion sorting method, a Hill sorting method, a merging sorting method, a quick sorting method, a heap sorting method, a counting sorting method, a bucket sorting method and a radix sorting method is adopted, and the reference sequence B is sorted from large to small according to the final preference score.
The invention also comprises a preschool children picture book management system, and the preschool children picture book intelligent recommendation system comprises: the system comprises a background server and a user side.
The background server contains a picture book database. The data in the gallery database contains the contents and basic information of all the galleries included, as well as the reading records and evaluation results of each registered user for the included galleries. The picture book database also stores the basic information and user evaluation of picture books uploaded by any registered user and not recorded in the picture book database. The background server is also used for responding to the data access request of the authenticated registered user.
The user side is in communication connection with the background server. The user side is used for sending a data request to the server side according to the instruction of the registered user; and further, drawing book reading, historical browsing information statistics and drawing book recommendation services are provided for registered users.
Wherein, the functional module in the user side includes: the system comprises five parts of personal information management, drawing book reading, drawing book retrieval, drawing book sharing and drawing book recommendation.
The personal information management page is used for displaying the name, age, gender and other user information of the current user; meanwhile, on the page of personal information management, the user can edit the user information. The personal information management page can also display the reading history, the score of the picture book and the shared book of the user. The page for browsing the picture book is used for displaying the picture book selected by the registered user and providing the book full text browsing service for the user. The page of the drawing book retrieval is used for supporting a user to send a query request to all drawing books in the database, and the collected drawing books and the drawing books which are shared by the user but not collected are displayed in a column in the drawing book retrieval process. The picture book sharing page is used for displaying the detailed list of the picture book shared by the user and supporting the user to share the books which are read and recommended to be read by other users in the picture book database. When the picture book shared by the user belongs to a picture book which is not included in the picture book database, the user is also required to upload the basic information of the picture book and grade the user of the picture book. The basic information of the drawing book includes: name, author, drawing book number, publication information, label, and cover image. And the page recommended by the picture book is used for the display system to intelligently evaluate according to the reading and scoring records of the current user and other similar users, so that the picture book recommended to the current user is provided. The recommended book pocket formed by the recommended picture books is automatically generated by the preschool child picture book management system by adopting the intelligent picture book recommendation method for preschool children, and is actively displayed when a user enters a picture book recommendation page.
As a further improvement of the invention, the user needs to register an account number and upload user information when experiencing the related functions of the preschool children picture book management system. The user side provides related services only after the registered user logs in the account.
The background server is provided with a special manager for manually checking the information which is uploaded and shared by the user but is not included in the picture book database, and storing and displaying the related data after the manual checking is passed.
The invention also comprises a preschool child picture book reading device, wherein an application program for realizing the user side function in the preschool child picture book management system runs in the preschool child picture book reading device, and performs data interaction with the background server positioned at the cloud end when the program runs, so that picture book reading, picture book sharing or picture book recommendation service is provided for a user.
The invention provides an intelligent picture book recommendation method for preschool children, a picture book management system and reading equipment thereof, which have the following beneficial effects:
the method for recommending the picture books provided by the invention creatively constructs a new quantitative evaluation tool by taking the labels and the scores of the picture books which are read by the current user and the picture books which are read by other users with similar attributes as basic data, accurately predicts the evaluation of the current user on other unread picture books and sequentially serves as a basis for recommending new picture books.
The method for recommending the drawing books can automatically filter abnormal or improper drawing books and ensure that the recommended drawing books are all in compliance. In addition, the method provided by the invention integrates user evaluation and content evaluation into the evaluation index, and simultaneously considers a plurality of user attributes such as age, gender and the like, so that recommended paintings are all favored or useful by the user.
Particularly, the recommendation method provided by the invention can be applied to reading and selling of online picture books, and can also be applied to management of entity picture books. And is very suitable for being used as a recommendation method of pictures and paintings of children or students.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart illustrating steps of an intelligent pre-school children picture book recommendation method according to embodiment 1 of the present invention.
Fig. 2 is a data block diagram of an implementation process of the intelligent picture book recommendation method for the preschool children in embodiment 1 of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
The method is used for recommending a new book which is suitable and meets the preference of the current user to the current user according to the reading records of the current user and other similar users in the recorded drawing book database.
As shown in fig. 1, the intelligent recommendation method includes the following steps:
s1: and acquiring all the picture books which have been viewed or shared by the current user and grading records thereof. Further, a read list A ═ A is obtained, which includes all the pictures and books that the current user has viewed or shared i 1 … … m, and its score list S i }，i＝1……m。
Wherein A is i Indicating that the current user has read or shared a picture book, S i Indicating that the current user is working on drawing book A i Scoring of (4); m represents the number of books in the read list.
The picture book that the current user has seen refers to the picture book that has been collected in the current picture book database and read by the current user. The picture book shared by the current user refers to a picture book which is not included in the current picture book database but is read and shared by the current user.
When any user shares the picture book, the basic information of the picture book and the user rating of the picture book must be uploaded to the current picture book database. The basic information of the drawing book includes: name, author, drawing book number, publication information, label, and cover image.
The label in the basic information is mainly used for marking the type information of the picture book. The labels of each picture book include the category of the picture book and attribute descriptions customized by the user in relation to the contents of the picture book. The types of the drawing books comprise scientific exploration, non-character types, bilingual types, living habits, character formation types, human arts and black and white drawing books.
User-customized property descriptions may include:
(1) and the keywords represent the length of the text content of the picture book.
(2) Keywords describing the content of the drawing insert.
(3) And the keywords represent the difficulty degree of reading the drawing book.
(4) Keywords that characterize the attributes of a character or plot in a picture book.
(5) Keywords describing drawing book winning information, such as: international anderson award, cadik award, fengzi-water drawing award, etc.;
(6) keywords describing the gallery press information;
(7) keywords that characterize the style of the drawing book material, such as: cloth books, three-dimensional books, etc.
It is emphasized that there may be more than one label per book and that since the categories of books are not differentiated from a single dimension, the categories may not be just one in the notes of each book, for example, for a purely pictorial caricature that mainly represents a story of an allegian, it may be classified as both non-textual and human-artistic categories, thus having two category labels.
In addition, the attribute tags customized by the user are more free and richer than the type tags. The label can be a common label selected from a label library or a new label submitted by a user newly. For example, the user may add labels such as "songe", "fairy tale", "poetry", "stories of stories", comic "," sheep-like "," small flying man "," apprentice ", and the like, according to the subject matter, contents, and the like of the drawing book.
S2: acquiring all the paintings which have been watched or shared by all similar users of the current user and grading records thereof, and rejecting the paintings which have been watched or shared by the current user and are contained in the paintings. Further, a reference list B ═ B containing drawings which have been viewed or shared by all similar users is obtained j J 1 … … n, and its score list V j }，j＝1……n。
Wherein, B j A picture book, V, representing that a similar user has read or has been shared but the current user has not read j Representing all similar users to a drawing book B j The score mean of (a); n denotes the number of drawing books in the reference list B.
Similar users refer to users of the same age/age group and gender as the current user. The age and gender of the user are actively uploaded by the user when registering the user account for accessing the current picture book database.
The method of the embodiment uses the age and the gender as hard indexes for distinguishing different users, and is also a criterion for determining the influence weight of the recommendation purposes of different users in the later period. Therefore, the method of the present embodiment divides the ages very finely, and not only divides the ages, but also divides the users according to the months, even when the ages are smaller, considering that the comprehension abilities of different users may be different greatly. Accordingly, when the age of the user is relatively large, considering that the difference in the comprehension abilities of children of different ages is small at this time, the division is not performed according to the month, but only according to the age group. Therefore, the fineness and the matching degree of the method for recommending the books to different users can be improved.
S3: and acquiring the labels of all the paintbooks in the read list A and the reference list B, and constructing a label similarity matrix E according to the label content of each paintbook.
The tag similarity matrix E is used for representing the similarity degree of the types of the pictures and books between the read list A and the reference list B; tag similarity E is as follows:
wherein, the element L in the label similarity matrix E ij Presentation painting book A i And B j The tag weight sum of the owned common tags.
Tag weight and L ij The calculation formula of (a) is as follows:
in the above formula, c represents a drawing book A i Or drawing book B j The label of (1); c represents a drawing book A i And drawing book B j The set of all of the tags that are present,
is used for judging whether the label c is a picture book A or not i And drawing book B j A discrimination function of the common label of (1); n is a radical of c Representing the number of paintbooks having a common label c; p is a radical of c The influence weight of the label c is shown, and the influence of the label c is smaller as the number of drawings having the label c is larger.
In the embodiment, the similarity degree of the contents between the read and unread paintings of the user is quantified by adopting a brand-new defined label similarity matrix, and the coincidence degree of label information between different paintings can be used as feature information of one dimension for recommending the paintings at the later stage.
In addition, it should be particularly noted that, in this embodiment, in addition to the currently defined album label, when the label similarity is calculated, the album shared by the current user is also used as an extended category label to participate in the calculation, so that the calculation process of the similarity is fused with the album sharing information of the current user.
S4: and fusing the tag similarity matrix E and the user scoring data of all the pictures in the read list A and the reference list B to generate a user preference matrix F.
The user preference matrix F is used for representing the preference degree of the current user to the picture books in the reference list B; the user preference matrix F is as follows:
wherein, the element W in the user preference degree matrix F ij Representing the predicted score value of the current user for the picture book in the reference list B calculated in combination with the scores of the different users and the tag similarity E. Specifically, the prediction score value W ij The calculation formula of (a) is as follows:
W ij ＝S i *V j *L ij 。
in this embodiment, the user preference matrix is actually a scoring table used to quantify the current user preference for the picture books in the reference list. The calculation process of the scoring table takes into account the label similarity between the unread picture books and the read picture books; i.e. embodying these drawings "look unlike". The scoring of read paintings by the current user is also considered, as well as the scoring of unread paintings by other similar users. Namely embodying the 'good and bad' of the paintings. Therefore, the prediction score value included in the user preference matrix constructed by the present embodiment should be a data index with high reliability.
S5：Calculating each picture book B in the current user pair reference list B according to the user preference matrix F j Final preference score G j ，G j The calculation formula of (c) is as follows:
G j ＝max i＝1,...,m {W ij }。
in the user preference degree matrix of the present embodiment, each data in each column represents preference degree evaluation made on a currently-prepared recommended drawing book according to one of the read drawings books of the current user, respectively. And the calculation process of the final preference score mainly comprises the steps of selecting the highest preference score of the current user for the picture book according to columns in the matrix, and taking the highest preference score as the final prediction evaluation of the current user for the corresponding picture book.
S6: based on the final preference score G for each picture book in the reference list B j And reordering the paintings, selecting K paintings with the final preference top in ranking name, and pushing the K paintings to the current user in sequence to form the required recommended book pocket.
In the reordering stage of reference sequence B, the final preference of each book can be divided into G j And arranging the reference sequence B in the order from large to small according to the final preference score by adopting any one of a bubble ordering method, a selection ordering method, an insertion ordering method, a Hill ordering method, a merging ordering method, a quick ordering method, a heap ordering method, a counting ordering method, a barrel ordering method and a radix ordering method as an ordering standard.
The number of pictures recommended in the recommended bag can be set by the user. For example, when the user chooses to recommend 10 books each time, the top 10 books in the reordered reference list are recommended to the user.
As shown in fig. 2, the overall working logic of the method for recommending a picture book in this embodiment is as follows:
firstly, comparing the book list read by the user (defined as the read book list) with the book list read by the similar user (defined as the unread book list), and solving for the difference between the two book lists, and reserving the picture book which is not seen by the current user but is seen by the similar user to form a reference book list. And then constructing a label similarity matrix according to the book notes of the reference book list and the read book list, and fusing different user scores in the reference book list and the read book list and the label similarity matrix to obtain a user preference matrix. And processing the elements in the user preference degree matrix to obtain the final user score of each book in the reference book list. And finally, reordering the reference book lists according to the final user scores of each book, and selecting the first books in the reordered reference book lists as recommended book bags recommended to the current user for reading.
The picture book recommendation method provided by the embodiment can be applied to the recommendation of electronic picture books on line and also can be applied to the recommendation of entity picture books collected in a library under the line. The management mode of the system is different from that of the existing entity picture book borrowing system, and the management mode only comprises the following steps: in order to implement the recommendation method, after the user finishes reading any drawing book, the user needs to feed back the score of the user on the drawing book to the book manager. In addition, for younger children, the guardian can also process the part of the work.
Example 2
On the basis of embodiment 1, this embodiment further provides a preschool child picture book management system. This preschool children picture book intelligence recommendation system includes: the system comprises a background server and a user side. The background server contains a picture book database. The data in the gallery database contains the contents and basic information of all the galleries included, as well as the reading records and evaluation results of each registered user for the included galleries. The picture book database also stores the basic information and user evaluation of picture books uploaded by any registered user and not recorded in the picture book database. The background server is also used for responding to the data access request of the authenticated registered user. The user side is in communication connection with the background server. The user side is used for sending a data request to the server side according to the instruction of the registered user; and further, drawing book reading, historical browsing information statistics and drawing book recommendation services are provided for registered users.
Wherein, functional module in the user side includes: the system comprises five parts, namely personal information management, drawing book reading, drawing book retrieval, drawing book sharing and drawing book recommendation.
The personal information management page is used for displaying the name, age, gender and other user information of the current user; meanwhile, on the page of personal information management, the user can edit the user information. The personal information management page can also be used for counting and displaying the reading history, the score of the picture books and the shared books of the user. But the reading history, the score of the picture book and the shared book shown on the page only contain brief information; if the detailed information needs to be known, the corresponding object needs to be clicked to jump to other page queries.
The page for reading the picture book is used for displaying the picture book selected by the registered user and providing the book full text reading service for the user. The page is equivalent to a local library in other online reading systems or equipment; in practical application, the bookshelf can be used for displaying; meanwhile, the user is supported to set or operate personalized functions such as a page turning mode, a background color, one-key direct at a historical reading position, page skipping and the like on the page. Of course, the picture book that the user is reading shown on the page can also provide the function options of online downloading and offline reading, etc.
The page of the picture book retrieval is used for supporting the query request sent by the user to all picture books in the database. In consideration of the fact that the database of the drawing books of the embodiment can support the 'shared book' actively uploaded by the user, the system displays the collected drawing books and the drawing books shared by the user but not collected in a column mode in the process of drawing book retrieval. For the collected picture books, after the picture books are retrieved, basic information, user comments and full-text browsing can be viewed, and for the picture books which are not collected, the users are only allowed to view the uploaded basic information and share the evaluation of the books by the users.
The picture book sharing page is used for displaying the detailed list of the picture book shared by the user and supporting the user to share the books which are read and recommended to be read by other users in the picture book database. When the picture book shared by the users belongs to a picture book which is not recorded in the picture book database, the users are required to upload the basic information of the picture book and grade the users of the picture book. The basic information of the drawing book in this embodiment includes: name, author, drawing book number, publication information, label, and cover image.
And the page recommended by the picture book is used for the display system to intelligently evaluate according to the reading and scoring records of the current user and other similar users, so that the picture book recommended to the current user is provided. The recommended book pocket formed by the recommended picture book is automatically generated by the preschool child picture book management system by adopting the intelligent picture book recommendation method for preschool children as in the embodiment 1, and is actively displayed when the user enters the picture book recommendation page.
It should be noted that, in order to facilitate collecting the book reading data of each user, the service is provided for other users. The pre-school children picture and painting management system provided by the embodiment requires that all users need to register accounts and upload user information when experiencing the relevant functions of the system. The user side provides related services only after the registered user logs in the account.
In the system provided by this embodiment, the background server has a special manager to perform manual review on the information that is uploaded and shared by the user but is not included in the drawing book database, and store and display the relevant data after the manual review is passed. Therefore, users are prevented from sharing wrong data or uploading illegal reading materials, and further influences on other users are avoided.
In practical applications, the pre-school children drawing book management system provided by this embodiment may be implemented by using an APP on the basis of an online reading web page or a mobile terminal, or may be implemented by using an online management platform on the basis of an existing physical drawing library. Even a management system based on an online book sales platform (such as amazon, the current network, the kyoto and the like), and further only provides a picture book recommendation service. The embodiment is not limited to the specific form for implementing the embodiment.
Example 2
On the basis of embodiments 1 and 2, the present embodiment further provides a preschool child picture book reading device, which is an online reading terminal device. I.e. an electronic book reader. He may be a desktop reading device such as a networked on-line reader like a gallery. Or it may be hand-held, such as a product like a tablet, a cell phone, an electronic book, or other online reading terminal. The terminal device has the capability of fully implementing the user-side function as in embodiment 2.
Specifically, the online reading terminal device in this embodiment may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including an independent server or a server cluster formed by multiple servers) capable of executing programs, and the like. The computer device of the embodiment at least includes but is not limited to: a memory and a processor communicatively coupled to each other via a system bus.
In this embodiment, the memory (i.e., the readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the computer device. Of course, the memory may also include both internal and external storage devices for the computer device. In this embodiment, the memory is generally used for storing an operating system, various types of application software, and the like installed in the computer device. In addition, the memory may also be used to temporarily store various types of data that have been output or are to be output.
The processor may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments.
The processor is typically used to control the overall operation of the computer device. In this embodiment, the processor is configured to run a program code stored in the memory or process data, and then execute an application program of a user side function in the pre-school children's drawing book management system in embodiment 1 when running the program, and perform data interaction with the background server located in the cloud when running the program, thereby providing a drawing book reading, drawing book sharing, or drawing book recommendation service for the user.
It is emphasized that the terminal device provided by the present embodiment needs to have a networking function to support communication and data interaction with the backend server. And has a separate display or does not have a function of connecting the display with other displays.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An intelligent preschool children picture book recommendation method is used for recommending a new book which is suitable and meets the preference of a current user to the current user according to reading records of the current user and other similar users in a recorded picture book database; it is characterized in that the preparation method is characterized in that,
the intelligent recommendation method comprises the following steps:
s1: acquiring all picture books which have been viewed or shared by a current user and grading records thereof; further, a read list A ═ A is obtained, which includes all the pictures and books that the current user has viewed or shared i 1 … … m, and its score list S i }，i＝1……m；
Wherein A is i Indicating the current picture book that the user has read or shared, S i Representing current user pairing graphPainting and calligraphy A i Scoring of (4); m represents the number of picture books in the read list;
s2: acquiring all the paintings which have been watched or shared by all similar users of the current user and grading records thereof, and rejecting the paintings which have been watched or shared by the current user and are contained in the paintings; further, a reference list B ═ B containing drawings which have been viewed or shared by all similar users is obtained j J 1 … … n, and its score list V j }，j＝1……n；
Wherein, B j A picture book, V, representing that a similar user has read or has been shared but the current user has not read j Representing all similar users to the drawing book B j The score mean of (a); n represents the number of drawings in the reference list B;
s3: acquiring tags of all picture books in the read list A and the reference list B, and constructing a tag similarity matrix E according to the tag content of each picture book, wherein the tag similarity matrix E is used for representing the type similarity of the picture books between the read list A and the reference list B;
wherein, the element L in the label similarity matrix E ij Presentation painting book A i And B j The label weight sum of owned common labels;
s4: fusing the tag similarity matrix E and user scoring data of all the paintings in the read list A and the reference list B to generate a user preference matrix F, wherein the user preference matrix F is used for representing the preference degree of the current user to the paintings in the reference list B;
wherein, the element W in the user preference degree matrix F ij Representing the current user paramedics calculated in combination with the scores and tag similarities E of different usersTaking into account the predicted score value of the picture book in the list B;
s5: calculating each picture book B in the current user pair reference list B according to the user preference matrix F j Final preference score G j ，G j The calculation formula of (a) is as follows:
G j ＝max i＝1,...,m {W ij }；
s6: based on the final preference score G for each picture book in the reference list B j And reordering the paintings, selecting K paintings with the final preference top in ranking name, and pushing the K paintings to the current user in sequence to form the required recommended book pocket.
2. The intelligent preschool child picture book recommendation method of claim 1, wherein: in step S1, the drawing book that the current user has already viewed means the drawing book that has been received and recorded in the current drawing book database and that has been read by the current user; the picture book shared by the current user refers to a picture book which is not recorded in the current picture book database but is read and shared by the current user; when any user shares the picture book, the basic information of the picture book must be uploaded to a current picture book database and the user rating of the picture book must be carried out; the basic information of the drawing book includes: name, author, drawing book number, publication information, label, and cover image.
3. The intelligent preschool child picture book recommendation method of claim 2, wherein: the labels are used for marking the type information of the paintbooks, and the label of each paintbook comprises the category of the paintbook and the attribute description customized by a user and related to the content of the paintbook; the types of the picture books comprise scientific exploration, non-character types, bilingual types, living habits, character formation types, human arts and black and white picture books; the user-defined attribute description comprises the following steps:
(1) key words representing the length of the text content of the picture book;
(2) keywords describing the picture content of the drawing book;
(3) key words representing the difficulty of reading the picture book;
(4) keywords representing attributes of characters or plots in the picture book;
(5) keywords describing drawing book winning information;
(6) keywords describing the gallery press information;
(7) and keywords representing the material style of the picture book.
4. The intelligent preschool child picture book recommendation method of claim 1, wherein: in step S2, the similar user refers to a user of the same age/age group and the same gender as the current user; the age and gender of the user are actively uploaded by the user when registering the user account for accessing the current picture book database.
5. The intelligent preschool child picture book recommendation method of claim 4, wherein: in step S3, in the label similarity matrix E, the label weight sum L ij The calculation formula of (a) is as follows:
in the above formula, c represents a drawing book A i Or drawing book B j The label of (1); c represents a drawing book A i And drawing book B j The set of all of the tags that are present,
is used for judging whether the label c is a picture book A or not i And drawing book B j A discrimination function of the common label of (1); n is a radical of c Indicates the number of paintings having a common label c; p is a radical of formula c The influence weight of the label c is shown, and the influence of the label c is smaller when the number of drawings with the label c is larger.
6. The intelligent preschool child picture book recommendation method of claim 1, wherein: in step S4In the user preference matrix F, the predicted score value W ij The calculation formula of (c) is as follows:
W ij ＝S i *V j *L ij 。
7. the intelligent preschool children picture book recommendation method according to claim 1, wherein in step S6, in the reordering stage of the reference sequence B, the final preference score G of each book is used j For the sorting benchmark, any one sorting method of a bubble sorting method, a selection sorting method, an insertion sorting method, a Hill sorting method, a merging sorting method, a quick sorting method, a heap sorting method, a counting sorting method, a bucket sorting method and a radix sorting method is adopted, and the reference sequence B is sorted from large to small according to the final preference score.
8. The utility model provides a preschool children's picture book management system which characterized in that, preschool children's picture book intelligence recommendation system includes:
the background server comprises a picture book database, wherein the data in the picture book database comprises the contents and the basic information of all the recorded picture books, and the reading record and the evaluation result of each registered user on the recorded picture books; the picture book database also stores the basic information and user evaluation of picture books uploaded by any registered user and not recorded in the picture book database; the background server is also used for responding to the data access request of the authenticated registered user;
the user side is in communication connection with the background server and is used for sending a data request to the server side according to the instruction of the registered user so as to provide services of drawing book reading, historical browsing information statistics and drawing book recommendation for the registered user; the functional modules in the user side comprise: personal information management, drawing book reading, drawing book retrieval, drawing book sharing and drawing book recommendation; the personal information management page is used for displaying the name, age and sex of the current user and other user information, and displaying the reading history, the score of the picture book and the shared book of the user; the page for reading the picture book is used for displaying the picture book selected by the registered user and providing book full text reading service for the user; the page of the drawing book retrieval is used for supporting a user to send a query request to all drawing books in the database, and the collected drawing books and the drawing books shared by the user but not collected are displayed in columns in the drawing book retrieval process; the picture book sharing page is used for displaying the detailed list of the picture book shared by the user and supporting the user to share the books which are read and recommended to be read by other users in the picture book database; when the picture book shared by the user belongs to a picture book which is not included in the picture book database, the user is also required to upload the basic information of the picture book and grade the user of the picture book; the basic information of the drawing book includes: name, author, drawing book number, publishing information, label, and cover image; the page recommended by the picture book is used for the display system to perform intelligent evaluation according to the reading and scoring records of the current user and other similar users, and then the picture book recommended to the current user; the recommended book pocket formed by the recommended picture book is automatically generated by the preschool child picture book management system by adopting the intelligent preschool child picture book recommendation method as claimed in any one of claims 1 to 7, and is actively displayed when a user enters a picture book recommendation page.
9. The preschool child picture book management system of claim 8, wherein: the method comprises the steps that a user needs to register an account number when experiencing related functions of a pre-school children picture and book management system, and uploads user information; the user side provides related services only after registering a user login account;
the background server is provided with a special manager for manually checking the information which is uploaded and shared by the user but is not included in the picture book database, and storing and displaying the related data after the manual checking is passed.
10. The utility model provides a preschool children's drawing book reading equipment which characterized in that: the preschool child picture book reading device runs an application program for realizing a user side function in the preschool child picture book management system according to any one of claims 8 or 9, and performs data interaction with the background server located at the cloud end when the program runs, so that picture book reading, picture book sharing or picture book recommendation services are provided for a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210676391.3A CN115033805A (en) | 2022-06-15 | 2022-06-15 | Preschool children picture book intelligent recommendation method and picture book management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210676391.3A CN115033805A (en) | 2022-06-15 | 2022-06-15 | Preschool children picture book intelligent recommendation method and picture book management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115033805A true CN115033805A (en) | 2022-09-09 |
Family
ID=83125576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210676391.3A Pending CN115033805A (en) | 2022-06-15 | 2022-06-15 | Preschool children picture book intelligent recommendation method and picture book management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115033805A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116401466A (en) * | 2023-06-08 | 2023-07-07 | 北京奇趣万物科技有限公司 | Book classification recommendation method and system |
-
2022
- 2022-06-15 CN CN202210676391.3A patent/CN115033805A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116401466A (en) * | 2023-06-08 | 2023-07-07 | 北京奇趣万物科技有限公司 | Book classification recommendation method and system |
| CN116401466B (en) * | 2023-06-08 | 2023-11-03 | 北京奇趣万物科技有限公司 | Book classification recommendation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Boiko | Content management bible | |
| Lurie et al. | Visual representation: Implications for decision making | |
| US10019531B2 (en) | System and method for displaying, connecting and analyzing data in an online collaborative webpage | |
| CN112711937A (en) | Template recommendation method, device, equipment and storage medium | |
| US20090300547A1 (en) | Recommender system for on-line articles and documents | |
| US20200097538A1 (en) | Book analysis and recommendation | |
| US20230214895A1 (en) | Methods and systems for product discovery in user generated content | |
| CN106716402A (en) | Entity-centric knowledge discovery | |
| US20240061887A1 (en) | Information search method and apparatus, computer device and storage medium | |
| CN102549563A (en) | Semantic exchange | |
| JP2010118064A (en) | Computer implemented method | |
| US20200226168A1 (en) | Methods and systems for optimizing display of user content | |
| WO2010085874A1 (en) | Recommender system for on-line articles and documents | |
| US20230030560A1 (en) | Methods and systems for tagged image generation | |
| Gerolimos | Tagging for libraries: a review of the effectiveness of tagging systems for library catalogs | |
| Ndumbaro | Understanding user-system interactions: An analysis of OPAC users’ digital footprints | |
| CN115033805A (en) | Preschool children picture book intelligent recommendation method and picture book management system | |
| JP7133674B1 (en) | Information processing device, information processing method and information processing program | |
| Feldman | The answer machine | |
| US20120136815A1 (en) | Display Device and Display Method | |
| US20180330422A1 (en) | Recommender systems and methods for pricing and evaluation of fine art works | |
| US20180165741A1 (en) | Information providing device, information providing method, information providing program, and computer-readable storage medium storing the program | |
| US20180067985A1 (en) | Spiritual Research System and Method | |
| CN116521937A (en) | Video form generation method, device, equipment, storage medium and program product | |
| Kim et al. | # ShoutYourAbortion on Instagram: exploring the visual representation of hashtag movement and the public’s responses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |