CN112950425B - Multi-dimension-based personalized learning plan dynamic generation method - Google Patents

Multi-dimension-based personalized learning plan dynamic generation method Download PDF

Info

Publication number
CN112950425B
CN112950425B CN202110258197.9A CN202110258197A CN112950425B CN 112950425 B CN112950425 B CN 112950425B CN 202110258197 A CN202110258197 A CN 202110258197A CN 112950425 B CN112950425 B CN 112950425B
Authority
CN
China
Prior art keywords
learning
data
content
course
plan
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
Application number
CN202110258197.9A
Other languages
Chinese (zh)
Other versions
CN112950425A (en
Inventor
郑洪涛
江华清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Chuangke Network Technology Co ltd
Original Assignee
Zhejiang Chuangke Network Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Chuangke Network Technology Co ltd filed Critical Zhejiang Chuangke Network Technology Co ltd
Priority to CN202110258197.9A priority Critical patent/CN112950425B/en
Publication of CN112950425A publication Critical patent/CN112950425A/en
Application granted granted Critical
Publication of CN112950425B publication Critical patent/CN112950425B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0633—Workflow analysis
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Educational Technology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The invention provides a multi-dimensional-based personalized learning plan dynamic generation method. Pre-building a learning record frame of a learner and a course planning frame of a teacher; acquiring multidimensional data learned by students according to the learning record frame; acquiring learning task data arranged by a teacher according to the course planning framework; determining learning state data according to the multi-dimensional data and the learning task data; and reassigning the daily learning plans of the students according to the learning state data to generate personalized learning plans with preferential non-learning content. According to the invention, the learning condition of the student is recorded, and the course planning of the teacher is recorded, so that the learning condition of the student and the condition of the arranged learning task can be clearly known, and the course task is continuously updated according to the priority of the course content in the course task, so that a multi-dimensional personalized learning plan is generated, and the learning of the student on the key knowledge is improved.

Description

Multi-dimension-based personalized learning plan dynamic generation method
Technical Field
The invention relates to the technical field of online learning, in particular to a multi-dimensional-based personalized learning plan dynamic generation method.
Background
At present, along with the rapid development of internet technology and the realization of online class, a study plan is formulated by a teacher, but the study plan of the teacher only accords with most people, the study plan assignment of a single student is not necessarily effective, the conventional study plan is randomly arranged by the teacher, and important and difficult division is possible, but knowledge points are divided, and the knowledge points cannot be studied in time. A personalized learning plan conforming to each student and performing knowledge point priority regulation cannot be generated.
Disclosure of Invention
The invention provides a multi-dimensional-based personalized learning plan dynamic generation method, which is used for solving the problem that a teacher is randomly arranged, and the important points and the difficult points are possibly divided, but the division result is not fine. It is impossible to generate a situation conforming to the personalized learning plan of each student.
A method for dynamically generating a personalized learning plan based on multiple dimensions comprises the following steps:
pre-building a learning record frame of a learner and a course planning frame of a teacher;
acquiring multidimensional data learned by students according to the learning record frame; wherein,
the multi-dimensional data includes: learning frequent data, learning difficulty data, learning content priority data;
acquiring learning task data arranged by a teacher according to the course planning framework; wherein,
the learning task data includes: learning key content, learning content classification and learning planning;
determining learning state data according to the multi-dimensional data and the learning task data;
the learning state data includes: unlearned content, unlearned content priority, and learned content;
and reassigning the daily learning plans of the students according to the learning state data to generate personalized learning plans with preferential non-learning content.
As an embodiment of the present invention: the learning record frame of the pre-built student comprises:
acquiring a first program component for data acquisition, and building a learning model of a student;
determining a learning environment generated by the student according to the learning model;
determining the type of data generated by the student according to the learning environment; wherein,
the data types include: identity type, time type, learning content type;
according to the data type, a first program component is set for data acquisition, and format definition is carried out on data conversion acquired by the first program component; wherein,
the format includes: text, video, audio, and graphics;
and combining the first program components after the format definition to generate a learning record frame.
As an embodiment of the present invention: the pre-built teacher's course planning framework includes:
acquiring a second program component for data acquisition, and building a teaching model of a teacher;
determining the teaching content of the student according to the teaching model;
determining the course type of the student according to the teaching content;
setting a second program component to issue a learning task according to the course type, setting time for the learning task issued by the second program component, and issuing the learning task at a fixed time according to the time setting;
and combining the second program components after the time setting to generate a course planning framework.
As an embodiment of the present invention: the multi-dimensional data of student study is obtained according to the study record frame, which comprises the following steps:
acquiring student identity information according to the learning record frame;
determining the learning time point, the learning duration and the learning course of the student according to the student identity information;
determining the learning time and total time of the student on the same day according to the learning time point and the learning time length, and generating learning time data;
according to the learning courses and the learning time length, determining the time length of learning contents of different course types of students, and generating learning difficulty data according to the course types;
determining learning purposes of different courses according to the learning courses;
determining course priorities of different course types according to the learning purpose;
determining learning content priority data according to the learning duration and course priority;
and generating multi-dimensional data according to the learning frequent data, the learning difficulty data and the learning content priority data.
As an embodiment of the present invention: the method for obtaining the multidimensional data of student learning according to the learning record frame further comprises the following steps:
determining the data type of the multi-dimensional data according to the multi-dimensional data;
setting a data key and a data unique identifier according to the data type; wherein,
the data key comprises: name, time, course type, data format;
setting a first classification rule of the data according to the unique data identifier;
setting a second classification rule of the data according to the data keywords;
and acquiring the learning data of the students according to the first classification rule, the second classification rule and the learning record frame to generate multi-dimensional data.
As an embodiment of the present invention: the step of obtaining learning task data arranged by a teacher according to the course planning framework comprises the following steps:
acquiring course task information according to the course planning framework;
determining course type, course content and course learning duration according to the course task information;
determining task duration corresponding to each class of courses of students according to the course content and the course learning duration, and determining the key content of learning according to the task duration;
according to the course types and the course contents, determining learning contents corresponding to each class of courses, and determining learning content classification;
according to the course content and the learning time length, determining learning time and learning time points corresponding to each part of course content, and determining a learning plan;
and generating learning task data according to the learning key content, the learning content classification and the learning plan.
As an embodiment of the present invention: according to the course planning framework, learning task data of teacher arrangement is obtained, and the method further comprises the following steps:
determining a learning plan of the learning task data according to the learning task data;
setting the plan release time of each learning plan according to the learning plan;
determining a plan release rule of a learning plan according to the plan release time;
and collecting the task data of the teacher according to the plan release rule and the course planning framework to generate learning task data.
As an embodiment of the present invention: the determining learning state data according to the multi-dimensional data and the learning task data comprises the following steps:
determining daily learning data of the students according to the multidimensional data, and generating a learning log;
generating a student study attendance record list according to the study task data and the study log;
determining learned content and unlearned content according to the learning attendance record table;
determining the priority of the unlearned content according to the unlearned content and the priority data of the learned content;
and generating learning state data according to the unlearned content, the unlearned content priority and the learned content.
As an embodiment of the present invention: the reassigning daily learning plans of students according to the learning state data to generate personalized learning plans with preferential non-learning content, comprising the following steps:
acquiring the learning state data and determining the history learning data of the students;
determining a learning task plan of the student according to the historical learning data; wherein,
the learning task plan comprises an executed learning plan and a learning plan to be executed;
and reallocating the learning content with high priority in the un-learned content according to the executed learning plan, the to-be-executed learning plan, the un-learned content and the un-learned content priority to generate a personalized learning plan.
As an embodiment of the present invention: the daily learning plans of the students are redistributed according to the learning state data, and personalized learning plans with preferential non-learning content are generated, and the method further comprises the following steps:
step 1: according to the learning state data, constructing a historical learning plan model of the student:
wherein R is i A data capacity representing the i-th learning state data; beta i A start difficulty setting value representing the ith learning state data; t (T) i A learning time indicating the i-th learning state data; s is S t，i Representing the implementation result parameters of the ith learning generation learning plan at the time t;
step 2: constructing a student regulation model according to the to-be-executed learning plan, the non-learning content and the non-learning content priority:
wherein S is j Representing the plan features corresponding to the j-th unlearned data; w (w) j An address representing the i-th unlearned data; t (T) j Representing data characteristics corresponding to the i-th unlearned data; m is M j A destination feature representing the i-th unlearned data; y represents the data characteristics of the ith unlearned data;
step 3, according to the regulation model and the learning plan model, through exponential modeling, through determining a personalized learning plan:
when f is more than or equal to 1, a personalized learning plan can be generated; when f < 1, a personalized learning plan cannot be generated.
The beneficial effects are as follows: according to the invention, the learning condition of the student is recorded, and the course planning of the teacher is recorded, so that the learning condition of the student and the condition of the arranged learning task can be clearly known, and the course task is continuously updated according to the priority of the course content in the course task, so that a multi-dimensional personalized learning plan is generated, and the learning of the student on the key knowledge is 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 may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a method for dynamically generating a personalized learning plan based on multiple dimensions in an embodiment of the invention;
FIG. 2 is a schematic diagram of a frame generation in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
As shown in fig. 1, the invention provides a multi-dimensional personalized learning plan dynamic generation method, which comprises the following steps:
step 100: pre-building a learning record frame of a learner and a course planning frame of a teacher;
step 101: acquiring multidimensional data learned by students according to the learning record frame; wherein,
the multi-dimensional data includes: learning frequent data, learning difficulty data, learning content priority data;
step 102: acquiring learning task data arranged by a teacher according to the course planning framework; wherein,
the learning task data includes: learning key content, learning content classification and learning planning;
step 103: determining learning state data according to the multi-dimensional data and the learning task data;
the learning state data includes: unlearned content, unlearned content priority, and learned content;
step 104: and reassigning the daily learning plans of the students according to the learning state data to generate personalized learning plans with preferential non-learning content.
The working principle of the technical scheme is as follows: the invention relates to a personalized learning plan which dynamically adjusts a learning plan of a student from three dimensions of learning duration of the student, learning difficulty of the student and priority of a learning course, learned content and unlearned content. The learning record frame is used for recording learning information of students; for example: the learning time of the students comprises learning time points, year, month and day and duration of learning a certain course, and each day is used as a statistics period to carry out uninterrupted real-time statistics. The course planning framework of the teacher is used for acquiring information of the teacher on homework arrangement of students; for example: the homework of students is divided according to the type of the learned courses, such as physics, language, english, chemistry, biology, music, history and the like, and the key contents of the learned courses can carry out multi-arrangement homework, for example, a certain language in the language is the key contents, and in mathematics, calculus is the key contents and the like. The learning content classification is to classify and refine the operation according to the topic type and the attributive chapter after the course classification; for example, select a question, a knowledge point belonging to a section of the history, chapter four; the priority of the learning content is determined according to the difficulty of the title and the importance degree of the course, and the meaning of the priority is the priority of learning, and whether the learning should be prioritized or not. According to the invention, multi-dimensional data and learning task data are determined, learning state data are compared between learning tasks which are already learned by students and data of all tasks which are arranged by teachers, and the learning tasks which are arranged by the teachers are judged to be learned, and finally, the courses are rearranged according to the priority of the course content which is not learned, so that the students can learn the learning tasks with high priority all the time along with the updating of teaching tasks, and a personalized dynamic learning plan is generated.
The beneficial effects of the technical scheme are as follows: according to the invention, the learning condition of the student is recorded, and the course planning of the teacher is recorded, so that the learning condition of the student and the condition of the arranged learning task can be clearly known, and the course task is continuously updated according to the priority of the course content in the course task, so that a multi-dimensional personalized learning plan is generated, and the learning of the student on the key knowledge is improved.
As an embodiment of the present invention: as shown in fig. 2, the pre-building a learning record frame of a learner includes:
acquiring a first program component for data acquisition, and building a learning model of a student;
determining a learning environment generated by the student according to the learning model;
determining the type of data generated by the student according to the learning environment; wherein,
the data types include: identity type, time type, learning content type;
according to the data type, a first program component is set for data acquisition, and format definition is carried out on data conversion acquired by the first program component; wherein,
the format includes: text, video, audio, and graphics;
and combining the first program components after the format definition to generate a learning record frame.
The working principle of the technical scheme is as follows: when the learning record model is built, different data are collected through a plurality of different assemblies, the building of the learning record frame is realized, the learning process and the learning content modeling are carried out in the learning model when students learn, the learning environment of the students is judged, the data can be clearly generated from the learning environment, the data are further divided according to the data types of the generated data, the data after division are clearer, and finally, the data collected by each assembly are subjected to format definition based on the data types, so that the data formats obtained by different assemblies can be the same or different. The final purpose of the format definition is to enable any user to recognize this, and thus, the data is converted by the components into visual text, video, audio and graphics.
The beneficial effects of the technical scheme are as follows: according to the invention, the learning record model is built, so that the learning content, time, identity and other data of the students in the learning process of the students can be acquired and displayed in a visual form, and the learning condition of the students can be conveniently analyzed.
As an embodiment of the present invention: as shown in fig. 2, the pre-building a course planning framework of a teacher includes:
acquiring a second program component for data acquisition, and building a teaching model of a teacher;
determining the teaching content of the student according to the teaching model;
determining the course type of the student according to the teaching content;
the teaching content and course type are running processes of data.
Setting a second program component to issue a learning task according to the course type, setting time for the learning task issued by the second program component, and issuing the learning task at a fixed time according to the time setting;
and combining the second program components after the time setting to generate a course planning framework.
The working principle of the technical scheme is as follows: the invention mainly aims to collect task data of learning tasks arranged by a teacher when a course planning model of the teacher is built. Therefore, the second program component mainly distributes teaching tasks according to the set time by setting time after the teaching content and the teaching type are clear, and therefore, the invention obtains a course planning framework after the time is set.
The beneficial effects of the technical scheme are as follows: according to the invention, by constructing a course planning framework of a teacher, the teaching tasks issued by the teacher are determined, and the teaching tasks comprise teaching contents and teaching time, so that the teaching data issued by the teacher can be determined. The learning content of the student is conveniently compared with the learning content of the student, the content without learning is judged, and the acquisition of teaching data is realized.
As an embodiment of the present invention: the multi-dimensional data of student study is obtained according to the study record frame, which comprises the following steps:
acquiring student identity information according to the learning record frame;
determining the learning time point, the learning duration and the learning course of the student according to the student identity information;
determining the learning time and total time of the student on the same day according to the learning time point and the learning time length, and generating learning time data;
according to the learning courses and the learning time length, determining the time length of learning contents of different course types of students, and generating learning difficulty data according to the course types;
determining learning purposes of different courses according to the learning courses;
determining course priorities of different course types according to the learning purpose;
determining learning content priority data according to the learning duration and course priority;
and generating multi-dimensional data according to the learning frequent data, the learning difficulty data and the learning content priority data.
The working principle of the technical scheme is as follows: when multi-dimensional data in the student learning process is collected, identity information of the student is firstly determined, and then the daily learning time and total learning time of the student, the learning time of different types of courses and the learning time of related content and knowledge points are determined through three aspects of learning time points, learning time and learning courses. Finally, determining the difficulty of each course and each knowledge point in the learning according to the course type; in the determination of the priority, the invention judges the priority based on the learning purpose and the learning duration of different courses.
The beneficial effects of the technical scheme are as follows: the invention can facilitate analysis of learning data of each student and individual learning condition of each student. The learning difficulty data can be used for judging the acceptance of students to each knowledge, so that teachers can properly prolong and reduce the response time of homework, and for the priority data, the teachers can realize the priority arrangement of courses according to the priority data, and the system can automatically adjust the priority data during the homework arrangement.
As an embodiment of the present invention: the method for obtaining the multidimensional data of student learning according to the learning record frame further comprises the following steps:
determining the data type of the multi-dimensional data according to the multi-dimensional data;
setting a data key and a data unique identifier according to the data type; wherein,
the data key comprises: name, time, course type, data format;
setting a first classification rule of the data according to the unique data identifier;
setting a second classification rule of the data according to the data keywords;
and acquiring the learning data of the students according to the first classification rule, the second classification rule and the learning record frame to generate multi-dimensional data.
The working principle of the technical scheme is as follows: when the method acquires multi-dimensional data, the unique data identifier and the key words of the data are set, and the unique data identifier and the key words of the data are embodied in a regular form.
The beneficial effects of the technical scheme are as follows: the situation that data are repeated when data are acquired can be prevented through the unique identification, and the data keywords can be searched through the keywords when the data are searched, so that the efficiency of the data in searching and inquiring is improved.
As an embodiment of the present invention: the step of obtaining learning task data arranged by a teacher according to the course planning framework comprises the following steps:
acquiring course task information according to the course planning framework;
determining course type, course content and course learning duration according to the course task information;
determining task duration corresponding to each class of courses of students according to the course content and the course learning duration, and determining the key content of learning according to the task duration;
according to the course types and the course contents, determining learning contents corresponding to each class of courses, and determining learning content classification;
according to the course content and the learning time length, determining learning time and learning time points corresponding to each part of course content, and determining a learning plan;
and generating learning task data according to the learning key content, the learning content classification and the learning plan.
The working principle of the technical scheme is as follows: when learning task data are acquired, the data processing of teacher arrangement operation is carried out from three aspects of course type, course content and course learning duration through course task information. Since the course contents of different course types are different, the course learning contents are corresponding when the teacher arranges the work, and thus the present invention can determine the learning content classification. According to the course content and the learning time length, after the course content in each time length is determined, the learning time length comprises the learning date and time point, in this case, the learning plan can be determined, and finally the learning task data can be determined.
The beneficial effects of the technical scheme are as follows: the invention can determine the learning task data composed of the key points, duration, learning plans and the like of the operation arranged by the teacher through the course planning framework of the teacher. Furthermore, the invention can obtain the learning task data of teachers.
As an embodiment of the present invention: according to the course planning framework, learning task data of teacher arrangement is obtained, and the method further comprises the following steps:
determining a learning plan of the learning task data according to the learning task data;
setting the plan release time of each learning plan according to the learning plan;
determining a plan release rule of a learning plan according to the plan release time;
and collecting the task data of the teacher according to the plan release rule and the course planning framework to generate learning task data.
The working principle of the technical scheme is as follows: when learning task data of students are acquired, not only learning plan data but also release time and release rules of a learning plan are required to be determined, and the learning task data is acquired according to the rules.
The beneficial effects of the technical scheme are as follows: when the learning task data are acquired, the invention ensures the high efficiency and the standardization of the release of each learning plan by setting the release time of the learning plan. Through the release rule, task release can be ensured to accord with the rule when the task data is released, and the data is convenient to collect.
As an embodiment of the present invention: the determining learning state data according to the multi-dimensional data and the learning task data comprises the following steps:
determining daily learning data of the students according to the multidimensional data, and generating a learning log;
generating a student study attendance record list according to the study task data and the study log;
determining learned content and unlearned content according to the learning attendance record table;
determining the priority of the unlearned content according to the unlearned content and the priority data of the learned content;
and generating learning state data according to the unlearned content, the unlearned content priority and the learned content.
The working principle of the technical scheme is as follows: the invention determines the data which are learned by students and the data which are not learned in the learning plan through multidimensional data and learning task data, thereby determining the learning state of the students during learning. In the process, the invention can determine the content which is already learned and the content which is not already learned by using the learning log and the learning attendance record table. Then, through the pre-determined learning content priority data, the priority of the un-learned content can be determined, and the learning state data of the students can be further judged.
The beneficial effects of the technical scheme are as follows: in order to dynamically change a student learning plan, learning state data of a student is obtained through data processing, and the learning condition of the student is determined through the data.
As an embodiment of the present invention: the reassigning daily learning plans of students according to the learning state data to generate personalized learning plans with preferential non-learning content, comprising the following steps:
acquiring the learning state data and determining the history learning data of the students;
determining a learning task plan of the student according to the historical learning data; wherein,
the learning task plan comprises an executed learning plan and a learning plan to be executed;
and reallocating the learning content with high priority in the un-learned content according to the executed learning plan, the to-be-executed learning plan, the un-learned content and the un-learned content priority to generate a personalized learning plan.
The working principle of the technical scheme is as follows: according to the invention, the historical learning condition of the student is determined according to the learning state data of the student, the original learning plan of the student is clarified, and then the high-efficiency personalized learning plan is obtained by reassigning the content with high priority.
Although the personalized learning generated in the later period is regulated, the personalized learning efficiency of the task issued by the original teacher is not better than that of the personalized learning plan, and at the moment, the step of the invention is needed to judge whether the personalized learning plan accords or not.
As an embodiment of the present invention: the student is provided with a learning state data according to the learning state data
Is to generate a personalized learning plan prioritized with non-learning content, further comprising the steps of:
step 1: according to the learning state data, constructing a historical learning plan model of the student:
wherein R is i A data capacity representing the i-th learning state data; beta i A start difficulty setting value representing the ith learning state data; t (T) i A learning time indicating the i-th learning state data; s is S t，i Representing the implementation result parameters of the ith learning generation learning plan at the time t; in the present inventionThe status characteristics of the students which are learned and not learned in the learning time are determined. />Representing each learned knowledge point at each moment; />Belongs to an exponential function and is used for realizing a history learning meter according to the exponential functionThe specific environment of the graphical representation of the scribe.
Step 2: constructing a student regulation model according to the to-be-executed learning plan, the non-learning content and the non-learning content priority:
wherein S is j Representing the plan features corresponding to the j-th unlearned data; w (w) j An address representing the i-th unlearned data; t (T) j Representing data characteristics corresponding to the i-th unlearned data; m is M j A destination feature representing the i-th unlearned data; y represents the data characteristics of the ith unlearned data;
step 3, according to the regulation model and the learning plan model, through exponential modeling, through determining a personalized learning plan:
when f is more than or equal to 1, a personalized learning plan can be generated; when f < 1, a personalized learning plan cannot be generated.
According to the technical scheme, firstly, on the basis of learning state data, through double synchronous modeling of indexes and features, according to 4 aspects of data quality, initial difficulty, learning time and implementation results, the historical learning plan can be determined, then through an adjustment model to be executed, learning data of students are determined from three directions of the learning plan to be executed, non-learning content and non-learning content priority, and finally, whether the learning data accords with the personalized plan is determined through a proportion algorithm.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (8)

1. A method for dynamically generating a personalized learning plan based on multiple dimensions is characterized by comprising the following steps:
pre-building a learning record frame of a learner and a course planning frame of a teacher;
acquiring multidimensional data learned by students according to the learning record frame; wherein,
the multi-dimensional data includes: learning frequent data, learning difficulty data, learning content priority data;
acquiring learning task data arranged by a teacher according to the course planning framework; wherein,
the learning task data includes: learning key content, learning content classification and learning planning;
determining learning state data according to the multi-dimensional data and the learning task data;
the learning state data includes: unlearned content, unlearned content priority, and learned content;
reassigning the daily learning plans of the students according to the learning state data to generate personalized learning plans with preferential non-learning content;
the reassigning daily learning plans of students according to the learning state data to generate personalized learning plans with preferential non-learning content, comprising the following steps:
acquiring the learning state data and determining the history learning data of the students;
determining a learning task plan of the student according to the historical learning data; wherein,
the learning task plan comprises an executed learning plan and a learning plan to be executed;
reassigning the learning content with high priority in the un-learned content according to the executed learning plan, the to-be-executed learning plan, the un-learned content and the un-learned content priority to generate a personalized learning plan;
the daily learning plans of the students are redistributed according to the learning state data, and personalized learning plans with preferential non-learning content are generated, and the method further comprises the following steps:
step 1: according to the learning state data, constructing a historical learning plan model of the student:
wherein,indicate->Data capacity of individual learning state data; />Indicate->Initial difficulty set values of the individual learning state data; />Indicate->Learning time of the individual learning state data; />Indicate->Individual learning generation learning plan is +.>The implementation result parameters of the moment;
step 2: constructing a student regulation model according to the to-be-executed learning plan, the non-learning content and the non-learning content priority:
wherein,indicate->Planning characteristics corresponding to the non-learned data; />Indicate->Addresses of the individual unlearned data; />Indicate->Data characteristics corresponding to the non-learned data; />Indicate->The target features of the individual unlearned data; />Indicate->Data characteristics of the individual unlearned data;
step 3, according to the regulation model and the learning plan model, through exponential modeling, through determining a personalized learning plan:
wherein whenWhen the method is used, a personalized learning plan can be generated; when->At this time, a personalized learning plan cannot be generated.
2. The method for dynamically generating a personalized learning plan based on multiple dimensions according to claim 1, wherein the pre-building of a learning record frame of a learner comprises:
acquiring a first program component for data acquisition, and building a learning model of a student;
determining a learning environment generated by the student according to the learning model;
determining the type of data generated by the student according to the learning environment; wherein,
the data types include: identity type, time type, learning content type;
according to the data type, a first program component is set for data acquisition, and format definition is carried out on data conversion acquired by the first program component; wherein,
the format includes: text, video, audio, and graphics;
and combining the first program components after the format definition to generate a learning record frame.
3. The method for dynamically generating a multi-dimensional personalized learning plan as recited in claim 1, wherein the pre-building of the teacher's curriculum planning framework comprises:
acquiring a second program component for data acquisition, and building a teaching model of a teacher;
determining the teaching content of the student according to the teaching model;
determining the course type of the student according to the teaching content;
setting a second program component to issue a learning task according to the course type, setting time for the learning task issued by the second program component, and issuing the learning task at a fixed time according to the time setting;
and combining the second program components after the time setting to generate a course planning framework.
4. The method for dynamically generating a personalized learning plan based on multiple dimensions according to claim 1, wherein the acquiring the multiple dimensions data of the student learning according to the learning record frame comprises:
acquiring student identity information according to the learning record frame;
determining the learning time point, the learning duration and the learning course of the student according to the student identity information;
determining the learning time and total time of the student on the same day according to the learning time point and the learning time length, and generating learning time data;
according to the learning courses and the learning time length, determining the time length of learning contents of different course types of students, and generating learning difficulty data according to the course types;
determining learning purposes of different courses according to the learning courses;
determining course priorities of different course types according to the learning purpose;
determining learning content priority data according to the learning duration and course priority;
and generating multi-dimensional data according to the learning frequent data, the learning difficulty data and the learning content priority data.
5. The method for dynamically generating a personalized learning plan based on multiple dimensions according to claim 1, wherein the acquiring the multiple dimensions data of the student learning according to the learning record frame further comprises:
determining the data type of the multi-dimensional data according to the multi-dimensional data;
setting a data key and a data unique identifier according to the data type; wherein,
the data key comprises: name, time, course type, data format;
setting a first classification rule of the data according to the unique data identifier;
setting a second classification rule of the data according to the data keywords;
and acquiring the learning data of the students according to the first classification rule, the second classification rule and the learning record frame to generate multi-dimensional data.
6. The method for dynamically generating a multi-dimensional personalized learning plan as recited in claim 1, wherein the obtaining learning task data of the teacher arrangement according to the curriculum planning framework comprises:
acquiring course task information according to the course planning framework;
determining course type, course content and course learning duration according to the course task information;
determining task duration corresponding to each class of courses of students according to the course content and the course learning duration, and determining the key content of learning according to the task duration;
according to the course types and the course contents, determining learning contents corresponding to each class of courses, and determining learning content classification;
according to the course content and the learning time length, determining learning time and learning time points corresponding to each part of course content, and determining a learning plan;
and generating learning task data according to the learning key content, the learning content classification and the learning plan.
7. The method for dynamically generating a multi-dimensional personalized learning plan according to claim 1, wherein the acquiring learning task data of a teacher's arrangement according to the course planning framework further comprises:
determining a learning plan of the learning task data according to the learning task data;
setting the plan release time of each learning plan according to the learning plan;
determining a plan release rule of a learning plan according to the plan release time;
and collecting the task data of the teacher according to the plan release rule and the course planning framework to generate learning task data.
8. The method for dynamically generating a personalized learning plan based on multiple dimensions according to claim 1, wherein determining learning state data according to the multiple dimensions data and learning task data comprises:
determining daily learning data of the students according to the multidimensional data, and generating a learning log;
generating a student study attendance record list according to the study task data and the study log;
determining learned content and unlearned content according to the learning attendance record table;
determining the priority of the unlearned content according to the unlearned content and the priority data of the learned content;
and generating learning state data according to the unlearned content, the unlearned content priority and the learned content.
CN202110258197.9A 2021-03-09 2021-03-09 Multi-dimension-based personalized learning plan dynamic generation method Active CN112950425B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110258197.9A CN112950425B (en) 2021-03-09 2021-03-09 Multi-dimension-based personalized learning plan dynamic generation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110258197.9A CN112950425B (en) 2021-03-09 2021-03-09 Multi-dimension-based personalized learning plan dynamic generation method

Publications (2)

Publication Number Publication Date
CN112950425A CN112950425A (en) 2021-06-11
CN112950425B true CN112950425B (en) 2024-02-06

Family

ID=76229010

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110258197.9A Active CN112950425B (en) 2021-03-09 2021-03-09 Multi-dimension-based personalized learning plan dynamic generation method

Country Status (1)

Country Link
CN (1) CN112950425B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113487248B (en) * 2021-09-07 2021-12-10 深圳市启程教育科技有限公司 Personalized course customization system and method based on big data
CN116416097B (en) * 2023-06-02 2023-08-18 成都优学家科技有限公司 Teaching method, system and equipment based on multidimensional teaching model

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108806341A (en) * 2018-03-29 2018-11-13 上海乂学教育科技有限公司 A kind of optimal individualized learning paths planning method
CN110047340A (en) * 2019-03-29 2019-07-23 广州恒智教育科技有限公司 A kind of test and training method and system of personalization
CN111915458A (en) * 2020-07-13 2020-11-10 同济大学 On-line experiment teaching system for exploration type and personalized learning
CN112016767A (en) * 2020-10-09 2020-12-01 北京高思博乐教育科技股份有限公司 Dynamic planning method and device for learning route
CN112396330A (en) * 2020-11-24 2021-02-23 中教云智数字科技有限公司 Learning scheme planning method based on machine learning

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150206441A1 (en) * 2014-01-18 2015-07-23 Invent.ly LLC Personalized online learning management system and method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108806341A (en) * 2018-03-29 2018-11-13 上海乂学教育科技有限公司 A kind of optimal individualized learning paths planning method
CN110047340A (en) * 2019-03-29 2019-07-23 广州恒智教育科技有限公司 A kind of test and training method and system of personalization
CN111915458A (en) * 2020-07-13 2020-11-10 同济大学 On-line experiment teaching system for exploration type and personalized learning
CN112016767A (en) * 2020-10-09 2020-12-01 北京高思博乐教育科技股份有限公司 Dynamic planning method and device for learning route
CN112396330A (en) * 2020-11-24 2021-02-23 中教云智数字科技有限公司 Learning scheme planning method based on machine learning

Also Published As

Publication number Publication date
CN112950425A (en) 2021-06-11

Similar Documents

Publication Publication Date Title
CN110992227B (en) School enterprise and professional skill talent combining culture system and method
CN112950425B (en) Multi-dimension-based personalized learning plan dynamic generation method
Zhang et al. A brief analysis of the key technologies and applications of educational data mining on online learning platform
Kuzminskyi et al. Information Support of Educationalists as an Important Function of a Postgraduate Education System.
Andryukhina et al. The Model of Monitoring of Vocational Pedagogical Competences of Professors in Secondary Vocational Education.
CN108109444B (en) Document teaching notes generation method based on audio teaching
WO2022170985A1 (en) Exercise selection method and apparatus, and computer device and storage medium
Javidi et al. Educational data mining and learning analytics: overview of benefits and challenges
CN114186983B (en) Video interview multidimensional scoring method, system, computer equipment and storage medium
CN110827181A (en) Career planning analysis system based on big data
Stefanova et al. Educational data mining perspectives within university big data environment
Sabin et al. The impact of automated timetabling on universities—A case study
CN111104455A (en) Multisource and multidimensional school teaching transverse information difference comparison analysis method
Larasati et al. Application for Lecturer Recruitment Using Simple Additive Weighting (SAW) Method Case Study: Tanri Abeng University Jakarta
CN108305193B (en) Dynamic course creation method and system
Housni et al. Applying Data Analytics and Cumulative Accuracy Profile (CAP) Approach in Real-Time Maintenance of Instructional Design Models
CN114328667A (en) Construction and system of university department portrait model based on employment data
Gao et al. optimization design and implementation of smart multimedia college English classroom integrating internet of things technology
Guo Course Analysis and Management System Design Based on Big Data Technology
CN116432890B (en) Craftsman fission management system and method based on recommendation relationship self-binding
Aprianto et al. Management of Education Utilizing Technology for Schools in Southeast Asia
Surendran et al. Improving the quality of education through data analytics and big data contributions
Li et al. The Research on Student Data Analysis System Based on Data Mining
Hua Research on Design of English Teaching Resource Management System Based on Collaborative Recommendation
Unger et al. Data Literacy

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