CN110008356B - Error correction book generation system and method - Google Patents
Error correction book generation system and method Download PDFInfo
- Publication number
- CN110008356B CN110008356B CN201910235524.1A CN201910235524A CN110008356B CN 110008356 B CN110008356 B CN 110008356B CN 201910235524 A CN201910235524 A CN 201910235524A CN 110008356 B CN110008356 B CN 110008356B
- Authority
- CN
- China
- Prior art keywords
- error correction
- document
- question
- knowledge
- wrong
- 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.)
- Active
Links
Images
Landscapes
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an error correction book generating system and method, comprising the following steps: the device comprises a learning result input module, a learned state identification module, an error correction scheme generation module and an error correction scheme transmission module. The invention is used for automatically helping learners and teachers to generate personalized correction books, and each learner takes the learning materials which are customized by the individuals, thereby avoiding the learners from wasting much time and energy on knowledge and subjects which are mastered or are difficult to master temporarily; and can also be used for improving the self-learning efficiency of the intelligent equipment.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to a system and a method for generating an error correction book.
Background
With the development of information technology, more and more scientific and technological means are applied to the traditional education and learning fields. Errors will inevitably occur as long as learning is available, and the improvement of the learner's performance is in continuous correction of errors. How to reasonably and effectively utilize a new technology tool to reduce the time of error correction of a learner and improve the error correction efficiency in learning becomes one of the problems to be solved urgently.
In traditional study, the most original way is to manually copy wrong questions on paper materials such as books, exercise books and the like on wrong problem books, the wrong problem books are not in a fixed format, and the wrong problem books made by a plurality of students are disordered in seven-eight vinasse, so that the wrong problem books with the fixed guide format on the paper materials are produced, such as 'student error correction special books' (publication number: CN101070026A), the mode has the advantages of very large workload, very low efficiency and few sustainable students. In order to reduce the workload of copying the questions, some methods adopt mechanical 'copying and pasting' methods, such as 'a device for arranging wrong questions' (the authorization notice number: CN 207417999U); some adopt a photographing or scanning method, such as "a device for quick error correction of students" (authorization notice number: CN 208063298U); still another method combines photographing with picture recognition, such as "a wrong-question management method and system" (application publication No. CN 105224665A). Different methods are used for reducing the burden of the students on transcribing the original error questions.
However, the core problem of how to "correct errors" in student learning is not solved. In the real learning activities, the learning time of students is limited, and the students often spend much time gnawing a difficult wrong question, so that the question is not understood, the time for learning other students is also occupied, and the students are very irretrievable. That is, even if there is an error problem book, the student does not know how to use the error problem book scientifically to correct the error efficiently.
According to the invention, an accurate learning result entry method which takes little time is adopted, and an automatic error correction scheme generation system is constructed, so that the time for acquiring error question information is further reduced; on the other hand, a complete, clear, flexible and long-term executable error correction scheme is provided for students, and the error correction efficiency of the students is greatly improved.
Disclosure of Invention
The invention solves the problems: the system and the method are used for automatically helping learners and teachers to generate personalized error correction books, and each learner takes the learning materials which are customized by a person, so that the phenomenon that the learners waste much time and energy on knowledge and subjects which are mastered or are difficult to master temporarily is avoided; and can also be used for improving the self-learning efficiency of the intelligent equipment.
The technical scheme adopted by the invention is as follows: an error correction book generation system comprising: learning result input module, acquisition state identification module, error correction scheme generation module, error correction scheme transmission module, wherein:
the learning result input module is used for pre-storing learning material data in the server, wherein the learning material data comprises a learning material name, a question, an answer, a question number, a page number, a question setting mode, difficulty and the like; when the learning result is recorded, corresponding learning materials and page numbers are selected, and then the wrong question number is marked at the corresponding position, so that the server can obtain the data of the learning result of the learner for other steps to call;
and the acquisition state identification module analyzes the knowledge elements of the questions in advance by the server, divides the questions into two types of correct and wrong according to newly input learning result data, and calculates the scores of the knowledge elements, wherein one method is to respectively add positive weights to the knowledge elements of the correct questions and negative weights to the knowledge elements of the wrong questions. Adding the weight values of each knowledge element to obtain respective scores, thereby obtaining a knowledge element state distribution diagram; sequencing according to the scores from high to low to obtain a knowledge element acquisition sequencing graph; adding the scores of the knowledge elements contained in the 'wrong' questions to obtain the score of each wrong question; sorting according to the wrong question scores to obtain a wrong question sorting table; adding the total scores of all the knowledge elements to obtain a learned state total score;
the error correction scheme generation module is used for generating a plurality of generation schemes according to different targets when the error correction scheme is generated; if the goal is to master knowledge, a ranking graph is obtained according to knowledge elements, the knowledge is sequentially ranked to form a document, and the document can be called a knowledge correction document for convenience of description; if the target is to do the latest error question, the error questions are sequentially arranged to form a document according to the latest error question sequencing table, and the document can be called an error question correction document for convenience of description; if the target is to review the past error questions, calling the error questions in a certain time period in the past, and sequencing the error questions according to the error question scores to form a document, wherein the document can be called an error question cyclic error correction document for convenience of description; if the target is a special exercise, calling a topic containing certain knowledge elements, and forming a document by sequencing according to topic scores, wherein the document can be called a special error correction document for convenience of description; if the comprehensive error correction scheme of a plurality of targets is included, combining the corresponding plurality of sub-documents to form a complete comprehensive document of the error correction scheme;
the error correction scheme transmission module is used for converting the formed error correction document into a universal displayable document when the error correction scheme is transmitted; calling a scene document by combining the actual use scene, combining the scene document with a universal displayable error correction document, and storing the combined scene document and the universal displayable error correction document on a specific server; if the learner is shown in an online mode, only an access interface is given; if the learner is given the download address in an electronic version mode; if the paper version of the document is given to the learner, the document is downloaded and then printed.
In the error correction scheme generation module, the form and carrier of the error correction scheme are electronic version documents, printed version documents, videos, audios, games, cartoons and the like, or the multiple forms and the multiple carriers are repeated in a crossed manner.
In the error correction scheme transmission module, the number of the components of the error correction scheme is not limited, and the transmission amount, the transmission time and the transmission mode of the error correction scheme are all a complete scheme generated once and transmitted once; or a plurality of parts of the complete scheme are generated at one time and are transmitted for a plurality of times; or multiple portions of a multiple generation scheme, divided into multiple passes.
The invention relates to an error correction book generation method, which comprises a learning result inputting step, a learned state identifying step, an error correction scheme generating step and an error correction scheme transmitting step, wherein the learning result inputting step comprises the following steps:
and a learning result inputting step, wherein data of the learning materials, including names, questions, answers, question numbers, page numbers, question setting modes, difficulty and the like of the learning materials, are prestored in the server. When the learning result is recorded, only corresponding learning materials and page numbers need to be selected, and then the corresponding positions of the wrong question numbers are marked, so that the server obtains the data of the learning result of the learner for other steps to call;
wherein the learning result is whether the learner's reaction to the learning material is wrong or correct compared with the standard answer, including but not limited to: solving the problem, knowledge mastering, skill acquisition, examination and exercise; the input means inputting the learning result information into the equipment; wherein the equipment includes but is not limited to computer, server, mobile phone, specialized recorder;
and a step of acquiring state identification, in which a server analyzes knowledge elements of the questions in advance, divides the questions into a correct type and an incorrect type according to newly input learning result data, and calculates knowledge element scores, wherein one method is to respectively add positive weights to the knowledge elements of the correct question and negative weights to the knowledge elements of the incorrect question. And adding the weight values of each knowledge element to obtain respective scores. Thereby obtaining a knowledge element state distribution diagram; sequencing according to the scores from high to low to obtain a sequencing graph for learning knowledge elements; adding the scores of the knowledge elements contained in the 'wrong' questions to obtain the score of each wrong question; sorting according to the wrong question scores to obtain a wrong question sorting table; adding the total scores of all the knowledge elements to obtain a learned state total score;
wherein the learning state refers to the state that the learner learns about the learning material at a certain moment, and includes but is not limited to correct or wrong final result of solving questions, correct or wrong result of solving questions, understanding degree of knowledge, learning or not of skills, and proficiency of skill master;
and an error correction scheme generation step, wherein when the error correction scheme is generated, a plurality of generation schemes are provided according to different targets. If the goal is to master knowledge, a ranking graph is obtained according to knowledge elements, the knowledge is sequentially ranked to form a document, and the document can be called a knowledge correction document for convenience of description; if the target is to do the latest error question, then the error questions are sequentially arranged to form a document according to the latest error question ordering table, and the document can be called an error question correction document for convenience of description; if the target is to review the past error questions, calling the error questions in a certain time period in the past, and sequencing the error questions according to the error question scores to form a document, wherein the document can be called an error question cyclic error correction document for convenience of description; if the target is a specialized exercise, topics containing certain knowledge elements are called out and sorted by topic score to form a document, which for ease of description may be referred to as a specialized error correction document. If the file is the comprehensive error correction scheme comprising a plurality of targets, combining the corresponding plurality of sub-files to form a complete comprehensive file of the error correction scheme;
the error correction scheme refers to a plan which helps a learner to convert an incorrect learning result into a correct learning result and has strong operability; the generation means that an error correction scheme is made according to the identification result of the learned state;
an error correction scheme transmitting step, wherein when the error correction scheme is transmitted, the formed error correction document is converted into a universal displayable document; calling a scene document by combining the actual use scene, combining the scene document with a universal displayable error correction document, and storing the combined scene document and the universal displayable error correction document on a specific server; if the learner is shown in an online mode, only an access interface is required; if the learner is given the download address in an electronic version mode; if the paper version document is given to the learner, the document needs to be downloaded and then printed;
wherein, the error correction scheme delivery means that the error correction scheme is finally given to the learner in some way.
In the step of generating the error correction scheme, the form and the carrier of the error correction scheme are electronic version documents, printing version documents, videos, audios, games, cartoons and the like, or the multiple forms and the multiple carriers are repeated in a crossed manner.
In the error correction scheme transmitting step, the number of the components of the error correction scheme is not limited, and the transmitting amount, the transmitting time and the transmitting mode of the error correction scheme are all a complete scheme generated once and transmitted once; or generating a plurality of parts of the complete scheme once, and dividing the parts into a plurality of times of transmission; or multiple portions of a multiple generation scheme, divided into multiple passes.
Compared with the prior art, the invention has the advantages that:
(1) the learning result input method is simple to operate and extremely short in time;
(2) the invention not only can give the wrong questions to students intact, but also can utilize the acquisition state identification method to carry out multi-level deep analysis on the wrong questions;
(3) on the basis of analysis, the invention can conveniently provide a scientific and reasonable personalized error correction scheme to students according to the actual requirements.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of an error book generation system according to the present invention;
FIG. 2 is a flow chart of learning result entry according to the present invention;
FIG. 3 is a flow chart of the acquisition status evaluation method of the present invention;
FIG. 4 is a flow chart of the error correction scheme generation of the present invention;
fig. 5 is a flow chart of the error correction scheme delivery of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For simplicity and clarity of description, the invention will be described below by describing several representative embodiments. The numerous details of the examples are merely provided to assist in understanding the inventive arrangements. It will be apparent, however, that the invention may be practiced without these specific details. Some embodiments are not described in detail, but rather are merely provided as frameworks, in order to avoid unnecessarily obscuring aspects of the invention. Hereinafter, "comprising" means "including but not limited to", "according to … …" means "at least according to … …, but not limited to … … only". When the number of one component is not particularly specified hereinafter, it means that the component may be one or more, or may be understood as at least one. In the following, when multiple instances are presented, this is not intended to be a space limitation, but is not meant to be the only ones set forth.
As shown in fig. 1, the error correction book generating system includes a server side and a client side. The server side comprises a database in which learning related data are stored in advance, a learning state identification module, a fine processing data, an error correction scheme generation module and an error correction scheme transmission module, wherein the fine processing data are used for analyzing and obtaining two bases of a knowledge element learning sequencing chart and a wrong problem sequencing table; the client provides learning result input, error correction target setting and use scene setting for a user, and obtains interface display and function realization of a scheme.
The whole system is composed of two servers and two cloud databases. One linux server has a 2-core CPU, a 4GB memory and a 10Mbps fixed public network bandwidth, and is used for establishing a topic content library, forwarding a request and the like. And the other linux server has a 2-core CPU, a 4GB memory and a 10Mbps fixed public network bandwidth, is used for a user side and comprises user interface display, function realization and the like. The system comprises a MySQL cloud database for storing a content library, analysis results of subject data and the like, and a MongoDB cloud database for storing user data, teacher management information and the like. Meanwhile, an automatic backup system of the database and abnormal monitoring of the server are deployed, and stability and robustness of service are guaranteed.
As shown in fig. 2, the learning result entry module pre-stores data of the learning materials in the server, including names, titles, answers, title numbers, page numbers, question setting modes, difficulty levels, and the like of the learning materials. When the learning result is recorded, after the information of the learner is determined, only the corresponding learning material and page number need to be selected, and then the mark is made at the corresponding position of the wrong question mark, and the operation is circulated. Thus, the server obtains the data of the learning result of the learner for other steps to call.
One of the specific methods is as follows: the server database stores the question information of various data, including the name of the learning material, the question, the answer, the question number, the page number, the question setting mode, the difficulty degree and the like, and each question uses a unique ID as an identifier. When the user determines the learner information and selects the data and the page number, the front end initiates a request to the background, and the data ID and the page number are used for inquiring question information to the background in a GET Params form. And after the background obtains the query parameters and verifies the identity of the user, searching the marked question ID of the user, filtering the marked question ID in a user database, finally returning data by using JSON, and identifying an error state by using an HTML Status Code. After the user marking is finished, the front end sends the marking result together with the job arrangement time selected by the user to the background in a Unix timestamp mode through a POST request in a JSON format, and after the background is verified as a legal user by JWT, the obtained title ID, state and Unix timestamp are written into a database. Thus, the server obtains the data of the learning result of the learner for other steps to call.
For example, user A selects document X, page number P1, the head end sends a request, and queries for title information with the ID of X and the value of page 1. And the background checks whether the user A is a legal user or not through the token in the Cookie. After the examination is passed, the title of page 1 of the data X is obtained. Then, the titles marked by the user A before are obtained, and the titles which are not marked by the user A in the page 1 of the data X are obtained through filtering. The front end displays on the interface and lets a mark and confirm. And after the A is submitted, the background updates the record and dynamically adjusts the user characteristics of the A according to the latest mark.
A learned state identification module: as shown in fig. 3, the server analyzes and extracts features of an existing topic library in advance through a machine learning algorithm, obtains knowledge elements of topics by assisting with artificial recognition and correction, and performs statistical analysis on importance, occurrence frequency and the like of the knowledge elements to obtain weighted values of the knowledge elements. Then, according to newly entered learning result data, the questions in the user database are divided into two types of 'correct' and 'wrong', and the knowledge element score is calculated. According to the weighted value of the knowledge elements, the positive weight is applied to the knowledge elements of the correct subjects, and the negative weight is applied to the knowledge elements of the wrong subjects. The weighting of each knowledge element can calculate a respective score, which can result in a knowledge element status profile. Sequencing according to the scores from high to low to obtain a sequencing graph for learning knowledge elements; adding the scores of the knowledge elements contained in the 'wrong' questions to obtain the score of each wrong question; sorting according to the wrong question scores to obtain a wrong question sorting table; and adding the total scores of all knowledge elements to obtain the total score of the learned state.
For example, user a previously entered a series of topics P in the entry step, and the server will query the database for the pre-processed results for each topic P. Because the system previously carries out statistics and analysis on each topic in P, the knowledge element Z and the weighted value W corresponding to each element are obtained and stored in the database. Here, the query preprocessing result can immediately obtain knowledge elements Zp and weighting values Wzp corresponding to each topic p, where Zp may have multiple elements, and p may affect the value Wzp, Wzp > 0. For all the related elements z appearing, the background reversely queries the corresponding topic p, if p is right, Wzp keeps a positive value Wzp, if p is wrong, Wzp changes to a negative value-Wzp. The weights Wzp of each knowledge element z are calculated to obtain the score g, so as to obtain the state distribution diagram of the knowledge elements and the learned ranking diagram of the knowledge elements. And then, the background carries out sorting calculation on the scores g of all knowledge elements Zp corresponding to the topic p from the topic p to obtain the score of each topic, and further obtains a wrong topic sorting table. And calculating the scores of all the presented knowledge elements Z to finally obtain the total score of the learned states.
An error correction scheme generation module: as shown in fig. 4, when the error correction scheme is generated, there are a plurality of generation schemes according to different targets. The user gives different params when calling the interface according to the required target. And if the submitted params is to master knowledge, the background verifies the user identity, then queries the knowledge element state distribution diagram and the knowledge element learned ranking diagram obtained in the learned state identification step from the database, and obtains the required knowledge elements according to the data to generate a knowledge error correction document. If the target is to do the latest wrong questions, the latest wrong question sorting table is inquired after the user identity is verified, and the wrong questions are sequentially arranged to form a wrong question error correction document. If the target is to review past wrong questions, the wrong questions in a certain time period need to be submitted in a UNIX timemap mode at the same time, the background calls out the wrong questions in the time period from the database according to the time period and user information, and the wrong questions are sorted according to wrong question scores to form a wrong question cyclic error correction document. If the target is special exercise, the front end needs to submit corresponding special information in a JSON format, the background obtains corresponding knowledge elements in the database according to the special information, calls the titles containing the knowledge elements, and sorts the titles according to the scores to form a special error correction document. If the comprehensive error correction scheme comprises a plurality of targets, combining the corresponding plurality of sub-documents to form a comprehensive document of the complete error correction scheme. When generating or merging the document, the system calls COM Bridge through the Jacob library, calls Word process and processes the document.
For example, a user a needs to generate a comprehensive document including the four targets, after a performs corresponding check confirmation in the interface, the front end initiates a GET request to the error correction scheme generation interface and gives a specific params, and after the background verifies the user identity of the user a through JWT, the user a sequentially processes according to the request data. Firstly, a background acquires the state distribution of the knowledge elements of A and the learned sequencing Z of the knowledge elements from a database, acquires a knowledge element file ZF required to be contained in a knowledge error correction document according to Z, then communicates with a document merging server, and calls a Word process through a Jacob and COM Bridge technology to process the knowledge element file ZF into the knowledge error correction document. Then, the background obtains an error problem file PF1 included in the error problem correction document according to the latest error problem ranking table C, and generates an error problem correction document in the same manner. Then, the background acquires UNIX timemap in the request parameters to obtain a review time period, then queries the wrong questions in the time period and sorts the wrong questions by wrong question scores to obtain a wrong question file PF2 contained in the wrong question cyclic error correction document, and generates the document. And then, the background inquires the knowledge elements Z which need to be mastered under the special items of A according to JSON format special information in the request, calls the corresponding topics P of the Z in the database, and sorts the topics according to the topic scores g of the P to form a special error correction document. And finally, uniformly arranging the four documents and sending the four documents to a document merging server, and calling a Word process to merge the four documents into a comprehensive document of a complete error correction scheme.
An error correction scheme delivery module: as shown in FIG. 5, the error correction scheme delivery is to convert the error correction document formed as described above into a general displayable document and deliver it to the user. After the background verifies the user identity through JWT, the real use scene of the preset product in the database is inquired, the scene document is called out, the scene document and the error correction document are sent to the document processing server together in a binary stream mode, Word is called through Jacob and COM Bridge technology and combined to obtain an output document, and the output document is transmitted back to the static file server. Then the background inquires a display mode in a database, if the file is displayed to the learner in an online mode, the background generates an access URL so that the file can be rendered online; if the URL is provided for the learner in an electronic version mode, the background generates a downloading URL and returns the downloading URL to the front end; if the paper version of the document is given to the learner, the document is downloaded and then printed.
For example, the user a needs to obtain the document, after the front end performs corresponding operation, the background JWT verifies the identity of the user a, queries the use scenario C of a product owned by the user a in the database by using the user information of the user a, and queries a scenario document F1 corresponding to the scenario C. And obtaining an error correction document F2 in the step of generating the error correction scheme, coding and converting F1 and F2 by the server, sending the encoded error correction document F2 to a document processing server in a Byte form, combining the encoded error correction document F into an output document F through a Word process, and further sending the output document F to a Static file server storing Static resources for subsequent operation. And then the background processes the obtained document F according to the display mode of the product owned by the user A, and online rendering can be performed, or a download URL is generated, or a worker downloads, prints and issues the paper version document to the user A.
The invention is already used in schools, helps teachers to realize intelligent arrangement homework, generates an error correction book suitable for learning of each student according to the actual learning conditions of the students, and has remarkable effects in the following aspects. (1) The teacher can automatically realize the arrangement of the personalized homework, so that the teacher guides students more pertinently; (2) the time and energy of the students are not wasted on improper learning materials, the learning accuracy is greatly enhanced, and the learning efficiency is obviously improved.
Claims (6)
1. An error book generation system, comprising: the learning system comprises a learning result input module, a learned state identification module, an error correction scheme generation module and an error correction scheme transmission module, wherein:
the learning result input module is used for pre-storing learning material data in the server, wherein the learning material data comprises a learning material name, a question, an answer, a question number, a page number, a question setting mode and difficulty; when the learning result is recorded, corresponding learning materials and page numbers are selected, and then the corresponding positions of the wrong question numbers are marked, so that the server can obtain the data of the learning result of the learner for other steps to call;
the learning state identification module is used for analyzing and extracting characteristics of an existing question library by a server through a machine learning algorithm in advance, assisting in manual identification and correction to obtain knowledge elements of the questions, and performing statistical analysis on the importance and the occurrence frequency of the knowledge elements to obtain the weighted value of the knowledge elements; then, according to newly input learning result data, dividing the questions in the user database into two types of correct and wrong, and calculating knowledge element scores; according to the weighted value of the knowledge elements, adding positive weight to the knowledge elements of the 'correct' question and adding negative weight to the knowledge elements of the 'wrong' question; the weighting of each knowledge element can calculate respective scores, so that a knowledge element state distribution diagram can be obtained, and a ranking diagram for knowledge element learning is obtained by ranking from high to low; adding the scores of the knowledge elements contained in the 'wrong' questions to obtain the score of each wrong question; sorting according to the wrong question scores to obtain a wrong question sorting table; adding the total scores of all knowledge elements to obtain a learned state total score;
the error correction scheme generation module is used for generating a plurality of generation schemes according to different targets when the error correction scheme is generated; if the goal is to master knowledge, a ranking graph is obtained according to knowledge elements, the knowledge is sequentially ranked to form a document, and the document can be called a knowledge correction document for convenience of description; if the target is to do the latest error question, then the error questions are sequentially arranged to form a document according to the latest error question ordering table, and the document can be called an error question correction document for convenience of description; if the target is to review the past wrong questions, calling the wrong questions in a certain time period in the past, and sequencing the wrong questions according to the wrong question scores to form a document, wherein the document is called a wrong question cyclic error correction document; if the target is a special exercise, calling a topic containing certain knowledge elements, and sorting according to the topic scores to form a document, wherein the document is called a special error correction document; if the comprehensive error correction scheme of a plurality of targets is included, combining the corresponding plurality of sub-documents to form a complete comprehensive document of the error correction scheme;
the error correction scheme transmission module is used for converting the formed error correction document into a universal displayable document when the error correction scheme is transmitted; calling a scene document by combining the actual use scene, combining the scene document with a universal displayable error correction document, and storing the combined scene document and the universal displayable error correction document on a specific server; if the learner is shown in an online mode, only an access interface is given; if the learner is given the download address in an electronic version mode; if the paper version of the document is given to the learner, the document is downloaded and then printed.
2. The error correction book generation system according to claim 1, characterized in that: in the error correction scheme generation module, the form and the carrier of the error correction scheme are electronic version documents, printing version documents, videos, audios, games and cartoons, or the multiple forms and the multiple carriers are crossed and repeated.
3. The error correction book generation system according to claim 1, characterized in that: in the error correction scheme transmission module, the transmission amount of the error correction scheme, the transmission time and the transmission mode are generated once and transmitted once; or a plurality of parts of the complete scheme are generated at one time and are transmitted for a plurality of times; or multiple portions of a multiple generation scheme, divided into multiple passes.
4. An error correction book generating method, characterized by: the method comprises a learning result inputting step, a learned state identifying step, an error correction scheme generating step and an error correction scheme transmitting step, wherein:
a learning result inputting step, wherein data of learning materials, including names, questions, answers, question numbers, page numbers, question setting modes and difficulty degrees of the learning materials, are pre-stored in a server; when the learning result is recorded, the server can obtain the data of the learning result of the learner for other steps to call only by selecting corresponding learning materials and page numbers and marking the corresponding position of the wrong question number;
the learning result indicates whether the learner's reaction to the learning material is wrong or correct in comparison with the standard answer, including but not limited to: solving the problem, mastering the knowledge, acquiring the skill, testing and doing exercise; the input is to input the learning result information into the equipment; the equipment comprises a computer, a server, a mobile phone and a special recorder;
a step of identifying the acquired state of the body,
the learning state identification module is used for analyzing and extracting characteristics of an existing question library by a server through a machine learning algorithm in advance, assisting in manual identification and correction to obtain knowledge elements of the questions, and performing statistical analysis on the importance and the occurrence frequency of the knowledge elements to obtain the weighted value of the knowledge elements; then according to newly input learning result data, dividing the questions in the user database into two types of 'correct' and 'wrong', and calculating the scores of the knowledge elements; according to the weighted value of the knowledge elements, adding positive weight to the knowledge elements of the correct question and adding negative weight to the knowledge elements of the wrong question; the weighting of each knowledge element can calculate respective scores, so that a knowledge element state distribution diagram can be obtained, and a ranking diagram for knowledge element learning is obtained by ranking from high to low; adding the scores of the knowledge elements contained in the 'wrong' questions to obtain the score of each wrong question; sorting according to the wrong question scores to obtain a wrong question sorting table; adding the total scores of all knowledge elements to obtain a learned state total score;
an error correction scheme generation step, wherein when the error correction scheme is generated, a plurality of generation schemes are provided according to different targets; if the target is to master knowledge, sequencing graphs are obtained according to knowledge elements, the knowledge is sequentially sequenced to form a document, and the document can be called a knowledge correction document; if the target is to do the latest error question, the error questions are sequentially arranged to form a document according to the latest error question sequencing table, and the document can be called an error question correction document; if the target is to review the past error questions, calling the error questions in a certain time period in the past, and sequencing the error questions according to the error question scores to form a document, wherein the document can be called an error question cyclic error correction document for convenience of description; if the target is a special exercise, calling a topic containing certain knowledge elements, and forming a document by sequencing according to topic scores, wherein the document can be called a special error correction document for convenience of description; if the file is the comprehensive error correction scheme comprising a plurality of targets, combining the corresponding plurality of sub-files to form a complete comprehensive file of the error correction scheme;
wherein, the error correction scheme is a plan with strong operability for helping the learner to convert the wrong learning result into the correct learning result; the generation refers to making an error correction scheme according to the identification result of the learned state;
an error correction scheme transmitting step, wherein when the error correction scheme is transmitted, the formed error correction document is converted into a universal displayable document; calling a scene document by combining the actual use scene, combining the scene document with a universal displayable error correction document, and storing the combined scene document and the universal displayable error correction document on a specific server; if the learner is shown in an online mode, only an access interface is required; if the learner is given the download address in an electronic version mode; if the paper version document is delivered to the learner, the document is downloaded firstly and then printed;
wherein, the error correction scheme delivery means that the error correction scheme is finally given to the learner in some way.
5. The error correction book generating method according to claim 4, characterized in that: in the step of generating the error correction scheme, the form and the carrier of the error correction scheme are electronic version documents, printing version documents, videos, audios, games and cartoons, or the multiple forms and the multiple carriers are repeated in a crossed manner.
6. The error correction book generating method according to claim 4, characterized in that: in the error correction scheme transmitting step, the transmitting amount, the transmitting time and the transmitting mode of the error correction scheme are generated once and transmitted once; or a plurality of parts of the complete scheme are generated at one time and are transmitted for a plurality of times; or multiple portions of a multiple generation scheme, divided into multiple passes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235524.1A CN110008356B (en) | 2019-03-27 | 2019-03-27 | Error correction book generation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235524.1A CN110008356B (en) | 2019-03-27 | 2019-03-27 | Error correction book generation system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008356A CN110008356A (en) | 2019-07-12 |
| CN110008356B true CN110008356B (en) | 2022-07-22 |
Family
ID=67168314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910235524.1A Active CN110008356B (en) | 2019-03-27 | 2019-03-27 | Error correction book generation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008356B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110936749B (en) * | 2019-12-10 | 2024-04-09 | 小本云服务(湖北)有限公司 | Correction card and correction book |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477755A (en) * | 2009-01-06 | 2009-07-08 | 陈诗周 | Error problem database system for student |
| CN102436547A (en) * | 2011-10-24 | 2012-05-02 | 北京商纳科技有限公司 | Wrong sentence statistical method and system for teaching |
| CN104299473A (en) * | 2013-07-20 | 2015-01-21 | 郑州学生宝电子科技有限公司 | Teaching and student learning error question knowledge base |
| CN105787839A (en) * | 2016-03-23 | 2016-07-20 | 成都准星云学科技有限公司 | Method and device for pushing learning resources |
| CN106709830A (en) * | 2015-08-13 | 2017-05-24 | 马正方 | Knowledge-point-structure-based question bank system |
| CN106846962A (en) * | 2017-03-20 | 2017-06-13 | 安徽七天教育科技有限公司 | A kind of wrong answer list generation method based on the wrong topic of student and accurate recommendation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180052884A1 (en) * | 2016-08-16 | 2018-02-22 | Ebay Inc. | Knowledge graph construction for intelligent online personal assistant |
-
2019
- 2019-03-27 CN CN201910235524.1A patent/CN110008356B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477755A (en) * | 2009-01-06 | 2009-07-08 | 陈诗周 | Error problem database system for student |
| CN102436547A (en) * | 2011-10-24 | 2012-05-02 | 北京商纳科技有限公司 | Wrong sentence statistical method and system for teaching |
| CN104299473A (en) * | 2013-07-20 | 2015-01-21 | 郑州学生宝电子科技有限公司 | Teaching and student learning error question knowledge base |
| CN106709830A (en) * | 2015-08-13 | 2017-05-24 | 马正方 | Knowledge-point-structure-based question bank system |
| CN105787839A (en) * | 2016-03-23 | 2016-07-20 | 成都准星云学科技有限公司 | Method and device for pushing learning resources |
| CN106846962A (en) * | 2017-03-20 | 2017-06-13 | 安徽七天教育科技有限公司 | A kind of wrong answer list generation method based on the wrong topic of student and accurate recommendation |
Non-Patent Citations (3)
| Title |
|---|
| Study on the Performance Evaluation and Weight of Knowledge Management Based on Value-Chain;Musheng Yang etc.;《2008 4th International Conference on Wireless Communications, Networking and Mobile Computing》;20080118;第1-4页 * |
| 在线错题本生成系统的设计与实现;杨建剑;《中国优秀硕士学位论文全文库（信息科技辑）》;20170315;第I138-3245页 * |
| 基于认知模型的学习评价分析及其应用;杨海艳;《中国优秀硕士学位论文全文数据库(社会科学Ⅱ辑）》;20160215;第H127-130页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008356A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JPH11282826A (en) | Electronic education system using internet | |
| CN109637238B (en) | Method, device, equipment and storage medium for generating exercise questions | |
| US10796592B2 (en) | User generated content within an online education platform | |
| WO2008030990A2 (en) | Adaptive and individual learning with feedback for online courses | |
| CN106251261B (en) | Training scheme generation method and device | |
| CN112837031B (en) | Automatic job reading method and device based on high-speed scanning and printing | |
| JP3883795B2 (en) | Attendance class selection device, attendance class selection method, and storage medium | |
| US20020164565A1 (en) | System and method for teaching job skills to individuals via a network | |
| CN110135799A (en) | The assessment method of vocational match degree, electronic device, computer equipment | |
| JP2004279808A (en) | Telelearning system | |
| CN111259277A (en) | Intelligent education test question library management system and method | |
| CN112598547A (en) | Education topic generation method and device based on automatic production line and electronic equipment | |
| CN110609947A (en) | Learning content recommendation method, terminal and storage medium of intelligent learning system | |
| CN113778446B (en) | Low-code application development platform | |
| CN110008356B (en) | Error correction book generation system and method | |
| CN112950038A (en) | Personalized operation arrangement method based on learning situation data | |
| CN116756271A (en) | Question bank information processing method and device based on textbook informatization and readable medium | |
| US7333769B2 (en) | Learning support method that updates and transmits learner understanding levels | |
| KR20230103995A (en) | Coding Problem Recommendation System and Coding Problem Recommending Method | |
| Elghouch et al. | ALS_CORR [LP]: An adaptive learning system based on the learning styles of Felder-Silverman and a Bayesian network | |
| JP3777497B2 (en) | Learning system and learning method | |
| CN114638587A (en) | Intelligent course arrangement system | |
| CN114168547A (en) | Teaching resource configuration system, method and equipment | |
| GB2543479A (en) | Rating multimedia content | |
| CN112733026A (en) | Online course pushing method based on big data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230627 Address after: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee after: Shenzhen Edson Technology Co.,Ltd. Address before: 230088 room 2102, building 3, Woye garden, the intersection of Tianbu East Road and Ganquan Road, Shushan District, Hefei City, Anhui Province Patentee before: HEFEI ZHIDUOSHAO EDUCATION TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |