CN114969564A - Grading reading evaluation and recommendation method and system for books outside class of primary school - Google Patents
Grading reading evaluation and recommendation method and system for books outside class of primary school Download PDFInfo
- Publication number
- CN114969564A CN114969564A CN202210623160.6A CN202210623160A CN114969564A CN 114969564 A CN114969564 A CN 114969564A CN 202210623160 A CN202210623160 A CN 202210623160A CN 114969564 A CN114969564 A CN 114969564A
- Authority
- CN
- China
- Prior art keywords
- book
- books
- class
- school
- primary school
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims abstract description 6
- 238000012417 linear regression Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 12
- 230000001419 dependent effect Effects 0.000 claims description 7
- 238000013210 evaluation model Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 2
- 229910052739 hydrogen Inorganic materials 0.000 claims 1
- 239000001257 hydrogen Substances 0.000 claims 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 claims 1
- 238000011160 research Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000556 factor analysis Methods 0.000 description 3
- 210000001747 pupil Anatomy 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012938 design process Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000011218 segmentation 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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 discloses a method and a system for grading reading evaluation and recommendation of books outside class of primary schools; wherein, the method comprises the following steps: selecting three books suitable for the primary school from the out-of-class books, and constructing a library of out-of-class reading books of the primary school; starting from three comprehensive characteristics of book diversity, book complexity and book connectivity, analyzing and judging to obtain five layers of various characteristics of pictures, Chinese characters, words, sentences and sections and chapters as alternative characteristic sets of the grading reading evaluation method of the books outside class of the primary school; screening out optimal comprehensive characteristics by using data analysis software to construct a grading reading evaluation method for books outside the class of the primary school; the method is characterized in that the applicable learning sections of books predicted by the out-of-class book grading reading evaluation method of the primary school are applied to the process of calculating the similarity of users by a collaborative filtering recommendation algorithm, the similarity between the users is calculated by adopting a Pearson correlation coefficient calculation method, and then the prediction score of the users on unscored books is calculated. The invention optimizes the performance of the out-of-class book recommendation system.
Description
Technical Field
The invention belongs to the technical field of natural language processing, and mainly relates to a primary school extracurricular book grading reading evaluation and recommendation method and a primary school extracurricular book grading reading recommendation system.
Background
Reading ability is a necessary and important ability that is at the base and core of human development, especially for elementary school students, where reading promotes a comprehensive development of its mental, ethical and aesthetic levels. In the face of an intricate book sea, how to recommend out-of-class books matched with the reading capacity of the section of the student becomes a difficult problem in front of broad teachers and parents. The hierarchical reading can provide a thought for solving the difficult problem, the hierarchical reading aims to adapt the reading capability and the text difficulty of the section where the reader is located, and the hierarchical reading evaluation system aiming at English, such as a Lexile reading frame, an A-Z classification method and the like, is relatively perfected into a system through long-term practice and development, and is high in popularization degree. Domestic hierarchical reading research starts late, and the proposal of a mature reading system is lacked, most of the research stays on qualitative recommendation, quantitative research is lacked, and the problem of book recommendation outside primary schools cannot be really solved.
The main task of the hierarchical reading evaluation system is to predict the difficulty of the text, so that reading materials matched with the reading capability of a specific reader are recommended to the specific reader, and the reading capability of the reader is improved. The text readability refers to the degree and the nature of the text which is easy to read and understand, is an important component of hierarchical reading, is mainly focused on the mother language teaching field and the external Chinese teaching aspect in application, the study aiming at the readability of the text of the primary and secondary schools is focused on the Chinese textbook level, and the study on the readability of the text read outside the primary and secondary schools is to be explored. Therefore, research is conducted on grading reading evaluation and recommendation of the primary school out-of-class books, the out-of-class book with text difficulty matched with the school class is recommended for the primary school students, and the improvement of reading capability of the out-of-class book is cultivated and has important significance.
The study on the readability of the Chinese text mainly aims at teaching and in-class study, the size of a corpus constructed by the study is relatively limited, and the credibility of the corpus is to be verified. Secondly, the evaluation standards for the Chinese text difficulty provided by the readability of the Chinese text are inconsistent, the selected text has more characteristics and complex form, the method is not easy to popularize, and the actual application performance needs to be verified.
Under the scene of hierarchical book recommendation outside primary schools, when recommendation is performed by a traditional collaborative filtering recommendation algorithm, the similarity of users needs to be calculated after traversing the scoring data of all books, so that the calculated data is not only low in accuracy rate, but also consumes a large amount of computing power along with the increase of the data. In addition, when information which is increasingly increased in geometric magnitude order is faced, how to recommend and acquire resources meeting user requirements from mass information resources becomes a problem of needing important attention, especially in the field of book recommendation of pupils out of class, at the present stage, people do not lack excellent works and readers who love good reading books, and the key is how to recommend a good book to students in the most suitable school segment, so that the reading capability is substantially improved.
Disclosure of Invention
The invention aims to solve the problem that books for reading outside class of primary schools are difficult to match with applicable school classes and optimize the performance of an outside class book recommendation system.
In order to achieve the above object, in one aspect, the present invention provides a method for grading reading evaluation and recommendation of books outside class of primary school, comprising the following steps:
selecting three books suitable for the primary school from the out-of-class books, and constructing a library of out-of-class reading books of the primary school;
starting from three comprehensive characteristics of book diversity, book complexity and book connectivity, analyzing, studying and judging to obtain five levels of pictures, Chinese characters, vocabularies, sentences and chapters and various characteristics as an alternative characteristic set of the grading reading evaluation method of books outside class of primary school;
screening out optimal comprehensive characteristics by using data analysis software to construct a grading reading evaluation method for books outside the class of the primary school;
the method is characterized in that the applicable learning sections of books predicted by the out-of-class book grading reading evaluation method of the primary school are applied to the process of calculating the similarity of users by a collaborative filtering recommendation algorithm, the similarity between the users is calculated by adopting a Pearson correlation coefficient calculation method, and then the prediction score of the users on unscored books is calculated.
On the other hand, the invention provides a grading reading evaluation and recommendation system for books outside a class in primary schools, which comprises the following components: the book recommendation system comprises a user management module, a book management module, a registration login module, a personal center module and a book recommendation functional module, wherein the book recommendation functional module is used for executing a grading reading evaluation and recommendation method of books outside a primary school.
The invention can solve the problem that the text content of the primary school extraclass books is not matched with the applicable school section, and can accurately solve the problem of the matching degree of the primary school extraclass book recommendation and the applicable school section.
Drawings
FIG. 1 is a schematic flow chart of a method for grading reading evaluation and recommendation of an out-of-class book in an elementary school according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the design process of the out-of-class book evaluation method for primary schools;
fig. 3 is a schematic structural diagram of a book recommendation system for reading outside of a school based on text content.
Detailed Description
Fig. 1 is a schematic flow chart of a method for grading reading evaluation and recommendation of an extra-class book of an elementary school according to an embodiment of the present invention. As shown in FIG. 1, the method includes steps S101-S104:
step S101, selecting three books suitable for the primary school from the out-of-class books, and constructing a library of out-of-class reading books of the primary school;
specifically, the embodiment of the invention is based on the basic course development center of the education department and recommended books of middle and primary schools and recommended books of libraries of middle and primary schools all over the country as the out-of-class book selection standard, three suitable books of the primary school are selected from the out-of-class books, and a library of the out-of-class reading books of the primary school is constructed.
The existing research on Chinese readability formulas mainly selects characteristics from four different levels, namely Chinese character level characteristics, vocabulary level characteristics, sentence level characteristics and chapter level characteristics, does not comprehensively consider whether the characteristics of all levels have relevance and commonality, and does not provide characteristics with stronger comprehensive generalization capability to construct readability formulas.
In addition, in the grading evaluation of the books read outside the class in the primary school, the characteristics of the picture layer are not ignored, the pictures are related to the books read outside the class in each school section in the primary school, and especially, the books drawn in the books read outside the class occupy a larger proportion in the low school section in the primary school.
And S102, analyzing, studying and judging three comprehensive characteristics of book diversity, book complexity and book connectivity to obtain five levels of various characteristics of pictures, Chinese characters, vocabularies, sentences and sections as an alternative characteristic set of the grading reading evaluation method of the books outside the class of the primary school.
The embodiment of the invention starts from three comprehensive characteristics of book diversity, book complexity and book connectivity, selects 59 characteristics as alternative characteristic sets at five levels of pictures, Chinese characters, vocabularies, sentences, chapters and the like through research and analysis, and utilizes a multivariate linear regression model for fitting.
Diversity about books
The diversity characteristics of the book are mainly formed by fitting 18 characteristics of picture diversity, Chinese character diversity, vocabulary diversity, sentence diversity, chapter diversity and the like through a multiple linear regression model. Table 1.1 is a table of the diversity characteristic information of books.
TABLE 1.1 book diversity characteristic information Table
Second, complexity with respect to books
The complexity of the book is mainly formed by fitting 25 characteristics such as the complexity of pictures, the complexity of Chinese characters, the complexity of vocabularies, the complexity of sentences, the complexity of chapters and the like through a multiple linear regression model. Table 2.2 is a complexity characteristic information table of the book.
TABLE 2.2 complexity characteristics information Table of books
Third, linking property of book
The book connectivity is mainly formed by fitting 16 characteristics of picture connectivity, Chinese character connectivity, vocabulary connectivity, sentence connectivity, chapter connectivity and the like through a multiple linear regression model. Table 2.3 is a table of the engagement characteristics of the books.
TABLE 2.3 Linked characteristic information Table of books
The embodiment of the invention uses the basic course development center based on the education department, recommended books about middle and primary schools and recommended books about libraries (rooms) of national middle and primary schools as the selection standard of the out-of-class books, and the constructed out-of-class book corpus of the primary school reading is used for fitting the grading evaluation model of the out-of-class reading books of the primary school, so that the model is more accurate and credible. In order to effectively improve the accuracy and the credibility of the primary school class-outside book grading evaluation model, the embodiment of the invention starts from three comprehensive characteristics of book diversity, book complexity and book connectivity, selects 59 characteristics as alternative characteristic sets on five levels of pictures, Chinese characters, vocabularies, sentences, chapters and the like through research and analysis, and utilizes a multivariate linear regression model to fit the primary school class-outside book grading reading evaluation model.
S103, screening out optimal comprehensive characteristics by using data analysis software to construct a grading reading evaluation method for books outside class of primary schools;
specifically, the embodiment of the invention applies a multiple linear regression model to the three screened comprehensive characteristics to fit a grading evaluation model of books read outside the primary school.
Specifically, as shown in fig. 2, a word segmentation tool and a Python data processing program in the aspect of natural language processing are used to extract text features of a book outside a class of a primary school, then 59 text feature sets are extracted and screened, factor analysis is mainly performed through a Social science statistics software Package (Solutions Statistical Package for the Social Sciences, SPSS for short) SPSS software, a correlation coefficient matrix among variables is explored on the basis of a dimension reduction idea, the variables are grouped according to the magnitude of the correlation of the variables, and a plurality of variables are aggregated into a small number of common factors, so that the difficulty of data acquisition and analysis is reduced. The factorial analysis requires that the correlation coefficient of the variables is greater than 0 and that the KMO test and Bartiett's sphericity test be satisfied.
And then carrying out factor analysis on the text features to obtain a correlation coefficient r between the text features and the applicable learning sections, sorting according to the magnitude of absolute values, carrying out multiple linear diagnosis by adopting a variance expansion factor method, and judging that the candidate features do not have the problem of collinearity if a variance expansion factor (VIF) is less than 10. Simultaneously calculating the unique explanation (delta R) of the feature added with the candidate feature set on the dependent variable applicable discipline section 2 ) If Δ R 2 >2%, the feature is retained, otherwise the feature is deleted from the candidate feature set.
Fitting a regression model, wherein the selected text characteristics are used as independent variables, the applicable learning section is used as a dependent variable, and fitting of a linear regression model is performed, wherein the fitted model has a main evaluation index with a complex correlation coefficient R and reflects the linear correlation degree between all independent variables and the dependent variable, and the larger the value of the complex correlation coefficient R is, the closer the linear correlation is; determining the coefficient R 2 The closer the R-square is to 1, the more suitable the model is for the data; adjusted R 2 Indicating the adjusted decision coefficient, whichAnd is also one of the important standard indexes for good model fitting.
The model is then subjected to an overall regression effect F test, which essentially tests the overall significance of the linear regression equation for the significance of the linear relationship between the explanatory variables and all of the explanatory variables and determines whether it is appropriate to fit the relationship between these variables with a linear model. Significance detection can only be passed if the model's significance is <0.05, and if not, then re-fitting using non-linear regression needs to be considered.
Then, a model regression coefficient T test needs to be carried out, whether each introduced variable has influence or not and whether the influence is significant or not needs to be considered in the constructed multiple regression model, whether the variable is kept in the model or not is finally determined, and it is generally considered that if the significance value of the variable is less than 0.05, the variable is represented to have statistical significance. If the regression coefficient T test is not passed, the characteristics of the text need to be screened again, and the steps are executed again.
After the steps are carried out, a multiple linear regression model can be output, in order to check whether the model effect is obvious or not, the constructed evaluation method of the reading books outside the primary school needs to be verified by using a test data set, and the accuracy of the evaluation performance of the evaluation method is tested.
And calculating a complex correlation coefficient R of the model through SPSS software, wherein the complex correlation coefficient R reflects the linear correlation degree between all independent variables and dependent variables, and calculating a decision coefficient R square and an adjusted R square, which are important indexes for measuring good model fitting. The model is then subjected to an overall regression effect F test, which examines whether the linear relationships between the explanatory variables and all of the explanatory variables are significant, and determines whether it is appropriate to fit the relationships between these variables with a linear model. And finally, carrying out regression coefficient T test on the model, and testing the significance of each variable to a dependent variable to obtain the grading reading evaluation method of the books outside the primary school.
Y＝αL 1 +βL 2 +γL 3 ++C
Wherein Y is the applicable school paragraph, L 1 For book diversity, L 2 To book complexity, L 3 For book engageability, C is the bias term. Alpha is the coefficient of the diversity of the book, beta is the coefficient of the complexity of the book, and gamma is the coefficient of the connectivity of the book.
The multivariate linear regression model is used for determining the optimal combination among a plurality of independent variables through SPSS software to predict and evaluate the optimal section, and the final obtained grading reading and evaluating method for the books outside the primary school is more effective and accords with the actual condition through a series of operations such as text feature extraction, text feature screening, factor analysis, fitting of a regression model, model F inspection, regression coefficient T inspection and the like.
And step S104, applying the applicable school segments of the books predicted by the out-of-class book grading reading evaluation method of the primary school to the process of calculating the similarity of the users by the collaborative filtering recommendation algorithm, calculating the similarity between the users by adopting a Pearson correlation coefficient calculation method, and then calculating the prediction value of the users to the unscored books.
The traditional collaborative filtering recommendation algorithm is suitable for occasions where the number of articles is obviously smaller than the number of users, and if the articles are too large, the cost is very high when a similarity matrix is calculated, so that the algorithm needs to be improved in the process of recommending books outside a class of primary schools.
The improved recommendation algorithm mainly applies the applicable learning segment of the books predicted by the class reading evaluation method of the extra-class books of the primary school to the process of calculating the similarity of the users by the collaborative filtering recommendation algorithm, calculates the similarity between the users by adopting a Pearson correlation coefficient calculation method, and then calculates the predicted value of the users to the unscored books, and the calculation method is as follows:
wherein i represents the ith book; i is u A book set representing user u's rating at a certain school passage; i is v A book collection representing user v's rating at a certain school passage; r is u,i The scoring of the ith book by a user u in a certain school section is shown; r is v,i The scoring of the ith book by a user v in a certain school section is shown;
mean book rating representing user u in a school section;
indicating the average book rating of user v in a certain school passage. s (u, u ') represents the similarity of user u and user u'. p is a radical of u,i The user's predicted score for the unscored book.
Fig. 3 is a schematic structural diagram of a text content-based recommendation system for reading books outside the class of an elementary school. The server side of the system shown in fig. 3 is suitable for the Django framework of Python language, and has the advantages of good completeness and universality.
The system for recommending books for reading outside class of primary school based on text content has five functional modules of user management, book management, registration and login, personal center, book recommendation and the like, and the book recommendation functional module is used for executing a method for grading reading evaluation and recommendation of books outside class of primary school. Each functional module is designed in detail from the aspects of requirement analysis, database design, front-end and back-end interaction and the like, and each functional module of the system is tested in a relevant way after the system is built.
By adopting the Django framework design, the book recommendation system for the out-of-class reading of the primary school based on the text content is realized, and the system can perform graded reading recommendation by combining the stage characteristics of primary school students. The method extracts the characteristics of the out-of-class reading materials of the same school class by analyzing and researching the out-of-class reading text content level of the primary school and carries out targeted recommendation. The out-of-class reading recommended for the pupils can reflect the reading interest and can be matched with the reading ability of the pupils. The system has good robustness and stability, complete functions and good interface interactivity, and accords with the use habits of users.
The embodiment of the invention provides a grading reading evaluation method for books outside class of primary schools, and selects 59 characteristics as alternative characteristic sets from three comprehensive characteristics of book diversity, book complexity and book connectivity through research and analysis on five levels of pictures, Chinese characters, vocabularies, sentences, chapters and the like, so that a grading evaluation model for books outside class reading of primary schools is fitted. Influence factors of various characteristics of each layer on grading evaluation of the books read outside the class of the primary school are fully integrated, and finally accurate matching of the text content of the books outside the class of the primary school and the applicable school students can be achieved.
In addition, the embodiment of the invention provides an improved collaborative filtering recommendation algorithm by fusing the hierarchical reading evaluation method, and applies the applicable learning class of the books predicted by the hierarchical reading evaluation method of the books outside the primary school to the collaborative filtering recommendation algorithm so as to realize accurate matching.
Claims (10)
1. A grading reading evaluation and recommendation method for books outside class of primary schools is characterized by comprising the following steps:
selecting three books suitable for the primary school from the out-of-class books, and constructing a library of out-of-class reading books of the primary school;
starting from three comprehensive characteristics of book diversity, book complexity and book connectivity, analyzing, studying and judging to obtain five levels of pictures, Chinese characters, vocabularies, sentences and chapters and various characteristics as an alternative characteristic set of the grading reading evaluation method of books outside class of primary school;
screening out optimal comprehensive characteristics by using data analysis software to construct a grading reading evaluation method for books outside the class of the primary school;
the method is characterized in that the applicable learning sections of books predicted by the out-of-class book grading reading evaluation method of the primary school are applied to the process of calculating the similarity of users by a collaborative filtering recommendation algorithm, the similarity between the users is calculated by adopting a Pearson correlation coefficient calculation method, and then the prediction score of the users on unscored books is calculated.
2. The method as claimed in claim 1, wherein the step of selecting the books suitable for the three school lessons from the extraclass books and constructing the extraclass reading book corpus of the primary school comprises:
the method is based on basic course development center of education department and recommended books of middle and primary schools and recommended books of national middle and primary schools as out-of-class book selection standards.
3. The method as claimed in claim 1, wherein the step of constructing the grading reading evaluation method of the books outside the primary school by screening out the optimal comprehensive characteristics by using data analysis software comprises the following steps:
fitting a grading evaluation model of books read outside the primary school by applying a multiple linear regression model to the screened three comprehensive characteristics; calculating a negative correlation coefficient R of the model by SPSS software, reflecting the linear correlation degree between all independent variables and dependent variables, and calculating a decision coefficient R side and an adjusted R side; then carrying out integral regression effect F test on the model, testing whether the linear relation between the explained variables and all the explained variables is obvious or not, and determining whether the relation between the variables is proper or not by using a linear model to fit; and finally, carrying out regression coefficient T inspection on the model, and inspecting the significance of each variable to a dependent variable to obtain the grading reading evaluation method of the books outside the primary school.
4. The method of claim 1, wherein the plurality of features comprises: book diversity characteristics, book complexity characteristics, and book engageability characteristics.
5. The method as claimed in claim 4, wherein the book diversity characteristic is obtained by fitting 18 characteristics including picture diversity, Chinese character diversity, vocabulary diversity, sentence diversity and chapter diversity through a multiple linear regression model.
6. The method of claim 4, wherein the book complexity is mainly determined by fitting 25 features including picture complexity, Chinese character complexity, vocabulary complexity, sentence complexity and chapter complexity through a multiple linear regression model.
7. The method as claimed in claim 4, wherein the book linking features are mainly formed by fitting 16 features including picture linking, Chinese character linking, vocabulary linking, sentence linking and chapter linking through a multiple linear regression model.
8. The method as claimed in claim 1, wherein the grading reading evaluation method for the out-of-class books of the primary school is realized by the following formula:
Y＝αL 1 +βL 2 +γL 3 ++C
wherein Y is the applicable school paragraph, L 1 For book diversity, L 2 To book complexity, L 3 The book linkage is shown as C, the bias term is C, the coefficient of the book diversity is alpha, the coefficient of the book complexity is beta, and the coefficient of the book linkage is gamma.
9. The method of claim 1, wherein the predictive score for an unscored book is calculated by the formula:
wherein i represents the ith book; i is u A book set representing user u's rating at a certain school passage; i is v A book collection representing user v's rating at a certain school passage; r is u,i The scoring of the ith book by a user u in a certain school section is shown; r is a radical of hydrogen v,i Showing the grade of the ith book by the user v at a certain school section;
indicating that user u is at a certain pointAverage book rating of the school section;
indicating the average book rating of user v in a certain school passage. s (u, u ') represents the similarity of user u and user u'; p is a radical of u,i The user's predicted score for the unscored book.
10. A grading reading evaluation and recommendation system for books outside a class in primary schools is characterized by comprising the following components: user management, book management, registration login, personal center and book recommendation function module for performing the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210623160.6A CN114969564A (en) | 2022-06-02 | 2022-06-02 | Grading reading evaluation and recommendation method and system for books outside class of primary school |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210623160.6A CN114969564A (en) | 2022-06-02 | 2022-06-02 | Grading reading evaluation and recommendation method and system for books outside class of primary school |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114969564A true CN114969564A (en) | 2022-08-30 |
Family
ID=82959569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210623160.6A Pending CN114969564A (en) | 2022-06-02 | 2022-06-02 | Grading reading evaluation and recommendation method and system for books outside class of primary school |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114969564A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668167A (en) * | 2024-02-01 | 2024-03-08 | 《全国新书目》杂志有限责任公司 | Book rating intelligent processing method based on big data analysis |
-
2022
- 2022-06-02 CN CN202210623160.6A patent/CN114969564A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668167A (en) * | 2024-02-01 | 2024-03-08 | 《全国新书目》杂志有限责任公司 | Book rating intelligent processing method based on big data analysis |
| CN117668167B (en) * | 2024-02-01 | 2024-04-05 | 《全国新书目》杂志有限责任公司 | Book rating intelligent processing method based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Salehijam | The value of systematic content analysis in legal research | |
| Sung et al. | Leveling L2 texts through readability: Combining multilevel linguistic features with the CEFR | |
| CN111524578B (en) | Psychological assessment device, method and system based on electronic psychological sand table | |
| TW201403354A (en) | System and method using data reduction approach and nonlinear algorithm to construct Chinese readability model | |
| Agarwal et al. | Autoeval: A nlp approach for automatic test evaluation system | |
| Zhou et al. | Application analysis of data mining technology in ideological and political education management | |
| Pearson | The predictive validity of the Academic IELTS test: A methodological synthesis | |
| CN116821377A (en) | Primary school Chinese automatic evaluation system based on knowledge graph and large model | |
| CN114969564A (en) | Grading reading evaluation and recommendation method and system for books outside class of primary school | |
| Lemarchand et al. | A computational approach to evaluating curricular alignment to the united nations sustainable development goals | |
| Devi | Understanding the qualitative and quantitative methods in the context of content analysis | |
| CN115859962B (en) | Text readability evaluation method and system | |
| CN112966518A (en) | High-quality answer identification method for large-scale online learning platform | |
| CN112989068B (en) | Knowledge graph construction method for Tang poetry knowledge and Tang poetry knowledge question-answering system | |
| CN109325096A (en) | A kind of knowledge resource search system of knowledge based resource classification | |
| Mollet et al. | Choosing the best tools for comparative analyses of texts | |
| Song et al. | Research on intelligent question answering system based on college enrollment | |
| Giabbanelli et al. | Generative AI for Systems Thinking: Can a GPT Question-Answering System Turn Text into the Causal Maps Produced by Human Readers? | |
| Shauki et al. | Developing a corpus of entrepreneurship emails (COREnE) for business courses in Malaysian university using integrated moves approach | |
| Tabatabaei et al. | Rhetorical conventions in the conclusion genre: Comparing English and Persian research articles in the field of Social Studies | |
| Hong et al. | Linguistic Feature Analysis of CEFR Labeling Reliability and Validity in Language Textbooks. | |
| Yang et al. | The Structures and Functions of Lexical Bundles in Argumentative Essays by Chinese EFL Students at the Tertiary Level. | |
| Ji | Readability Evaluation of Books in Chinese as a Foreign Language Using the Machine Learning Algorithm | |
| Hidayati et al. | VISUALIZING RESEARCHES ON ENGLISH LEARNING: A BIBLIOMETRIC ANALYSIS | |
| Usoniene et al. | Corpus Academicum Lithuanicum: design criteria, methodology, application |
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 |