CN112818236A - Learning content recommendation method and system based on scene - Google Patents
Learning content recommendation method and system based on scene Download PDFInfo
- Publication number
- CN112818236A CN112818236A CN202110154590.3A CN202110154590A CN112818236A CN 112818236 A CN112818236 A CN 112818236A CN 202110154590 A CN202110154590 A CN 202110154590A CN 112818236 A CN112818236 A CN 112818236A
- Authority
- CN
- China
- Prior art keywords
- learning
- knowledge points
- target object
- learned
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000012552 review Methods 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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a scene-based learning content recommendation method and a scene-based learning content recommendation system, which can determine learned knowledge points and unlearned knowledge points of a target object according to on-line learning historical records of the target object, then determine knowledge points which are not completely mastered by the target object from the learned knowledge points according to examination scores corresponding to the learned knowledge points, finally select the knowledge points with specific learning classes from the unlearned knowledge points or the unlearned knowledge points as the preferred recommended learning content of the target object according to the learning efficiency identification value of the target object, therefore, the targeted learning content recommendation can be accurately carried out according to the requirements of the target object on different knowledge points and the mastery degree of the different knowledge points, therefore, the interest of the students in learning different knowledge points and the reliability and efficiency of knowledge point teaching are improved.
Description
Technical Field
The invention relates to the technical field of intelligent teaching, in particular to a learning content recommendation method and system based on scenes.
Background
At present, the scheduled subject teaching for students is realized according to a corresponding subject teaching outline, and the subject teaching outline sets the teaching sequence and teaching class time of different knowledge points, so that the continuity of teaching for different knowledge points can be ensured. However, the teaching mode in the prior art cannot carry out targeted learning content recommendation on the demands of students on different knowledge points and the mastery degrees of the different knowledge points in the learning process, which is not beneficial to the repeated review of the knowledge points by the students and the selection of the corresponding knowledge points for learning according to the actual conditions of the students, thereby reducing the learning interest of the students on the different knowledge points and the reliability and the efficiency of the knowledge point teaching.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a learning content recommendation method and a learning content recommendation system based on scenes, which analyzes an on-line learning history by acquiring the on-line learning history of a target object, thereby determining the proportion of the knowledge points which have been learned by the target object in all the course knowledge points, and also determines the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses, then the corresponding examination achievement of the target object in the examination aiming at the learned knowledge point is obtained, determining the knowledge points which are not completely mastered by the target object in the learned knowledge points according to the examination score, and finally determining the learning efficiency of the target object in the online learning scene according to the occupation ratio and the knowledge points which are not completely mastered; selecting a knowledge point with a specific learning class from the un-learned knowledge point or the incompletely mastered knowledge point according to the learning efficiency as a preferred recommended learning content of the target object; therefore, the scene-based learning content recommendation method and the scene-based learning content recommendation system can determine learned knowledge points and unlearned knowledge points of a target object according to the on-line learning history of the target object, then determine knowledge points which are not completely mastered by the target object from the learned knowledge points according to the examination scores corresponding to the learned knowledge points, and finally select the knowledge points with specific learning courses from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object according to the learning efficiency of the target object, so that targeted learning content recommendation can be accurately performed according to the requirements of the target object on different knowledge points and the mastering degree of the different knowledge points, and the interest of students in learning different knowledge points and the reliability and efficiency of knowledge point teaching are improved.
The invention provides a learning content recommendation method based on scenes, which comprises the following steps;
step S1, acquiring the on-line learning history of the target object, and analyzing the on-line learning history so as to determine the proportion of the knowledge points which have been learned by the target object in all course knowledge points; determining the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and all course knowledge points;
step S2, acquiring the corresponding examination score of the target object in the examination aiming at the learned knowledge point, and determining the knowledge point which is not completely held by the target object in the learned knowledge point according to the examination score;
step S3, determining the learning efficiency of the target object in the online learning scene according to the ratio and the incompletely mastered knowledge points; selecting a knowledge point with a specific learning class from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency to serve as preferred recommended learning content of the target object;
further, in the step S1, an online learning history of the target object is acquired, and the online learning history is analyzed, so as to determine the proportion of the knowledge points that the target object has learned in all the curriculum knowledge points; and further determining the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses, specifically comprising:
step S101, acquiring on-line learning text data historical browsing records of a target object in different learning time periods, and performing text character recognition processing on the on-line learning text data historical browsing records so as to determine learned knowledge points of the target object in each course chapter; in practice, the learned knowledge points of the target object in each course section can be determined by comparing the characters obtained by the text character recognition processing and recognition with a preset knowledge point character database;
step S102, obtaining the ratio Q of the learned knowledge points of the target object in all the course knowledge points according to the following formula (1) and the above determined learned knowledge points:
in the above formula (1), R represents the total number of courses learned on the target object line, R has values of 1, 2, 3, …, R, M represents the total number of knowledge points included in all courses, n represents the total number of knowledge points included in all coursesrIndicates the number of chapters per r lessons, FriIndicates the number of knowledge points learned by the target object in the ith section of the nth course, i is 1, 2, 3, …, nr;
Step S103, eliminating the learned knowledge points one by one from the knowledge points contained in all the courses, thereby determining the unlearned knowledge points in the target object online learning scene;
further, in step S2, acquiring an examination score corresponding to the target subject in an examination for a learned knowledge point, and determining, according to the examination score, that the knowledge point that the target subject does not completely grasp in the learned knowledge point specifically includes;
step S201, acquiring the examination score of each section of the corresponding course of the target object in the examination aiming at the learned knowledge point;
step S202, determining learned knowledge points corresponding to examination scores of the target object in the examination, wherein the examination scores of the target object in the examination do not exceed 80% of the total score, as knowledge points which are not completely mastered by the target object;
further, in the step S3, determining the learning efficiency of the target object in the online learning scene according to the proportion and the incompletely grasped knowledge points; selecting knowledge points with specific learning class time from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency, wherein the selected knowledge points are specifically used as preferred recommended learning contents of the target object;
step S301, determining a learning efficiency identification value V of the target object in the online learning scene according to the following formula (2):
in the above formula (2), SrIndicating the 1 st chapter, the 2 nd chapter …, and the n th chapter of the target object in the r-th courserChapter 1, nrActual scores in examinations corresponding to chapters Average value of (d); g is an intermediate parameter;
the intermediate parameter G is determined by the following formula (3):
in the above formula (3), SriRepresenting the actual score of the target object in the examination corresponding to the ith section in the ith lesson; sri0Indicating the full score of the test corresponding to the ith section in the ith lesson;
step S302, comparing the learning efficiency identification value V with a preset learning efficiency identification value threshold, and if the learning efficiency identification value V exceeds the preset learning efficiency identification value threshold, selecting a knowledge point which is larger than a preset learning period in the actual learning period from the unlearned knowledge points or the incompletely mastered knowledge points as a preferred recommended learning content of the target object; and if the learning efficiency identification value V does not exceed the preset learning efficiency identification value, selecting the knowledge points with the actual learning period less than or equal to the preset learning period from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object.
The invention also provides a scene-based learning content recommendation system, which comprises an online learning historical record acquisition and analysis module, an unlearned knowledge point determination module, an incompletely mastered knowledge point determination module, a learning efficiency determination module and a recommended learning content determination module; wherein the content of the first and second substances,
the on-line learning history acquisition and analysis module is used for acquiring an on-line learning history of a target object and analyzing the on-line learning history so as to determine the proportion of the learned knowledge points of the target object in all course knowledge points;
the unlearned knowledge point determining module is used for determining unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses;
the incomplete-mastered knowledge point determining module is used for acquiring the corresponding examination score of the target object in the examination aiming at the learned knowledge point, and determining the knowledge point which is not completely mastered by the target object in the learned knowledge point according to the examination score;
the learning efficiency determining module is used for determining the learning efficiency of the target object in an online learning scene according to the occupation ratio and the incompletely mastered knowledge points;
the recommended learning content determining module is used for selecting a knowledge point with a specific learning class from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency to serve as the preferred recommended learning content of the target object;
further, the on-line learning history acquisition and analysis module acquires an on-line learning history of a target object, and analyzes the on-line learning history, so as to determine the proportion of the knowledge points learned by the target object in all course knowledge points, specifically including:
acquiring on-line learning text data historical browsing records of a target object in different learning time periods, and performing text character recognition processing on the on-line learning text data historical browsing records so as to determine learned knowledge points of the target object in each course chapter; in practice, the learned knowledge points of the target object in each course section can be determined by comparing the characters obtained by the text character recognition processing and recognition with a preset knowledge point character database;
and then obtaining the proportion Q of the knowledge points which have been learned by the target object in all course knowledge points according to the following formula (1) and the determined learned knowledge points:
in the above formula (1), R represents the total number of courses learned on the target object line, R has values of 1, 2, 3, …, R, M represents the total number of knowledge points included in all courses, n represents the total number of knowledge points included in all coursesrIndicates the number of chapters per r lessons, FriIndicates the number of knowledge points learned by the target object in the ith section of the nth course, i is 1, 2, 3, …, nr;
And the number of the first and second groups,
the determining module of the unlearned knowledge points determines the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses, and specifically includes:
the learned knowledge points are eliminated one by one from the knowledge points contained in all the courses, so that the unlearned knowledge points in the online learning scene of the target object are determined;
further, the step of acquiring the examination score corresponding to the target subject in the examination for the learned knowledge point by the incompletely mastered knowledge point determining module, and the step of determining the knowledge point not completely held by the target subject in the learned knowledge point according to the examination score specifically includes:
acquiring the examination score of each section of the corresponding course of the target object in the examination aiming at the learned knowledge point;
then, determining the learned knowledge points corresponding to the examination scores of the target object in the examination, wherein the examination scores of the target object in the examination do not exceed 80% of the total scores, as the knowledge points which are not completely mastered by the target object;
further, the determining learning efficiency of the target object in the online learning scene according to the ratio and the incompletely grasped knowledge point by the learning efficiency determining module specifically includes:
determining a learning efficiency identification value V of the target object in an online learning scene according to the following formula (2):
in the above formula (2), SrIndicating the 1 st chapter, the 2 nd chapter …, and the n th chapter of the target object in the r-th courserChapter 1, nrActual scores in examinations corresponding to chapters Average value of (d); g is an intermediate parameter;
the intermediate parameter G is determined by the following formula (3):
in the above formula (3), SriRepresenting the actual score of the target object in the examination corresponding to the ith section in the ith lesson; sri0Indicating the full score of the test corresponding to the ith section in the ith lesson;
and the number of the first and second groups,
the recommended learning content determining module selects a knowledge point having a specific learning course from the unlearned knowledge points or the incompletely grasped knowledge points according to the learning efficiency, and the recommended learning content determining module as the preferred recommended learning content of the target object specifically includes:
comparing the learning efficiency identification value V with a preset learning efficiency identification value threshold, and if the learning efficiency identification value V exceeds the preset learning efficiency identification value threshold, selecting a knowledge point which is larger than a preset learning period in the actual learning period from the unlearned knowledge points or the incompletely mastered knowledge points as a preferred recommended learning content of the target object; and if the learning efficiency identification value V does not exceed the preset learning efficiency identification value, selecting the knowledge points with the actual learning period less than or equal to the preset learning period from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object.
Compared with the prior art, the scene-based learning content recommendation method and system can be used for determining the proportion of the learned knowledge points of the target object in all the course knowledge points by acquiring the online learning history of the target object and analyzing the online learning history, determining the knowledge points of the target object which are not learned in the online learning scene according to the learned knowledge points and all the course knowledge points, acquiring the test scores of the target object in the test aiming at the learned knowledge points, determining the knowledge points of the target object which are not completely held in the learned knowledge points according to the test scores, and finally determining the learning efficiency of the target object in the online learning scene according to the proportion and the knowledge points which are not completely held; selecting a knowledge point with a specific learning class from the un-learned knowledge point or the incompletely mastered knowledge point according to the learning efficiency as a preferred recommended learning content of the target object; therefore, the scene-based learning content recommendation method and the scene-based learning content recommendation system can determine learned knowledge points and unlearned knowledge points of a target object according to the on-line learning history of the target object, then determine knowledge points which are not completely mastered by the target object from the learned knowledge points according to the examination scores corresponding to the learned knowledge points, and finally select the knowledge points with specific learning courses from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object according to the learning efficiency of the target object, so that targeted learning content recommendation can be accurately performed according to the requirements of the target object on different knowledge points and the mastering degree of the different knowledge points, and the interest of students in learning different knowledge points and the reliability and efficiency of knowledge point teaching are improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
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 description of the embodiments or 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 schematic flowchart of a learning content recommendation method based on a scene according to the present invention.
Fig. 2 is a schematic structural diagram of a learning content recommendation system based on a scene provided in 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.
Fig. 1 is a schematic flowchart of a learning content recommendation method and system based on a scene according to an embodiment of the present invention. The learning content recommending method based on the scene comprises the following steps;
step S1, obtaining the on-line learning history of the target object, analyzing the on-line learning history, and determining the proportion of the knowledge points which have been learned by the target object in all course knowledge points; and determining the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses;
step S2, acquiring the corresponding examination score of the target object in the examination aiming at the learned knowledge point, and determining the knowledge point which is not completely held by the target object in the learned knowledge point according to the examination score;
step S3, determining the learning efficiency of the target object in the online learning scene according to the occupation ratio and the incompletely mastered knowledge points; and selecting the knowledge points with specific learning class from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency as the preferred recommended learning content of the target object.
The beneficial effects of the above technical scheme are: the scene-based learning content recommendation method can determine learned knowledge points and unlearned knowledge points of a target object according to on-line learning historical records of the target object, then determine knowledge points which are not completely mastered by the target object from the learned knowledge points according to examination scores corresponding to the learned knowledge points, and finally select the knowledge points with specific learning courses from the unlearned knowledge points or the uncompletely mastered knowledge points as preferred recommended learning content of the target object according to the learning efficiency of the target object, so that targeted learning content recommendation can be accurately performed according to the requirements of the target object on different knowledge points and the mastering degrees of the different knowledge points, and the learning interest of students on the different knowledge points and the reliability and efficiency of knowledge point teaching are improved.
Preferably, in the step S1, an online learning history of the target object is acquired, and the online learning history is analyzed to determine the proportion of knowledge points that the target object has learned in all course knowledge points; and further determining the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses, wherein the unlearned knowledge points specifically comprise:
step S101, acquiring on-line learning text data historical browsing records of a target object in different learning time periods, and performing text character recognition processing on the on-line learning text data historical browsing records so as to determine learned knowledge points of the target object in each course chapter;
step S102, obtaining the proportion Q of the knowledge points which have been learned by the target object in all course knowledge points according to the following formula (1) and the determined learned knowledge points:
in the above formula (1), R represents the total number of courses learned on the target object line, R has values of 1, 2, 3, …, R, M represents the total number of knowledge points included in all courses, n represents the total number of knowledge points included in all coursesrIndicates the number of chapters per r lessons, FriIndicates the number of knowledge points learned by the target object in the ith section of the nth course, i is 1, 2, 3, …, nr;
Step S103, excluding the learned knowledge points one by one from the knowledge points included in all the courses, thereby determining the unknown knowledge points in the target object online learning scene.
The beneficial effects of the above technical scheme are: the text character recognition processing is carried out on the on-line learning text data historical browsing records of the target object in different learning time periods, so that the knowledge points in the on-line learning text data historical browsing records can be accurately determined, and the learned knowledge points of the target object can be quickly and comprehensively determined. In addition, by using the above formula (1), the proportion of the knowledge points that the target object has learned in all the course knowledge points can be accurately and quantitatively calculated, which is convenient for comprehensively and effectively counting the learning condition of the knowledge points of the target object.
Preferably, in the step S2, an examination score corresponding to the target subject in the examination for the learned knowledge point is obtained, and according to the examination score, it is determined that the knowledge point that the target subject does not completely grasp in the learned knowledge point specifically includes;
step S201, acquiring the examination score of each section of the corresponding course of the target object in the examination aiming at the learned knowledge points;
in step S202, the learned knowledge points corresponding to examination results of the target subject in the examination of not more than 80% of the total results are determined as the knowledge points not completely grasped by the target subject.
The beneficial effects of the above technical scheme are: the knowledge point which is not completely mastered by the target object can be quickly and accurately determined according to the size of the examination score of each section of the corresponding course relative to the total score in the examination aiming at the learned knowledge point by the target object.
Preferably, in the step S3, determining the learning efficiency of the target object in the online learning scene according to the occupation ratio and the incompletely mastered knowledge point; selecting a knowledge point with a specific learning class from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency, wherein the selected knowledge point is specifically used as the preferred recommended learning content of the target object;
step S301, determining a learning efficiency flag value V of the target object in the online learning scene according to the following formula (2):
in the above formula (2), SrIndicating the 1 st chapter, the 2 nd chapter …, and the n th chapter of the target object in the r-th courserChapter 1, nrActual scores in examinations corresponding to chapters Average value of (d); g is an intermediate parameter;
the intermediate parameter G is determined by the following formula (3):
in the above formula (3), SriRepresenting the actual score of the target object in the examination corresponding to the ith section in the ith lesson; sri0Indicating the full score of the test corresponding to the ith section in the ith lesson;
step S302, comparing the learning efficiency identification value V with a preset learning efficiency identification value threshold, and if the learning efficiency identification value V exceeds the preset learning efficiency identification value threshold, selecting a knowledge point which is larger than a preset learning period in the actual learning period from the unlearned knowledge points or the incompletely mastered knowledge points as a preferred recommended learning content of the target object; and if the learning efficiency identification value V does not exceed the preset learning efficiency identification value, selecting the knowledge points with the actual learning period less than or equal to the preset learning period from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object.
The beneficial effects of the above technical scheme are: through the above formulas (2) and (3), the learning efficiency of the target object in the current online learning scene can be quantitatively evaluated. When the learning efficiency exceeds the preset learning efficiency threshold, the target object has higher learning efficiency at present, and can receive larger learning tasks, so that the knowledge points which are larger than the preset learning class in the actual learning class are selected from the un-learned knowledge points or the incompletely-mastered knowledge points, and can be matched with the current learning capacity of the target object; and when the learning efficiency does not exceed the preset learning efficiency threshold, the target object has lower learning efficiency at present, and can receive smaller learning tasks, so that the knowledge points which are smaller than or equal to the preset learning class in the actual learning class are selected from the un-learned knowledge points or the incompletely-mastered knowledge points, and can be matched with the current learning capacity of the target object.
Fig. 2 is a schematic structural diagram of a learning content recommendation system based on a scene according to an embodiment of the present invention. The scene-based learning content recommendation method comprises an online learning historical record acquisition and analysis module, an unlearned knowledge point determination module, an incompletely mastered knowledge point determination module, a learning efficiency determination module and a recommended learning content determination module; wherein the content of the first and second substances,
the on-line learning history acquisition and analysis module is used for acquiring an on-line learning history of a target object and analyzing the on-line learning history so as to determine the proportion of the learned knowledge points of the target object in all course knowledge points;
the unlearned knowledge point determining module is used for determining unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses;
the incomplete holding knowledge point determining module is used for acquiring the corresponding examination score of the target object in the examination aiming at the learned knowledge point, and determining the incomplete holding knowledge point of the target object in the learned knowledge point according to the examination score;
the learning efficiency determining module is used for determining the learning efficiency of the target object in an online learning scene according to the occupation ratio and the incompletely mastered knowledge points;
the recommended learning content determining module is used for selecting the knowledge points with the specific learning class from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency to serve as the preferred recommended learning content of the target object.
The beneficial effects of the above technical scheme are: the scene-based learning content recommendation system can determine learned knowledge points and unlearned knowledge points of a target object according to on-line learning historical records of the target object, then determine knowledge points which are not completely mastered by the target object from the learned knowledge points according to examination scores corresponding to the learned knowledge points, and finally select the knowledge points with specific learning courses from the unlearned knowledge points or the uncompletely mastered knowledge points as preferred recommended learning content of the target object according to the learning efficiency of the target object, so that targeted learning content recommendation can be accurately performed according to the requirements of the target object on different knowledge points and the mastering degrees of the different knowledge points, and the learning interest of students on the different knowledge points and the reliability and efficiency of knowledge point teaching are improved.
Preferably, the on-line learning history obtaining and analyzing module obtains an on-line learning history of the target object, and analyzes the on-line learning history, so as to determine the proportion of the knowledge points that the target object has learned in all the course knowledge points, specifically including:
acquiring on-line learning text data historical browsing records of a target object in different learning time periods, and performing text character recognition processing on the on-line learning text data historical browsing records so as to determine learned knowledge points of the target object in each course chapter;
and then obtaining the proportion Q of the learned knowledge points of the target object in all the course knowledge points according to the following formula (1) and the determined learned knowledge points:
in the above formula (1), R represents the total number of courses learned on the target object line, R has values of 1, 2, 3, …, R, M represents the total number of knowledge points included in all courses, n represents the total number of knowledge points included in all coursesrIndicates the number of chapters per r lessons, FriIndicates the number of knowledge points learned by the target object in the ith section of the nth course, i is 1, 2, 3, …, nr;
And the number of the first and second groups,
the determining module of the unlearned knowledge points determines the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses, and specifically includes:
and eliminating the learned knowledge points one by one from the knowledge points contained in all the courses, thereby determining the unlearned knowledge points in the online learning scene of the target object.
The beneficial effects of the above technical scheme are: the text character recognition processing is carried out on the on-line learning text data historical browsing records of the target object in different learning time periods, so that the knowledge points in the on-line learning text data historical browsing records can be accurately determined, and the learned knowledge points of the target object can be quickly and comprehensively determined. In addition, by using the above formula (1), the proportion of the knowledge points that the target object has learned in all the course knowledge points can be accurately and quantitatively calculated, which is convenient for comprehensively and effectively counting the learning condition of the knowledge points of the target object.
Preferably, the determining module of the knowledge point not completely mastered acquires the examination score corresponding to the target object in the examination for the learned knowledge point, and according to the examination score, determining the knowledge point not completely mastered by the target object in the learned knowledge point specifically includes:
acquiring the examination score of each section of the corresponding course of the target object in the examination aiming at the learned knowledge point;
and then, the learned knowledge points corresponding to the examination results of the target object in the examination, which do not exceed 80% of the total results, are determined as the knowledge points which are not completely mastered by the target object.
The beneficial effects of the above technical scheme are: the knowledge point which is not completely mastered by the target object can be quickly and accurately determined according to the size of the examination score of each section of the corresponding course relative to the total score in the examination aiming at the learned knowledge point by the target object.
Preferably, the determining learning efficiency of the target object in the online learning scene according to the occupation ratio and the incompletely mastered knowledge point by the learning efficiency determining module specifically includes:
determining a learning efficiency identification value V of the target object in the online learning scene according to the following formula (2):
in the above formula (2), SrIndicating the 1 st chapter, the 2 nd chapter …, and the n th chapter of the target object in the r-th courserChapter 1, nrActual scores in examinations corresponding to chapters Average value of (d); g is an intermediate parameter;
the intermediate parameter G is determined by the following formula (3):
in the above formula (3), SriRepresenting the actual score of the target object in the examination corresponding to the ith section in the ith lesson; sri0Indicating the full score of the test corresponding to the ith section in the ith lesson;
and the number of the first and second groups,
the recommended learning content determining module selects a knowledge point having a specific learning class from the unlearned knowledge point or the incompletely grasped knowledge point according to the learning efficiency, and the recommended learning content determining module as the preferred recommended learning content of the target object specifically includes:
comparing the learning efficiency identification value V with a preset learning efficiency identification value threshold, and if the learning efficiency identification value V exceeds the preset learning efficiency identification value threshold, selecting a knowledge point which is larger than a preset learning period in the actual learning period from the unlearned knowledge points or the incompletely mastered knowledge points as a preferred recommended learning content of the target object; and if the learning efficiency identification value V does not exceed the preset learning efficiency identification value, selecting the knowledge points with the actual learning period less than or equal to the preset learning period from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object.
The beneficial effects of the above technical scheme are: through the above formulas (2) and (3), the learning efficiency of the target object in the current online learning scene can be quantitatively evaluated. When the learning efficiency exceeds the preset learning efficiency threshold, the target object has higher learning efficiency at present, and can receive larger learning tasks, so that the knowledge points which are larger than the preset learning class in the actual learning class are selected from the un-learned knowledge points or the incompletely-mastered knowledge points, and can be matched with the current learning capacity of the target object; and when the learning efficiency does not exceed the preset learning efficiency threshold, the target object has lower learning efficiency at present, and can receive smaller learning tasks, so that the knowledge points which are smaller than or equal to the preset learning class in the actual learning class are selected from the un-learned knowledge points or the incompletely-mastered knowledge points, and can be matched with the current learning capacity of the target object.
As can be seen from the content of the above embodiment, the scene-based learning content recommendation method and system determine the proportion of the knowledge points already learned by the target object in all the curriculum knowledge points by obtaining the online learning history of the target object and analyzing the online learning history, and also determine the knowledge points not already learned in the online learning scene of the target object according to the learned knowledge points and all the curriculum knowledge points, then obtain the corresponding examination of the target object in the examination for the learned knowledge points, determine the knowledge points not completely held by the target object in the learned knowledge points according to the examination score, and finally determine the learning efficiency of the target object in the online learning scene according to the proportion and the knowledge points not completely mastered; selecting a knowledge point with a specific learning class from the un-learned knowledge point or the incompletely mastered knowledge point according to the learning efficiency as a preferred recommended learning content of the target object; therefore, the scene-based learning content recommendation method and the scene-based learning content recommendation system can determine learned knowledge points and unlearned knowledge points of a target object according to the on-line learning history of the target object, then determine knowledge points which are not completely mastered by the target object from the learned knowledge points according to the examination scores corresponding to the learned knowledge points, and finally select the knowledge points with specific learning courses from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object according to the learning efficiency of the target object, so that targeted learning content recommendation can be accurately performed according to the requirements of the target object on different knowledge points and the mastering degree of the different knowledge points, and the interest of students in learning different knowledge points and the reliability and efficiency of knowledge point teaching are improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A scene-based learning content recommendation method characterized by comprising the steps of;
step S1, acquiring the on-line learning history of the target object, and analyzing the on-line learning history so as to determine the proportion of the knowledge points which have been learned by the target object in all course knowledge points; determining the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and all course knowledge points;
step S2, acquiring the corresponding examination score of the target object in the examination aiming at the learned knowledge point, and determining the knowledge point which is not completely held by the target object in the learned knowledge point according to the examination score;
step S3, determining the learning efficiency of the target object in the online learning scene according to the ratio and the incompletely mastered knowledge points; and selecting the knowledge points with a specific learning class from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency to serve as the preferred recommended learning content of the target object.
2. The scene-based learning content recommendation method according to claim 1, wherein:
in step S1, acquiring an online learning history of a target object, and analyzing the online learning history to determine the proportion of knowledge points that the target object has learned in all course knowledge points; and further determining the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses, specifically comprising:
step S101, acquiring on-line learning text data historical browsing records of a target object in different learning time periods, and performing text character recognition processing on the on-line learning text data historical browsing records so as to determine learned knowledge points of the target object in each course chapter;
step S102, obtaining the ratio Q of the learned knowledge points of the target object in all the course knowledge points according to the following formula (1) and the above determined learned knowledge points:
in the above formula (1), R represents the total number of courses learned on the target object line, R has values of 1, 2, 3, …, R, M represents the total number of knowledge points included in all courses, n represents the total number of knowledge points included in all coursesrIndicates the number of chapters per r lessons, FriIndicates the number of knowledge points learned by the target object in the ith section of the nth course, i is 1, 2, 3, …, nr;
Step S103, eliminating the learned knowledge points from the knowledge points contained in all the courses one by one, thereby determining the unlearned knowledge points in the target object online learning scene.
3. The scene-based learning content recommendation method according to claim 2, wherein:
in step S2, acquiring an examination score corresponding to the target subject in an examination for a learned knowledge point, and determining, according to the examination score, that the knowledge point that the target subject does not completely grasp in the learned knowledge point specifically includes;
step S201, acquiring the examination score of each section of the corresponding course of the target object in the examination aiming at the learned knowledge point;
step S202, the learned knowledge points corresponding to the examination results of the target object in the examination, which are not more than 80% of the total results, are determined as the knowledge points which are not completely mastered by the target object.
4. The scene-based learning content recommendation method according to claim 2 or 3, characterized in that: in the step S3, determining the learning efficiency of the target object in the online learning scene according to the ratio and the incompletely grasped knowledge points; selecting knowledge points with specific learning class time from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency, wherein the selected knowledge points are specifically used as preferred recommended learning contents of the target object;
step S301, determining a learning efficiency identification value V of the target object in the online learning scene according to the following formula (2):
in the above formula (2), SrIndicating the 1 st chapter, the 2 nd chapter …, and the n th chapter of the target object in the r-th courserChapter 1, nrActual score S in examination corresponding to each chapterr1、Sr2…Average value of (d); g is an intermediate parameter;
the intermediate parameter G is determined by the following formula (3):
in the above formula (3), SriRepresenting the actual score of the target object in the examination corresponding to the ith section in the ith lesson; sri0Indicating the full score of the test corresponding to the ith section in the ith lesson;
step S302, comparing the learning efficiency identification value V with a preset learning efficiency identification value threshold, and if the learning efficiency identification value V exceeds the preset learning efficiency identification value threshold, selecting a knowledge point which is larger than a preset learning period in the actual learning period from the unlearned knowledge points or the incompletely mastered knowledge points as a preferred recommended learning content of the target object; and if the learning efficiency identification value V does not exceed the preset learning efficiency identification value, selecting the knowledge points with the actual learning period less than or equal to the preset learning period from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object.
5. The scene-based learning content recommendation system is characterized by comprising an online learning history acquisition and analysis module, an unlearned knowledge point determination module, an incompletely mastered knowledge point determination module, a learning efficiency determination module and a recommended learning content determination module; wherein the content of the first and second substances,
the on-line learning history acquisition and analysis module is used for acquiring an on-line learning history of a target object and analyzing the on-line learning history so as to determine the proportion of the learned knowledge points of the target object in all course knowledge points;
the unlearned knowledge point determining module is used for determining unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses; the incomplete-mastered knowledge point determining module is used for acquiring the corresponding examination score of the target object in the examination aiming at the learned knowledge point, and determining the knowledge point which is not completely mastered by the target object in the learned knowledge point according to the examination score;
the learning efficiency determining module is used for determining the learning efficiency of the target object in an online learning scene according to the occupation ratio and the incompletely mastered knowledge points;
and the recommended learning content determining module is used for selecting the knowledge points with a specific learning class from the unlearned knowledge points or the incompletely mastered knowledge points according to the learning efficiency to serve as the preferred recommended learning content of the target object.
6. The scene-based learning content recommendation system of claim 5, wherein:
the on-line learning history acquisition and analysis module acquires an on-line learning history of a target object, and analyzes the on-line learning history so as to determine the proportion of the knowledge points learned by the target object in all course knowledge points, specifically comprising:
acquiring on-line learning text data historical browsing records of a target object in different learning time periods, and performing text character recognition processing on the on-line learning text data historical browsing records so as to determine learned knowledge points of the target object in each course chapter;
and then obtaining the proportion Q of the knowledge points which have been learned by the target object in all course knowledge points according to the following formula (1) and the determined learned knowledge points:
in the above formula (1), R represents the total number of courses learned on the target object line, R has values of 1, 2, 3, …, and R, and M represents the total courses included in all coursesTotal number of knowledge points, nrIndicates the number of chapters per r lessons, FriIndicates the number of knowledge points learned by the target object in the ith section of the nth course, i is 1, 2, 3, …, nr;
And the number of the first and second groups,
the determining module of the unlearned knowledge points determines the unlearned knowledge points in the online learning scene of the target object according to the learned knowledge points and the knowledge points of all courses, and specifically includes:
and eliminating the learned knowledge points one by one from the knowledge points contained in all the courses, thereby determining the unknown knowledge points in the online learning scene of the target object.
7. The scene-based learning content recommendation system of claim 6, wherein:
the step of acquiring the examination score corresponding to the target object in the examination aiming at the learned knowledge point by the incompletely mastered knowledge point determining module and determining the knowledge point which is not completely mastered by the target object in the learned knowledge point according to the examination score specifically comprises the following steps:
acquiring the examination score of each section of the corresponding course of the target object in the examination aiming at the learned knowledge point;
and then determining the learned knowledge points corresponding to the examination results of the target object in the examination, wherein the examination results of the target object in the examination do not exceed 80% of the total results, as the knowledge points which are not completely mastered by the target object.
8. The scene-based learning content recommendation system according to claim 6 or 7, characterized in that: the learning efficiency determination module determines the learning efficiency of the target object in the online learning scene according to the ratio and the incompletely mastered knowledge points, and specifically includes:
determining a learning efficiency identification value V of the target object in an online learning scene according to the following formula (2):
in the above formula (2), SrIndicating the 1 st chapter, the 2 nd chapter …, and the n th chapter of the target object in the r-th courserChapter 1, nrActual score S in examination corresponding to each chapterr1、Sr2…Average value of (d); g is an intermediate parameter;
the intermediate parameter G is determined by the following formula (3):
in the above formula (3), SriRepresenting the actual score of the target object in the examination corresponding to the ith section in the ith lesson; sri0Indicating the full score of the test corresponding to the ith section in the ith lesson;
and the number of the first and second groups,
the recommended learning content determining module selects a knowledge point having a specific learning course from the unlearned knowledge points or the incompletely grasped knowledge points according to the learning efficiency, and the recommended learning content determining module as the preferred recommended learning content of the target object specifically includes:
comparing the learning efficiency identification value V with a preset learning efficiency identification value threshold, and if the learning efficiency identification value V exceeds the preset learning efficiency identification value threshold, selecting a knowledge point which is larger than a preset learning period in the actual learning period from the unlearned knowledge points or the incompletely mastered knowledge points as a preferred recommended learning content of the target object; and if the learning efficiency identification value V does not exceed the preset learning efficiency identification value, selecting the knowledge points with the actual learning period less than or equal to the preset learning period from the unlearned knowledge points or the incompletely mastered knowledge points as the preferred recommended learning content of the target object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110154590.3A CN112818236A (en) | 2021-02-04 | 2021-02-04 | Learning content recommendation method and system based on scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110154590.3A CN112818236A (en) | 2021-02-04 | 2021-02-04 | Learning content recommendation method and system based on scene |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112818236A true CN112818236A (en) | 2021-05-18 |
Family
ID=75861399
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110154590.3A Pending CN112818236A (en) | 2021-02-04 | 2021-02-04 | Learning content recommendation method and system based on scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112818236A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114647721A (en) * | 2022-05-23 | 2022-06-21 | 风林科技(深圳)有限公司 | Educational intelligent robot control method, device and medium |
-
2021
- 2021-02-04 CN CN202110154590.3A patent/CN112818236A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114647721A (en) * | 2022-05-23 | 2022-06-21 | 风林科技(深圳)有限公司 | Educational intelligent robot control method, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021000909A1 (en) | Curriculum optimisation method, apparatus, and system | |
CN111144191B (en) | Font identification method, font identification device, electronic equipment and storage medium | |
CN111090809A (en) | Topic recommendation method and device, computer equipment and storage medium | |
CN110659311B (en) | Topic pushing method and device, electronic equipment and storage medium | |
CN114219224B (en) | Teaching quality detection method and system for intelligent classroom | |
CN114579760A (en) | Student wrong question knowledge point self-adaptive stage learning system | |
CN111597305B (en) | Entity marking method, entity marking device, computer equipment and storage medium | |
CN112163760A (en) | Student learning concentration degree detection method and system | |
CN115358897B (en) | Student management method, system, terminal and storage medium based on electronic student identity card | |
CN114581269A (en) | All-dimensional student learning condition tracking platform from homework to examination | |
CN110111011B (en) | Teaching quality supervision method and device and electronic equipment | |
CN112818236A (en) | Learning content recommendation method and system based on scene | |
CN112015783B (en) | Interactive learning process generation method and system | |
CN112507792B (en) | Online video key frame positioning method, positioning system, equipment and storage medium | |
CN113535982A (en) | Big data-based teaching system | |
CN116304315B (en) | Intelligent content recommendation system for online teaching | |
CN112132715A (en) | Intelligent courseware management method and system | |
CN116704606A (en) | Physicochemical experiment operation behavior identification method, system, device and storage medium | |
CN112015830B (en) | Question storage method suitable for adaptive learning | |
CN112163975A (en) | Intelligent learning guiding and prompting method and system | |
CN114971962A (en) | Student homework evaluation method and device, electronic device and storage medium | |
CN113869569A (en) | Learning score prediction and personalized intervention method based on decision tree | |
CN114580882A (en) | Teaching effect evaluation system and method for hybrid teaching method | |
CN114004499A (en) | Long calculation terminal of time of teaching operation | |
CN115687630A (en) | Method and device for generating course learning report |
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 |