CN115952908A - Learning path planning method, system, device and storage medium - Google Patents
Learning path planning method, system, device and storage medium Download PDFInfo
- Publication number
- CN115952908A CN115952908A CN202211738319.5A CN202211738319A CN115952908A CN 115952908 A CN115952908 A CN 115952908A CN 202211738319 A CN202211738319 A CN 202211738319A CN 115952908 A CN115952908 A CN 115952908A
- Authority
- CN
- China
- Prior art keywords
- learning
- user
- knowledge point
- behavior data
- target user
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a learning path planning method, a system, equipment and a storage medium, wherein the method comprises the following steps: acquiring learning behavior data of a target user; determining a user characteristic image of the target user based on the clustering result of the learning behavior data; and performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar users are selected from the users with the same user characteristic portrait. According to the method, the sketch modeling is carried out according to the learning behavior data of the target user, and then the income calculation is carried out on the historical learning behavior data of the similar users corresponding to the user characteristic drawings, so that the target learning path with the maximum income is obtained, and the accuracy of learning path planning is effectively improved without combining the relevance between knowledge points.
Description
Technical Field
The present invention relates to the field of educational technology, and in particular, to a learning path planning method, system, device, and storage medium.
Background
With the wide application of the internet, the traditional education mode is gradually changed to the online education mode, and the online education mode is more important for planning the learning path by combining the learning conditions of the user due to the large number of learning people, so that the personal learning ability is improved.
The current learning path planning scheme mainly takes a knowledge map as a path planning basis, determines the mastery degree of each knowledge point of a student based on evaluation and diagnosis in the course learning process, and further obtains the learning path of the user by combining the preorders, successors and correlation among the knowledge points. However, in the case of discrete knowledge points and no boundary in the knowledge point range, the structuring degree of the knowledge graph corresponding to the knowledge points is more dispersed, and the accuracy of the recommended learning path is lower.
Disclosure of Invention
The invention provides a method, a system, equipment and a storage medium for planning a learning path, aiming at improving the accuracy of the planning of the learning path.
The invention provides a learning path planning method, which comprises the following steps:
acquiring learning behavior data of a target user;
determining a user characteristic image of the target user based on the clustering result of the learning behavior data;
and performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar users are selected from the users with the same user characteristic portrait.
According to the learning path planning method provided by the invention, the step of determining the user characteristic image of the target user based on the clustering result of the learning behavior data comprises the following steps:
extracting multidimensional learning characteristic data from the learning behavior data;
performing clustering analysis on the multi-dimensional learning characteristic data to obtain a clustering result;
and generating the user characteristic picture of the target user based on the clustering result.
According to the learning path planning method provided by the invention, the step of calculating the income of the historical learning behavior data of each similar user to obtain the target learning path of the target user comprises the following steps:
counting an exercise topic set of the target user based on the learning behavior data, and counting a historical topic set of each similar user based on historical learning behavior data of each similar user;
determining a plurality of candidate knowledge point sets based on the exercise topic set of the target user and the historical topic sets of the similar users;
determining learning income scores corresponding to the candidate knowledge point sets, and determining an optimal knowledge point set according to the learning income scores;
and forming a target learning path of the target user based on the optimal knowledge point set.
According to the learning path planning method provided by the invention, the target learning path of the target user is formed based on the optimal knowledge point set, and the method comprises the following steps:
determining the current mastering level of the target user corresponding to each knowledge point in the optimal knowledge point set respectively based on the learning behavior data of the target user;
determining the average mastery level corresponding to each knowledge point in the optimal knowledge point set respectively based on the historical learning behavior data corresponding to each similar user;
determining the discrete degree of each knowledge point based on the current mastery level and the average mastery level respectively corresponding to each knowledge point;
and forming the target learning path based on the discrete degree of each knowledge point.
According to the learning path planning method provided by the invention, the determining of a plurality of candidate knowledge point sets based on the exercise topic sets of the target users and the historical topic sets of the similar users comprises the following steps:
determining a plurality of topic sets to be promoted according to the exercise topic sets and the historical topic sets of the similar users;
and respectively carrying out knowledge point integration processing on each topic set to be promoted to obtain each candidate knowledge point set.
According to the learning path planning method provided by the present invention, after determining the user feature representation of the target user based on the clustering result of the learning behavior data, the method further comprises:
selecting a plurality of test questions from a preset exercise question set based on the diagnosis question proportion corresponding to the user characteristic picture;
and adjusting the user characteristic picture of the target user based on the evaluation result corresponding to each test question.
According to the learning path planning method provided by the invention, the similar users are selected and obtained on the basis of the following steps:
based on the learning behavior data and historical learning behavior data corresponding to each user, determining interest similarity between each user and the target user;
and sequencing the interest similarities to obtain the similar users according to a sequencing result.
The invention also provides a learning path planning system, comprising:
the acquisition module is used for acquiring learning behavior data of a target user;
the determining module is used for determining the user characteristic image of the target user based on the clustering result of the learning behavior data;
and the calculation module is used for performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar user is selected from each user with the same user characteristic portrait.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the learning path planning method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a learned path planning method as set forth in any one of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements a method of learning path planning as described in any one of the above.
According to the learning path planning method, the system, the equipment and the storage medium, the portrait modeling is carried out according to the learning behavior data of the target user, then the income calculation is carried out on the historical learning behavior data of the similar user corresponding to the user characteristic image, the target learning path with the maximum income is obtained, the association among knowledge points is not needed to be combined, and the accuracy of learning path planning is effectively improved.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of a learning path planning method provided by the present invention;
FIG. 2 is a schematic diagram of learning behavior data provided by an embodiment of the invention;
FIG. 3 is a second schematic flowchart of the learning path planning method provided by the present invention;
FIG. 4 is a third schematic flowchart of a learning path planning method according to the present invention;
FIG. 5 is a flow diagram of knowledge point recommendation provided by an embodiment of the invention;
FIG. 6 is a schematic structural diagram of a learned path planning system provided by the present invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
The terminology used in the one or more embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the invention. As used in one or more embodiments of the present invention, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present invention refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used herein to describe various information in one or more embodiments of the present invention, such information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present invention. Depending on the context, the word "if" as used herein may be interpreted as "at" \8230; … "when" or "when 8230; \8230"; "when".
Fig. 1 is a schematic flow chart of a learning path planning method provided by the present invention. As shown in fig. 1, the learned path planning method includes:
it should be noted that fig. 2 is a schematic diagram of learning behavior data provided in an embodiment of the present invention, as shown in fig. 2, the learning behavior data includes basic attribute information such as name, age, and specialty, optionally, when a user registers and logs in a system, the basic attribute information of the user needs to be filled, in addition, the learning behavior data further includes learning behavior attribute information such as system access time, system access frequency, video click viewing record, courseware click viewing record, attendance, student achievement, and job submission condition, and optionally, an exercise topic set that a target user has practiced can be obtained through statistics according to the information such as the student achievement and the job submission condition. The learning behavior data may also include information such as background knowledge mastery and user personality. The background knowledge mastering condition and the user character can be obtained by filling out a related questionnaire according to a target user.
it should be noted that, the basic attribute information such as age and specialty can directly obtain the labels corresponding to the basic attribute information, for example, the age label includes 90 th, 95 th, 00 th, etc., the specialty label includes computer, automation, electromechanical, foreign language, etc., and each label can be directly obtained by dividing according to the basic attribute information such as age and specialty of the target user, so that there is no need to perform cluster analysis on the basic attribute information.
Specifically, in this embodiment, multidimensional learning characteristic data is extracted from the learning behavior data, where the multidimensional learning characteristic data represents characteristic data capable of reflecting the learning ability of the target user, for example, learning behavior attribute information such as system access time, system access frequency, video click viewing record, courseware click viewing record, attendance, student achievement, and job submission condition is extracted. Further, the multi-dimensional learning feature data is subjected to clustering analysis to obtain a clustering result, the clustering result includes multi-dimensional learning feature labels, and then the user feature image of the target user is determined according to the multi-dimensional learning feature labels, for example, the multi-dimensional learning feature labels include but are not limited to a learning attitude label and a learning ability label, and when the learning attitude label is positive and the learning ability label is excellent, the user feature image of the target user can be determined to be an excellent learning feature image.
And step 13, performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar users are selected from the users with the same user characteristic portrait.
Specifically, a plurality of users are randomly selected as the similar users based on the users with the same user feature representation, and the similarity between each user and the target user can be calculated by combining the historical learning behavior data of each user and the learning behavior data of the target user, so that the similar users are selected and obtained based on the similarity. Further, according to the exercise topic set of the target user and the historical topic sets of the similar users, a plurality of candidate knowledge point sets are obtained through calculation, and then an optimal knowledge point set is selected from the candidate knowledge point sets, wherein in one embodiment, the specific selection process comprises the following steps: and respectively carrying out profit calculation on each candidate knowledge point set, thereby combining the candidate knowledge point sets with the maximum learning profit into an optimal knowledge point set. In another embodiment, the achievement of each knowledge point corresponding to the topic can be determined based on the learning behavior data of the target user, so that a plurality of knowledge points with lower achievements form the optimal knowledge point set.
Further, based on each knowledge point in the optimal knowledge point set, a target learning path corresponding to the target user is formed, and in order to improve accuracy of learning path planning, more specifically, the grasp levels of the target user and each similar user corresponding to each knowledge point in the optimal knowledge point set are respectively counted, and then the average grasp level corresponding to each knowledge point is determined according to the grasp level of each similar user corresponding to each knowledge point in the optimal knowledge point set, so that the deviation degree of each knowledge point is calculated according to the average grasp level corresponding to each knowledge point and the grasp level of the target user corresponding to each knowledge point in the optimal knowledge point set, and further, the target learning path of the target user is formed according to the deviation degree of each knowledge point.
According to the embodiment of the invention, the portraits are modeled according to the learning behavior data of the target user, and then the income calculation is carried out on the historical learning behavior data of the similar users corresponding to the user characteristic portraits, so that the target learning path with the maximum income is obtained, and the accuracy of learning path planning is effectively improved without combining the relevance between knowledge points.
Fig. 3 is a second schematic flow chart of the learned route planning method provided by the present invention, as shown in fig. 3, in an embodiment of the present invention, the step 12: determining the user characteristic image of the target user based on the clustering result of the learning behavior data, wherein the determining comprises the following steps:
it should be noted that the multidimensional learning characteristic data includes multidimensional characteristic data such as system access frequency, access time, video click viewing record, courseware resource viewing record, job submission condition, achievement, knowledge point mastering level, posting number, learning character and the like.
it should be noted that the clustering analysis includes a K-mean clustering algorithm, a Mini-Batch K-Means clustering algorithm, and the like, and in addition, the clustering result includes a multidimensional learning feature label, specifically, each feature data in the multidimensional learning feature data is clustered to obtain a multidimensional user label, and understandably, based on the system access frequency and access time, a learning behavior label of the target user can be obtained, optionally, the learning behavior label includes enthusiasm, laziness, medievality, and the like, and based on the job submission condition, achievement, and knowledge point mastering level, a learning attitude label of the target user can be obtained, optionally, the learning attitude label includes a positive initiative label and a semi-abandonment label, and according to the knowledge point mastering level, a learning intention label can be obtained. In addition, according to basic attributes such as age, sex, education level, etc., basic image tags of the target users can be obtained.
And 123, generating a user characteristic image of the target user based on the clustering result.
Specifically, according to the multi-dimensional learning feature labels in the aggregation result, the user feature image of the target user is determined. The more the dimensions of the label are, the more detailed and comprehensive the learning portrait of the target user is depicted.
It should be noted that the user feature image may include learning general; the learning is excellent, and can also comprise the current learning generality, and the future learning remains the generality; the current learning is excellent, and the future learning is kept excellent; the current study is general, and the future study is excellent; the current learning is difficult, and the future learning is general; the current learning is general, and the future learning is unknown; the current learning is difficult, and the future learning is excellent; the current learning is excellent, and the future learning is general; learning is currently difficult and unknown in the future.
According to the embodiment of the invention, the clustering of the multi-dimensional learning feature data is realized through the scheme, so that the user feature image of the target user can be comprehensively and accurately depicted according to the clustered multi-dimensional user label.
In an embodiment of the present invention, after determining the user feature representation of the target user based on the clustering result of the learning behavior data, the method further includes:
selecting a plurality of test questions from a preset exercise question set based on the diagnosis question proportion corresponding to the user characteristic picture; and adjusting the user characteristic picture of the target user based on the evaluation result corresponding to each test question.
It should be noted that different types of portraits may recommend learning assessment exercises in different proportions. Specifically, the learning user category to which the user feature image belongs is determined, and understandably, the current learning is general, the future learning is general, the current learning is general, the future learning is excellent, the current learning is difficult, the future learning is general, and the current learning is general, and the user feature image unknown to correspond to the future learning is divided into potential groups; dividing user characteristic images corresponding to the current excellent learning, the future excellent learning, the current learning difficulty and the future excellent learning into a strength group; the current learning is excellent, and the future learning is general; the current learning is difficult, and the unknown corresponding user characteristic image is divided into students.
Further, in order to improve the accuracy of the user feature image depicting the target user, in this embodiment, the user feature image can be adjusted, specifically, a test question is selected from the preset exercise question set according to a diagnosis question ratio corresponding to a learning user category, optionally, the diagnosis question ratio includes a ratio among simple questions, conventional questions and expansion questions, the conventional questions in the potential group have a large proportion, the expansion questions in the strength group have a large proportion, and the simple questions in the student study are large proportion. It should be noted that the diagnosis question ratio is not fixed, and the diagnosis question ratio is dynamically adjusted according to the evaluation result of the target user on the test question, for example, when the accuracy of the evaluation result of the simple question of the target user is higher, the ratio of the simple question is reduced, and the ratio of conventional extraction and expansion extraction is improved. In addition, in the process of selecting the test questions from the preset exercise question set, the profit score of the test question response to the target user is determined according to a profit model, wherein the profit model is as follows:
R Y (x|θ,l)＝f(x|θ,l)R Y (x|θ,l)+(1-f(x|θ,l))R Y (θ,[l,(x,0)])-R Y (θ,l)
the method comprises the steps of obtaining a user characteristic image, wherein Y represents profit scores, theta represents a user characteristic image, l represents a diagnosis question proportion, x represents a test question, and the next test question is selected from a preset exercise question set to enable the profit scores to be maximized, so that the user characteristic image of a target user can be adjusted based on an evaluation result corresponding to each test question. And the accuracy of the evaluation result of the target user on the expansion questions is higher, the user feature portrait of the target user is adjusted to be general in current learning and excellent in future learning.
Additionally, if the target user does not have learning behavior data, the user characteristic image of the target user cannot be obtained through depicting, a plurality of test questions can be selected from a preset exercise question set according to a preset default question proportion, wherein the process of selecting the test questions is basically the same as the process of selecting the next test question from the preset exercise question set to maximize the profit score Y, and then the user characteristic image corresponding to the target user is determined based on the evaluation result corresponding to each test question. Therefore, the user characteristic image corresponding to the target user can be portrayed without a large amount of answering data and long-time learning data.
According to the embodiment of the invention, the test questions are selected in the preset exercise question set according to the diagnosis question proportion corresponding to the user characteristic pictures, and then the user characteristic pictures of the target users are adjusted according to the evaluation results, so that the accuracy of the user characteristic pictures is effectively improved, and the self-adaptive planning of the learning path is realized by adjusting the user adjustment pictures.
In an embodiment of the present invention, the similar users are selected based on the following steps:
based on the learning behavior data and historical learning behavior data corresponding to each user, determining interest similarity between each user and the target user; and sequencing the interest similarities to obtain the similar users according to the sequencing result.
Specifically, firstly, each user identical to the user feature image is obtained through inquiry based on the user feature image of the target user, and further, the following steps are executed for historical learning behavior data corresponding to any user: calculating interest similarity between the target user and the target user according to the historical learning behavior data of the user and the learning behavior data of the target user, and optionally calculating intersection and union between the exercise topic set of the target user and the historical topic set of the similar user, so as to calculate the interest similarity, wherein an interest similarity calculation formula is as follows:
further, all the interest similarities are ranked to obtain a ranking result, optionally, according to the ranking result, the user with the highest interest similarity is selected as the similar user, and preferably, in order to improve the accuracy of subsequent learning path planning, a preset number of users with higher interest similarity are selected as the similar users, wherein the preset number may be set according to an actual situation, and is not specifically limited herein.
According to the embodiment of the invention, similar users are obtained by determining the interest similarity between the target user and each user, so that income calculation can be carried out according to the historical learning behavior data of the similar users, and the optimal target learning path is obtained.
Fig. 4 is a third schematic flow chart of the learning path planning method provided by the present invention, as shown in fig. 4, in an embodiment of the present invention, the step 13: performing income calculation on the historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the income calculation comprises the following steps:
specifically, the exercise topic sets of the target users are obtained through statistics according to information such as courseware clicking and watching records, student scores and homework submitting conditions in the learning behavior data, historical topic sets corresponding to the similar users are obtained through statistics based on the historical learning behavior data, and historical topic sets corresponding to the similar users are obtained through statistics.
specifically, the following steps are executed for any one of the historical topic sets of similar users:
and differentiating the historical topic set of the similar user with the exercise topic set of the target user to obtain a topic set which has not been exercised by the target user, and further integrating knowledge points of each topic in the topic set which has not been exercised to obtain a candidate knowledge point set which needs to be improved by the target user.
it should be noted that learning different knowledge points results and benefits to students are different. Specifically, the following steps are executed for any one candidate knowledge point set:
and determining the respective corresponding grasp levels of the target user on each knowledge point in the most candidate knowledge point set and determining the respective corresponding average grasp levels of each knowledge point in the candidate knowledge point set based on the learning behavior data of the target user, wherein the average grasp levels corresponding to the knowledge points are determined according to the grasp levels of the knowledge points of the similar users. In other embodiments, the average mastery level of a knowledge point may also be determined according to the mastery levels of all users in the system for the knowledge point. It can be understood that the mastering level of the target user for the knowledge point to which each topic belongs can be obtained through statistics based on behavior attribute information such as the achievement and the job submission condition in the learning behavior data of the target user.
Further, based on the average mastery level corresponding to each knowledge point in the candidate knowledge point set and the mastery level corresponding to each knowledge point by the target user, a learning profit score corresponding to the candidate knowledge point set is determined, and a learning profit algorithm is as follows:
wherein KAP represents a learning profit score, n represents the number of knowledge points, e ki Indicating the grasping level, e qi Indicating the average level of mastery. Furthermore, according to the learning income scores corresponding to the candidate knowledge point sets, the candidate knowledge point set with the largest learning income score is selected as the optimal knowledge point set.
And 134, forming a target learning path of the target user based on the optimal knowledge point set.
Specifically, based on the learning behavior data of the target user, the current mastery level of the target user corresponding to each knowledge point in the optimal knowledge point set is counted; and based on historical learning behavior data corresponding to each similar user, counting the average mastery level corresponding to each knowledge point in the optimal knowledge point set, and further calculating the dispersion degree corresponding to any knowledge point in the optimal knowledge point set according to the current mastery level and the average mastery level corresponding to any knowledge point in the optimal knowledge point set, so as to form the target learning path according to the dispersion degree corresponding to each knowledge point. In other embodiments, the target learning path may also be formed according to a difference between a current grasp level and an average grasp level corresponding to any knowledge point in the optimal knowledge point set, and thus according to a difference corresponding to each knowledge point.
According to the embodiment of the invention, the optimal knowledge point set with the maximum learning benefit is obtained by performing benefit calculation on each candidate knowledge point set, so that a target learning path is formed based on the optimal knowledge point set, and the accuracy of learning path planning is improved.
In an embodiment of the present invention, the forming a target learning path of the target user based on the optimal knowledge point set includes:
determining the current mastering level of the target user corresponding to each knowledge point in the optimal knowledge point set respectively based on the learning behavior data of the target user; determining the average mastery level corresponding to each knowledge point in the optimal knowledge point set respectively based on the historical learning behavior data corresponding to each similar user; determining the discrete degree of each knowledge point based on the current mastery level and the average mastery level respectively corresponding to each knowledge point; and forming the target learning path based on the discrete degree of each knowledge point.
Specifically, fig. 5 is a schematic flow chart of knowledge point recommendation provided in an embodiment of the present invention, and as shown in fig. 5, based on behavior attribute information such as scores in learning behavior data and job submission conditions of the target user, current mastery levels corresponding to the respective knowledge points in the optimal knowledge point set by the target user may be counted, for example, when practice scores corresponding to all topics of a certain knowledge point by the target user are higher, an average value of practice scores corresponding to all topics of the knowledge point may be used as the current mastery level of the knowledge point, and a plurality of score thresholds may be preset, where each score threshold corresponds to one mastery level, and the average value of practice scores corresponding to all topics of the knowledge point is compared with the plurality of score thresholds, so that a mastery level corresponding to a score threshold is used as the current mastery level of a knowledge point.
Further, the following steps are performed for any one of the similar users: based on the behavior attribute information such as the score and the job submission condition in the historical learning behavior data of the similar user, the mastering level of the similar user corresponding to each knowledge point in the optimal knowledge point set can be counted. Further, for any knowledge point in the optimal knowledge point set: and calculating to obtain the average mastery level of the knowledge point according to the mastery levels of the similar users to the knowledge point, and further calculating to obtain the discrete degree of the knowledge point based on the current mastery level and the average mastery level respectively corresponding to the knowledge point.
Further, the discrete degrees of the knowledge points are sorted to obtain a sorting result, so that the knowledge points are classified into "priority", late learning "and" advanced learning "according to the sorting result, thereby forming recommended knowledge points and further obtaining the target learning path.
According to the embodiment of the invention, the discrete degree calculation is carried out according to the mastery degree of the target user on each knowledge point and the average mastery degree of each knowledge point so as to determine the knowledge points required to be learned and recommended by the target user, obtain the target learning path and improve the accuracy of learning path planning.
In an embodiment of the present invention, the determining a plurality of sets of candidate knowledge points based on the exercise topic set of the target user and the historical topic sets of the similar users includes:
determining a plurality of topic sets to be promoted according to the exercise topic sets and the historical topic sets of the similar users; and respectively carrying out knowledge point integration processing on each topic set to be promoted to obtain each candidate knowledge point set.
Specifically, the following steps are executed for any one of the historical topic sets of similar users:
according to the history topic set of the similar user and the exercise topic set of the target user, the topics which are not already exercised by the target user relative to the history topic set of the similar user can be determined, that is, the history topic set selects each topic which does not have intersection with the exercise topic set of the target user, and then the ability of the similar user after completing which topic exercises is improved is judged, so that a to-be-improved topic set corresponding to the target user is obtained, and the to-be-improved topic set calculation formula is as follows: and O = V-U, wherein O represents a topic set to be promoted, V represents a historical topic set, U represents an exercise topic set, it needs to be explained that each exercise topic has a knowledge point to which the exercise topic belongs, and knowledge point integration is performed on each topic in the topic set to be promoted to obtain a candidate knowledge point set which needs to be promoted by a target user.
According to the method and the device, the problem set needing to be improved by the target user is determined according to the historical problem set of the similar user and the exercise problem set of the target user, and then the candidate knowledge point set is determined based on the candidate knowledge point set, so that the learning path corresponding to the optimal knowledge point is accurately calculated according to each knowledge point in the candidate knowledge point set.
The following describes the learned route planning system provided by the present invention, and the learned route planning system described below and the learned route planning method described above may be referred to correspondingly.
Fig. 6 is a schematic structural diagram of a learned route planning system provided by the present invention, and as shown in fig. 6, a learned route planning system according to an embodiment of the present invention includes:
the acquisition module 61 is configured to acquire learning behavior data of a target user;
a determining module 62, configured to determine a user feature image of the target user based on the clustering result of the learning behavior data;
and the calculating module 63 is configured to perform revenue calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, where the similar user is selected from users with the same user feature representation.
The determination module 62 is further configured to:
extracting multidimensional learning characteristic data from the learning behavior data;
performing clustering analysis on the multi-dimensional learning characteristic data to obtain a clustering result;
and generating the user characteristic picture of the target user based on the clustering result.
The calculation module 63 is further configured to:
counting an exercise topic set of the target user based on the learning behavior data, and counting a historical topic set of each similar user based on historical learning behavior data of each similar user;
determining a plurality of candidate knowledge point sets based on the exercise topic set of the target user and the historical topic sets of the similar users;
determining learning income scores corresponding to the candidate knowledge point sets, and determining an optimal knowledge point set according to the learning income scores;
and forming a target learning path of the target user based on the optimal knowledge point set.
The calculation module 63 is further configured to:
determining the current mastering level of the target user corresponding to each knowledge point in the optimal knowledge point set respectively based on the learning behavior data of the target user;
determining the average mastering level corresponding to each knowledge point in the optimal knowledge point set based on the historical learning behavior data corresponding to each similar user;
determining the discrete degree of each knowledge point based on the current mastery level and the average mastery level respectively corresponding to each knowledge point;
and forming the target learning path based on the discrete degree of each knowledge point.
The calculation module 63 is further configured to:
determining a plurality of topic sets to be promoted according to the exercise topic sets and the historical topic sets of the similar users;
and respectively carrying out knowledge point integration processing on each topic set to be promoted to obtain each candidate knowledge point set.
The learned path planning system further includes:
selecting a plurality of test questions from a preset exercise question set based on the diagnosis question proportion corresponding to the user characteristic picture;
and adjusting the user characteristic picture of the target user based on the evaluation result corresponding to each test question.
The learned path planning system further includes:
based on the learning behavior data and historical learning behavior data corresponding to each user, determining interest similarity between each user and the target user;
and sequencing the interest similarities to obtain the similar users according to the sequencing result.
It should be noted that, the system provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment, and can achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those of the method embodiment in this embodiment are not repeated herein.
Fig. 7 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 7, the electronic device may include: a processor (processor) 710, a memory (memory) 720, a communication Interface (Communications Interface) 730, and a communication bus 740, wherein the processor 710, the memory 720, and the communication Interface 730 communicate with each other via the communication bus 740. Processor 710 may invoke logic instructions in memory 720 to perform a learned path planning method comprising: acquiring learning behavior data of a target user; determining a user characteristic image of the target user based on the clustering result of the learning behavior data; and performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar user is selected from each user with the same user characteristic portrait.
Furthermore, the logic instructions in the memory 720 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the learned path planning method provided by the above methods, the method including: acquiring learning behavior data of a target user; determining a user characteristic image of the target user based on the clustering result of the learning behavior data; and performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar users are selected from the users with the same user characteristic portrait.
In another aspect, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is capable of executing the learned path planning method provided by the above methods, and the method includes: acquiring learning behavior data of a target user; determining a user characteristic image of the target user based on the clustering result of the learning behavior data; and performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar user is selected from each user with the same user characteristic portrait.
The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for learning path planning, comprising:
acquiring learning behavior data of a target user;
determining a user characteristic image of the target user based on the clustering result of the learning behavior data;
and performing income calculation on historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar users are selected from the users with the same user characteristic portrait.
2. The method for planning learned paths according to claim 1, wherein the determining the user feature portrayal of the target user based on the clustering result of the learned behavior data includes:
extracting multidimensional learning characteristic data from the learning behavior data;
performing clustering analysis on the multi-dimensional learning characteristic data to obtain a clustering result;
and generating the user characteristic picture of the target user based on the clustering result.
3. The method for planning a learned path according to claim 1, wherein the performing benefit calculation on the historical learned behavior data of each similar user to obtain the target learned path of the target user includes:
counting an exercise topic set of the target user based on the learning behavior data, and counting a historical topic set of each similar user based on historical learning behavior data of each similar user;
determining a plurality of candidate knowledge point sets based on the exercise topic set of the target user and the historical topic sets of the similar users;
determining learning income scores corresponding to the candidate knowledge point sets, and determining an optimal knowledge point set according to the learning income scores;
and forming a target learning path of the target user based on the optimal knowledge point set.
4. The method for planning learned route according to claim 3, wherein the forming the target learned route of the target user based on the optimal knowledge point set comprises:
determining the current mastering level of the target user corresponding to each knowledge point in the optimal knowledge point set respectively based on the learning behavior data of the target user;
determining the average mastering level corresponding to each knowledge point in the optimal knowledge point set based on the historical learning behavior data corresponding to each similar user;
determining the discrete degree of each knowledge point based on the current mastery level and the average mastery level respectively corresponding to each knowledge point;
and forming the target learning path based on the discrete degree of each knowledge point.
5. The method for learning path planning according to claim 3, wherein the determining a plurality of sets of candidate knowledge points based on the training topic set of the target user and the historical topic sets of the similar users comprises:
determining a plurality of topic sets to be promoted according to the exercise topic sets and the historical topic sets of the similar users;
and respectively carrying out knowledge point integration processing on each topic set to be promoted to obtain each candidate knowledge point set.
6. The method for planning learned paths according to claim 1, wherein after determining the user feature representation of the target user based on the clustering result of the learned behavior data, the method further comprises:
selecting a plurality of test questions from a preset exercise question set based on the diagnosis question proportion corresponding to the user characteristic picture;
and adjusting the user characteristic picture of the target user based on the evaluation result corresponding to each test question.
7. The method for learning path planning according to claim 1, wherein the similar users are selected based on the following steps:
based on the learning behavior data and historical learning behavior data corresponding to each user, determining interest similarity between each user and the target user;
and sequencing the interest similarities to obtain the similar users according to the sequencing result.
8. A learned path planning system, comprising:
the acquisition module is used for acquiring learning behavior data of a target user;
the determining module is used for determining the user characteristic image of the target user based on the clustering result of the learning behavior data;
and the calculation module is used for performing income calculation on the historical learning behavior data of each similar user to obtain a target learning path of the target user, wherein the similar user is selected from the users with the same user characteristic portrait.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements the learned path planning method of any of claims 1-7 when executing the program.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor implements the learned path planning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211738319.5A CN115952908A (en) | 2022-12-30 | 2022-12-30 | Learning path planning method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211738319.5A CN115952908A (en) | 2022-12-30 | 2022-12-30 | Learning path planning method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115952908A true CN115952908A (en) | 2023-04-11 |
Family
ID=87285741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211738319.5A Pending CN115952908A (en) | 2022-12-30 | 2022-12-30 | Learning path planning method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115952908A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117474730A (en) * | 2023-11-22 | 2024-01-30 | 紫光摩度教育科技有限公司 | Learning path planning method, processor, device and storage medium |
-
2022
- 2022-12-30 CN CN202211738319.5A patent/CN115952908A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117474730A (en) * | 2023-11-22 | 2024-01-30 | 紫光摩度教育科技有限公司 | Learning path planning method, processor, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102106462B1 (en) | Method for filtering similar problem based on weight | |
| CN109740048B (en) | Course recommendation method and device | |
| Priest | Information equity, public understanding of science, and the biotechnology debate | |
| CN112214670B (en) | Online course recommendation method and device, electronic equipment and storage medium | |
| CN110659311B (en) | Topic pushing method and device, electronic equipment and storage medium | |
| CN110321421B (en) | Expert recommendation method for website knowledge community system and computer storage medium | |
| WO2022170985A1 (en) | Exercise selection method and apparatus, and computer device and storage medium | |
| CN111651676A (en) | Method, device, equipment and medium for performing occupation recommendation based on capability model | |
| JP3883795B2 (en) | Attendance class selection device, attendance class selection method, and storage medium | |
| CN111832952B (en) | Education courseware pushing system | |
| CN115146161A (en) | Personalized learning resource recommendation method and system based on content recommendation | |
| CN112733035A (en) | Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device | |
| Li et al. | MOOC-FRS: A new fusion recommender system for MOOCs | |
| CN111639485A (en) | Course recommendation method based on text similarity and related equipment | |
| Recker et al. | Analyzing learner and instructor interactions within learning management systems: Approaches and examples | |
| CN114416929A (en) | Sample generation method, device, equipment and storage medium of entity recall model | |
| Hidayat et al. | Determine Felder Silverman learning style model using literature based and K-means clustering | |
| CN111311997B (en) | Interaction method based on network education resources | |
| CN109800880B (en) | Self-adaptive learning feature extraction system based on dynamic learning style information and application | |
| JP7293658B2 (en) | Information processing device, information processing method and program | |
| CN111415283A (en) | Factor analysis method and device for effective online teaching | |
| CN115952908A (en) | Learning path planning method, system, device and storage medium | |
| CN115934899A (en) | IT industry resume recommendation method and device, electronic equipment and storage medium | |
| CN116228361A (en) | Course recommendation method, device, equipment and storage medium based on feature matching | |
| CN111831886B (en) | Network courseware pushing method based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |