Interactive content generation method and system for AR intelligent teaching

Abstract

The invention provides an interactive content generation method and system for AR intelligent teaching, and relates to the technical field of AR intelligent teaching. The method comprises the following steps: acquiring AR intelligent teaching content data, and establishing an AR intelligent teaching content database; performing clustering relation analysis based on knowledge points on the teaching content in the AR intelligent teaching content database to form a teaching content cluster; historical teaching result data of the teaching content clusters are collected, hierarchical mapping analysis based on teaching results is carried out, and interactive content hierarchical mapping data are formed; and obtaining real-time teaching result information, and performing interaction content generation guide processing according to the interaction content hierarchical mapping data to form real-time interaction teaching content. According to the method, interactive real-time generation of the AR intelligent teaching content is realized based on the historical teaching data, the personalized function of AR intelligent teaching is further improved, the teaching quality and the teaching effect are greatly improved, the requirements of different teaching objects are met, and higher adaptability is achieved.

Description

Technical Field

[0001] The present invention relates to the field of AR intelligent teaching technology, and in particular to a method and system for generating interactive content for AR intelligent teaching. Background Art

[0002] With the advancement of society and science, the emergence and application of new technologies such as intelligent technology and virtual reality in various industries have effectively promoted production efficiency. In the field of education, the application of AR intelligent teaching can provide students with an immersive experience, allowing them to absorb and understand the knowledge in a more intuitive and efficient way, further improving the quality and effectiveness of teaching.

[0003] Currently, AR intelligent teaching still relies on pre-existing teaching databases to arrange step-by-step teaching courses according to a set teaching sequence. Although this improves understanding and absorption of knowledge points, the uneven foundational knowledge of different teaching objects makes it impossible to fully adapt to all teaching objects. If teaching content can be personalized and interactive, it will definitely be able to more effectively improve the learning effect and efficiency of teaching objects.

[0004] Therefore, designing an interactive content generation method and system for AR intelligent teaching, which realizes interactive real-time generation of AR intelligent teaching content based on historical teaching data, further enhances the personalized function of AR intelligent teaching, greatly improves the teaching quality and teaching effect, and meets the needs of different teaching objects with stronger adaptability, is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide an interactive content generation method for AR intelligent teaching. By establishing a database of AR intelligent teaching content, different teaching contents are clustered based on the connection relationship between knowledge points to form a teaching content cluster that can guide the teaching sequence. On this basis, the adaptability of the teaching content of different knowledge points is analyzed in combination with the scores of the teaching objects in the history teaching process, that is, the teaching relationship of the teaching content of adjacent knowledge points in the teaching effect with the scores as a reference is determined, thereby providing a reasonable and accurate data reference for real-time teaching to select teaching content that adapts to the teaching objects for interactive content generation, which greatly improves the personalization level of teaching content and improves the overall teaching effect and teaching quality.

[0006] The purpose of the present invention is also to provide an interactive content generation system for AR intelligent teaching. The system forms a complete system for interactive content generation through a teaching data acquisition unit, a teaching database, a feature analysis unit and an interactive content generation unit. Different units have different functions and work closely together to complete different content processing tasks, effectively ensuring the rationality and accuracy of interactive content generation, and is an important material basis for realizing interactive content generation.

[0007] In a first aspect, the present invention provides an interactive content generation method for AR intelligent teaching, including: obtaining AR intelligent teaching content data and establishing an AR intelligent teaching content database; performing clustering connection analysis based on knowledge points on the teaching content in the AR intelligent teaching content database to form teaching content clusters; collecting historical teaching result data of the teaching content clusters, and performing hierarchical mapping analysis based on the teaching results to form interactive content hierarchical mapping data; obtaining real-time teaching result information, and performing interactive content generation guidance processing based on the interactive content hierarchical mapping data to form real-time interactive teaching content.

[0008] In the present invention, the method establishes a database of AR intelligent teaching content to cluster different teaching contents based on the connection relationship of knowledge points, forming a teaching content cluster that can guide the teaching sequence, and on this basis, combines the scores of different teaching contents by teaching objects in the history teaching process to conduct adaptability analysis of teaching contents of different knowledge points, that is, the teaching relationship of teaching contents of adjacent knowledge points in the teaching effect with scores as a reference, thereby providing a reasonable and accurate data reference for real-time teaching to select teaching content that adapts to teaching objects for interactive generation of content, greatly improving the personalization level of teaching content, and improving the overall teaching effect and teaching quality.

[0009] As a possible implementation method, a cluster connection analysis based on knowledge points is performed on the teaching contents in the AR intelligent teaching content database to form teaching content clusters, including: calibrating teaching knowledge points and related knowledge points for different teaching contents in the AR intelligent teaching content database; clustering different teaching contents in the AR intelligent teaching content database according to corresponding teaching knowledge points to form different knowledge point teaching content sets; and conducting connection analysis on all related knowledge points corresponding to all teaching contents in different knowledge point teaching content sets to establish teaching content clusters.

[0010] In the present invention, in order to interactively generate AR intelligent teaching content, it is first necessary to determine the reasonable order of the teaching content. After all, for a course or professional knowledge, the knowledge points it contains are systematic, and different knowledge points have mutual connections. In essence, only after completing the learning and absorption of the corresponding knowledge points can the next knowledge point that is associated with this knowledge point be effectively learned. This application calibrates the knowledge points involved in different teaching contents and then completes reasonable clustering based on knowledge points to form a teaching content cluster with a logical order of teaching. Here, because different teaching contents are targeted at knowledge points, teaching knowledge points and related knowledge points are distinguished. Related knowledge points are other knowledge points that must be involved when the teaching content mainly wants to teach the teaching knowledge points.

[0011] As a possible implementation method, a connection analysis is performed on all relevant knowledge points corresponding to all teaching contents in different knowledge point teaching content sets to establish a teaching content cluster, including: determining any knowledge point teaching content set as an analysis object set, and performing a connection analysis in the following manner: for the analysis object set, determining the knowledge point teaching content set whose teaching knowledge points of other knowledge point teaching content sets are relevant knowledge points of the analysis object set, and forming a connection direction from the teaching knowledge points to the relevant knowledge points on different knowledge point teaching content sets; for each knowledge point teaching content set determined to be associated with the analysis object set, continuing to perform a connection analysis on all relevant knowledge points, determining all corresponding associated knowledge point teaching content sets, until all knowledge point teaching content sets are linked together to form a teaching content cluster.

[0012] In the present invention, it is understandable that, for a course or professional knowledge, the amount of related knowledge points involved in the sequential teaching content formed is regular to a certain extent, especially when conducting initial teaching, a single teaching knowledge point will be used as the basic knowledge point of the corresponding course or professional knowledge. This type of knowledge point will basically not involve other related knowledge points, and thus can be judged by quantity. However, after distinguishing between teaching knowledge points and related knowledge points in the teaching content, the present application can determine the teaching order of the knowledge system for any teaching content, that is, based on the related knowledge points of the teaching content, other related knowledge points are traced as teaching knowledge points, and finally the connection of all teaching contents is formed into a teaching content cluster. Of course, since the related knowledge points are indispensable supplementary knowledge around the teaching knowledge points of the teaching content, it is necessary for the teaching object to master the related knowledge points before learning and absorbing the teaching knowledge points. Based on such a logical order, the teaching order relationship between different teaching contents in the teaching content cluster can be determined.

[0013] As a possible implementation method, historical teaching result data of the teaching content cluster is collected, and a hierarchical mapping analysis based on the teaching results is performed to form interactive content hierarchical mapping data, including: determining historical teaching score data of different teaching contents in different knowledge point teaching content sets based on the historical teaching result data; dividing the difficulty of different teaching contents in different knowledge point teaching content sets based on the historical teaching scores to form corresponding teaching content difficulty division data; performing qualified screening based on the historical teaching scores on the different teaching content difficulty division data to form corresponding historical teaching qualified score data; performing score mapping analysis based on the teaching object according to the historical teaching qualified score data corresponding to the different teaching content difficulty division data to form interactive content hierarchical mapping data.

[0014] In the present invention, for different teaching objects, the learning effect on different teaching knowledge points is different, and this difference in learning effect will affect the mastery of the teaching knowledge point currently being learned and the related knowledge point involved in the learning of other teaching knowledge points later will also affect the mastery of the corresponding teaching knowledge point, and the mastery of the knowledge point is usually intuitively reflected in the form of exercises or practice tests, and the mastery of the teaching content is also affected to a certain extent by the difficulty of the teaching content. Therefore, the score of the historical teaching object on the corresponding teaching content can be used as the basis for the difficulty division of the teaching content, especially in the total score under big data, which can better eliminate the influence of the score change caused by the individual learning situation on the inaccurate judgment of the teaching difficulty, making the division of the teaching content more accurate. Of course, there will also be a benchmark for judging whether the teaching object has passed the learning of teaching content of different difficulty levels. The hierarchical mapping of the teaching content is preferably carried out on the basis of the passing of the teaching effect. The data of unqualified learning results has no practical reference significance. After all, these data are largely related to the seriousness of individual learning or the sporadic nature of the test.

[0015] As a possible implementation method, different teaching contents in different knowledge point teaching content sets are divided into difficulty levels based on historical teaching scores to form corresponding teaching content difficulty division data, including: for different knowledge point teaching content sets, extracting the historical scores of all teaching objects corresponding to different teaching contents; normalizing the historical scores of all teaching objects to form historical normalized scores, and determining the historical total score of the teaching content; sorting different teaching contents in descending order according to the historical total score of the teaching content, to form teaching content difficulty division data corresponding to the knowledge point teaching content set.

[0016] In the present invention, when dividing the difficulty of the same teaching content, the big data of the learning scores of the history teaching objects is used for determination. It can be understood that different teaching contents may have different total score settings. Therefore, in order to ensure the uniformity and rationality of the analysis, it is necessary to normalize the scores, which can make the results of the difficulty division more accurate and reasonable.

[0017] As a possible implementation method, different teaching content difficulty classification data are screened based on the history teaching score to form corresponding history teaching qualified score data, including: setting corresponding teaching qualified scores for different teaching content difficulty classification data; for different teaching contents in the teaching content difficulty classification data, all historical normalized scores that reach the teaching qualified scores are determined as historical normalized qualified scores, and the teaching objects are calibrated; all historical normalized qualified scores under different teaching contents in the teaching content difficulty classification data are collected to form history teaching qualified score data.

[0018] In the present invention, different teaching objects need to screen data that do not achieve satisfactory learning results based on their individual circumstances, learning attitudes, and the sporadic nature of learning tests. It is understandable that the teaching passing score can be set based on the actual evaluation of the absorption effect of the teaching knowledge points, or a reasonable score value can be determined based on big data. After excluding the data that does not reach the passing score, the remaining data can be used as the basic data for subsequent interactive correlation analysis of the learning content of different teaching knowledge points, making the analysis more reasonable and accurate.

[0019] As a possible implementation method, based on the history teaching qualified score data corresponding to the data of different teaching content difficulty levels, a score mapping analysis based on the teaching object is performed to form interactive content hierarchical mapping data, including: for different history teaching qualified score data, the following score mapping analysis is performed with the teaching object as the analysis standard: according to the sequential relationship of the teaching content sets of different knowledge points in the teaching content cluster, for different teaching objects, the corresponding teaching content and historical normalized qualified score under any history teaching qualified score data are determined; for different teaching objects, the historical normalized qualified score of the same teaching object in the next history teaching qualified score data is determined according to the connection relationship of the teaching content cluster, and the historical normalization of the next history teaching qualified score data is continued. The qualified scores are obtained until no historical normalized qualified scores for the same teaching object are obtained. All historical normalized qualified scores of the teaching objects are calibrated with corresponding teaching contents and sequentially connected based on teaching content clusters to form an object score mapping relationship; for different teaching objects, the different historical normalized qualified scores of different objects with the same historical normalized qualified scores on the same teaching content in the previous historical teaching qualified score data are determined according to the connection relationship order of the teaching content clusters on any two adjacent knowledge point teaching content sets, and then the teaching content mapping score range of different teaching contents in the next knowledge point teaching content set corresponding to the determined scores on the teaching content of each previous knowledge point teaching content set is formed. m represents the number of different knowledge point teaching content sets, m+1 represents the next knowledge point teaching content set adjacent to the knowledge point teaching content set numbered m in the teaching content cluster, represents the passing score value corresponding to the teaching content numbered n in the knowledge point teaching content set numbered m, n represents the number of the different teaching contents corresponding to the knowledge point teaching content set numbered m, k represents the number of the different teaching contents in the next knowledge point teaching content set adjacent to the knowledge point teaching content set numbered m in the teaching content cluster, The passing score for the teaching content numbered n in the knowledge point teaching content numbered m is The qualified score value range formed by the teaching content numbered k in the adjacent next knowledge point teaching content set; the teaching content mapping score range corresponding to the different scores of different teaching contents in each knowledge point teaching content set is collected to form interactive content hierarchical mapping data.

[0020] In the present invention, the hierarchical mapping data to be obtained is mainly used to determine how to select the subsequent teaching content after the teaching subject determines the score obtained on the previous teaching content in the teaching sequence defined by the teaching content cluster. After all, different teaching subjects will affect the difficulty level of the next learning content based on their mastery of the previous teaching content and their own individual knowledge learning situation. By taking the teaching subject as the analysis reference target, the adjacent teaching content sets are determined to determine the possible score of a certain teaching content selected in the next teaching content set after the same subject determines the score on the previous teaching content. In this way, the difficulty of the next teaching content and the teaching content that can be passed can be interactively selected based on the current teaching subject's score on the teaching content, as well as the corresponding score prediction. Here, for different teaching subjects, since the learning ability of the teaching subject is unknown during the subsequent analysis, if different teaching subjects obtain the same score in the current teaching content set, the range of possible scores of the teaching content in the next teaching content set can be determined. In this way, the teaching scores obtained by teaching subjects with different learning abilities can be predicted, making the subsequent interactive generation of teaching content more flexible and with a wider range of choices.

[0021] As a possible implementation method, real-time teaching result information is obtained, and interactive content generation guidance processing is performed based on interactive content hierarchical mapping data to form real-time interactive teaching content, including: using the connection relationship of teaching content clusters as the generation guidance sequence of teaching content, starting from the first knowledge point teaching content set, any teaching content at the middle level is generated to form initial sequence teaching content; obtaining the real-time teaching normalized score of the initial sequence teaching content: if the real-time teaching normalized score corresponding to the initial sequence teaching content reaches the corresponding teaching qualified score, then the interactive content generation analysis of the next knowledge point teaching content set is performed; if the real-time teaching normalized score corresponding to the initial sequence teaching content does not reach the corresponding teaching qualified score, then the teaching content in the current knowledge point teaching content set that has a difficulty level adjacent to the initial sequence teaching content and has a lower difficulty level is used as the new sequence teaching content to continue the score qualification analysis until the formed real-time teaching normalized score reaches the corresponding teaching qualified score position, and then the interactive content generation analysis of the next knowledge point teaching content set is performed.

[0022] In the present invention, of course, when generating real-time interactive content, teaching is first conducted in the order of the teaching content clusters. The initial sequence teaching content is determined and scored. Based on the score of the initial sequence teaching content, the next teaching content is generated by analyzing the interaction. For the initial teaching content, since it starts with arbitrary teaching content of the middle level, the intermediate arbitrary teaching is simply to select one of the two middle difficulty levels if the number of levels of the teaching content is even, and to select the middle teaching content as the initial sequence teaching content if the number of levels is odd. If the score reaches the teaching passing score, it can be considered that the teaching subject has completed learning of the teaching content and can proceed to learning the next teaching content in the teaching content cluster. If the teaching passing score is not reached, the teaching subject continues to learn in the teaching content cluster at a lower difficulty level until the result reaches the teaching passing score, and then selects the teaching content of the next teaching content cluster.

[0023] As a possible implementation method, an interactive content generation analysis of the next knowledge point teaching content set is performed, including: based on the interactive content hierarchical mapping data, the teaching content with the greatest difficulty in the adjacent next knowledge point teaching content set with a mapping relationship is used as the interactive generation content to perform a mapping score range analysis in the following manner: if the formed real-time teaching normalized score belongs to the mapping score range, then the interactive content generation analysis of the next knowledge point teaching content set is performed with reference to the real-time teaching normalized score; if the formed real-time teaching normalized score does not belong to the mapping score range, then the teaching content in the current knowledge point teaching content set with a difficulty level adjacent to the current learning content and with a lower difficulty level is used as the new sequential teaching content to continue the score qualification analysis, until the formed real-time teaching normalized score belongs to the corresponding mapping score range, and then the interactive content generation analysis of the next knowledge point teaching content set is performed with reference to the real-time teaching normalized score.

[0024] In the present invention, for the selection of teaching content in the next teaching content set, since the scores obtained in the initial sequence teaching content have a mapping relationship in the interactive content grading mapping data, the teaching content and the corresponding score range that are suitable for the different difficulty levels of the teaching objects in the next teaching content set can be determined. Usually, the teaching content with the greatest difficulty is selected as the first choice. If the score after learning is within the corresponding score range, it is considered that the learning state of the teaching object is in a reasonable state, and the learning of the teaching content is passed. The teaching content of the next teaching content set can be selected based on the score reference interactive content grading mapping data. If the score is not within the corresponding range, it is considered that the corresponding teaching effect has not been achieved or has exceeded the expected teaching effect. Here, it is usually considered that the expectation has not been achieved, so learning is carried out again by obtaining teaching content with lower difficulty until the score is within the corresponding range before selecting the teaching content of the next teaching content set.

[0025] In the second aspect, the present invention provides an interactive content generation system for AR intelligent teaching, including: a teaching data acquisition unit, used to obtain AR intelligent teaching content data and real-time teaching result information; a teaching database, used to store the AR intelligent teaching content data acquired by the teaching data acquisition unit; a feature analysis unit, used to perform clustering connection analysis on the AR intelligent teaching content data in the teaching database to form teaching content clusters, and perform hierarchical mapping analysis based on the teaching results to form interactive content hierarchical mapping data; an interactive content generation unit, used to obtain the real-time teaching result information acquired by the teaching data acquisition unit, and perform interactive content generation guidance processing according to the teaching content clusters and interactive content hierarchical mapping data formed by the feature analysis unit to form real-time interactive teaching content.

[0026] In the present invention, the system forms a complete system for interactive content generation through a teaching data acquisition unit, a teaching database, a feature analysis unit, and an interactive content generation unit. Different units have different functions and work closely together to complete different content processing tasks, effectively ensuring the rationality and accuracy of interactive content generation, and is an important material basis for realizing interactive content generation.

[0027] The interactive content generation method and system for AR intelligent teaching provided by the present invention have the following beneficial effects:

[0028] This method establishes a database of AR intelligent teaching content and clusters different teaching contents based on the connection relationship of knowledge points to form teaching content clusters that can guide the teaching sequence. On this basis, the adaptability of teaching content of different knowledge points is analyzed in combination with the scores of different teaching contents by teaching objects in the history teaching process, that is, the teaching relationship of teaching content of adjacent knowledge points in the teaching effect with score as reference is determined, which provides reasonable and accurate data reference for real-time teaching to select teaching content that adapts to teaching objects for interactive generation of content, greatly improving the personalization level of teaching content and improving the overall teaching effect and teaching quality.

[0029] The system forms a complete interactive content generation system through the teaching data acquisition unit, teaching database, feature analysis unit and interactive content generation unit. Different units have different functions and work closely together to complete different content processing tasks, effectively ensuring the rationality and accuracy of interactive content generation, and is an important material basis for realizing interactive content generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 A diagram showing the steps of a method for generating interactive content for AR intelligent teaching according to an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of the structure of an interactive content generation system for AR intelligent teaching provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

[0034] With the advancement of society and science, the emergence and application of new technologies such as intelligent technology and virtual reality in various industries have effectively promoted production efficiency. In the field of education, the application of AR intelligent teaching can provide students with an immersive experience, allowing them to absorb and understand the knowledge in a more intuitive and efficient way, further improving the quality and effectiveness of teaching.

[0035] Currently, AR intelligent teaching still relies on pre-existing teaching databases to arrange step-by-step teaching courses according to a set teaching sequence. Although this improves understanding and absorption of knowledge points, the uneven foundational knowledge of different teaching objects makes it impossible to fully adapt to all teaching objects. If teaching content can be personalized and interactive, it will definitely be able to more effectively improve the learning effect and efficiency of teaching objects.

[0036] refer to Figure 1-Figure 2 An embodiment of the present invention provides an interactive content generation method for AR intelligent teaching. The method establishes a database of AR intelligent teaching content and clusters different teaching contents based on the connection relationship between knowledge points to form a teaching content cluster that can guide the teaching sequence. On this basis, the adaptability of the teaching content of different knowledge points is analyzed in combination with the scores of the teaching objects in the history teaching process, that is, the teaching relationship of the teaching content of adjacent knowledge points in the teaching effect with the scores as a reference is determined, thereby providing a reasonable and accurate data reference for real-time teaching to select teaching content that adapts to the teaching objects for interactive content generation, greatly improving the personalization level of teaching content and improving the overall teaching effect and teaching quality.

[0037] The interactive content generation method for AR intelligent teaching specifically includes the following steps:

[0038] S1: Acquire AR intelligent teaching content data and establish an AR intelligent teaching content database.

[0039] For AR intelligent teaching, there is already complete teaching content, so before producing and analyzing interactive content, it is necessary to collect content data to form a data foundation.

[0040] S2: Conduct clustering analysis of the teaching contents in the AR intelligent teaching content database based on knowledge points to form teaching content clusters.

[0041] The teaching contents in the AR intelligent teaching content database are clustered and connected based on knowledge points to form teaching content clusters, including: calibrating teaching knowledge points and related knowledge points for different teaching contents in the AR intelligent teaching content database; clustering different teaching contents in the AR intelligent teaching content database according to corresponding teaching knowledge points to form different knowledge point teaching content sets; and conducting connection analysis on all related knowledge points corresponding to all teaching contents in different knowledge point teaching content sets to establish teaching content clusters.

[0042] To interactively generate AR intelligent teaching content, it is first necessary to determine the reasonable order of the teaching content. After all, for a course or professional knowledge, the knowledge points it contains are systematic, and different knowledge points have mutual connections. In essence, only after completing the learning and absorption of the corresponding knowledge points can the next knowledge point that is associated with this knowledge point be effectively learned. This application calibrates the knowledge points involved in different teaching contents and then completes reasonable clustering based on knowledge points to form a teaching content cluster with a logical order of teaching. Here, because different teaching contents are targeted at knowledge points, teaching knowledge points and related knowledge points are distinguished. Related knowledge points are other knowledge points that must be involved when the teaching content mainly wants to teach the teaching knowledge points.

[0043] Conduct connection analysis on all relevant knowledge points corresponding to all teaching contents in different knowledge point teaching content sets to establish teaching content clusters, including: determining any knowledge point teaching content set as an analysis object set, and conducting connection analysis in the following manner: for the analysis object set, determine the knowledge point teaching content set whose teaching knowledge points of other knowledge point teaching content sets are relevant knowledge points of the analysis object set, and form connection directions from teaching knowledge points to relevant knowledge points on different knowledge point teaching content sets; for each knowledge point teaching content set determined to be associated with the analysis object set, continue to conduct connection analysis on all relevant knowledge points, determine all corresponding associated knowledge point teaching content sets, until all knowledge point teaching content sets are linked together to form a teaching content cluster.

[0044] It is understandable that, for a course or professional knowledge, the amount of related knowledge points involved in the sequential teaching content formed is regular to a certain extent, especially when conducting initial teaching, a single teaching knowledge point will be used as the basic knowledge point of the corresponding course or professional knowledge at the beginning. This type of knowledge point will basically not involve other related knowledge points, and thus can be judged by quantity. However, after distinguishing between teaching knowledge points and related knowledge points in the teaching content, the present application can determine the teaching order of the knowledge system for any teaching content, that is, according to the related knowledge points of the teaching content, other related knowledge points are traced as teaching knowledge points, and finally the connection of all teaching contents is formed into a teaching content cluster. Of course, since the related knowledge points are indispensable supplementary knowledge around the teaching knowledge points of the teaching content, it is necessary for the teaching object to first master the related knowledge points before learning and absorbing the teaching knowledge points. Based on such a logical order, the teaching order relationship between different teaching contents in the teaching content cluster can be determined.

[0045] S3: Collect historical teaching result data of the teaching content cluster, and conduct hierarchical mapping analysis based on the teaching results to form interactive content hierarchical mapping data.

[0046] Collect historical teaching result data of the teaching content cluster, and conduct hierarchical mapping analysis based on the teaching results to form interactive content hierarchical mapping data, including: determining historical teaching score data of different teaching contents in different knowledge point teaching content sets based on the historical teaching result data; dividing the difficulty of different teaching contents in different knowledge point teaching content sets based on the historical teaching score to form corresponding teaching content difficulty division data; conducting qualified screening of different teaching content difficulty division data based on the historical teaching score to form corresponding historical teaching qualified score data; conducting score mapping analysis based on the teaching object according to the historical teaching qualified score data corresponding to different teaching content difficulty division data to form interactive content hierarchical mapping data.

[0047] For different teaching subjects, the learning effects on different teaching knowledge points are different. This difference in learning effects will affect the mastery of the current teaching knowledge point and the mastery of the corresponding teaching knowledge point when learning other teaching knowledge points in the future. The mastery of knowledge points is usually reflected intuitively in the form of exercises or practice tests, and the mastery of teaching content is also affected to a certain extent by the difficulty of the teaching content. Therefore, the scores of historical teaching subjects on the corresponding teaching content can be used as the basis for the difficulty classification of teaching content. Especially in the total score under big data, it can better eliminate the influence of score changes caused by individual learning conditions on the inaccurate judgment of teaching difficulty, making the classification of teaching content more accurate. Of course, there will also be benchmarks for judging whether the teaching subject has passed the learning of teaching content of different difficulty levels. The hierarchical mapping of teaching content is best carried out on the basis of passing the teaching effect. Data with unqualified learning results has no practical reference significance. After all, these data are largely related to the seriousness of individual learning or the sporadic nature of the test.

[0048] Different teaching contents in different knowledge point teaching content sets are divided into difficulty levels based on historical teaching scores to form corresponding teaching content difficulty division data, including: for different knowledge point teaching content sets, extracting the historical scores of all teaching objects corresponding to different teaching contents; normalizing the historical scores of all teaching objects to form historical normalized scores, and determining the total historical scores of the teaching contents; sorting different teaching contents in descending order according to the total historical scores of the teaching contents to form teaching content difficulty division data corresponding to the knowledge point teaching content sets.

[0049] When dividing the difficulty of the same teaching content, the big data of the learning scores of the history teaching objects is used to determine it. It is understandable that different teaching contents may have different total score settings. Therefore, in order to ensure the uniformity and rationality of the analysis, it is necessary to normalize the scores, which can make the results of the difficulty division more accurate and reasonable.

[0050] The data of different teaching content difficulty divisions are screened for qualification based on the history teaching scores to form corresponding history teaching qualification score data, including: setting corresponding teaching qualification scores for the data of different teaching content difficulty divisions; determining all historical normalized scores that reach the teaching qualification scores for different teaching contents in the teaching content difficulty division data as historical normalized qualification scores, and calibrating the teaching objects; and collecting all historical normalized qualification scores under different teaching contents in the teaching content difficulty division data to form history teaching qualification score data.

[0051] Different teaching subjects, based on their individual circumstances, learning attitudes, and the sporadic nature of learning tests, need to screen out data that doesn't achieve satisfactory learning results. It's understandable that the passing score can be set based on actual assessments of the student's absorption of the teaching knowledge points, or a reasonable score can be determined based on big data. After excluding data that doesn't achieve a passing score, the remaining data can serve as the basis for subsequent analysis of the interactive correlation between learning content across different teaching knowledge points, making the analysis more reasonable and accurate.

[0052] According to the history teaching qualified score data corresponding to the data of different teaching content difficulty levels, a score mapping analysis based on the teaching object is performed to form interactive content hierarchical mapping data, including: for different history teaching qualified score data, the following score mapping analysis is performed with the teaching object as the analysis standard: according to the sequential relationship of the teaching content sets of different knowledge points in the teaching content cluster, for different teaching objects, the corresponding teaching content and historical normalized qualified score under any history teaching qualified score data are determined; for different teaching objects, the historical normalized qualified score of the same teaching object in the next history teaching qualified score data is determined according to the connection relationship of the teaching content cluster, and the historical normalized qualified score of the next history teaching qualified score data is continued to be obtained. Take, until no more historical normalized qualified scores of the same teaching object are obtained, all historical normalized qualified scores of the teaching objects are calibrated with corresponding teaching contents and sequentially connected based on teaching content clusters to form an object score mapping relationship; for different teaching objects, for any two adjacent knowledge point teaching content sets, determine the different historical normalized qualified scores of different objects with the same historical normalized qualified scores on the same teaching content in the previous historical teaching qualified score data according to the connection relationship order of the teaching content clusters, and then form the teaching content mapping score range of different teaching contents in the next knowledge point teaching content set corresponding to the determined score on the teaching content of each previous knowledge point teaching content set. m represents the number of different knowledge point teaching content sets, m+1 represents the next knowledge point teaching content set adjacent to the knowledge point teaching content set numbered m in the teaching content cluster, represents the passing score value corresponding to the teaching content numbered n in the knowledge point teaching content set numbered m, n represents the number of the different teaching contents corresponding to the knowledge point teaching content set numbered m, k represents the number of the different teaching contents in the next knowledge point teaching content set adjacent to the knowledge point teaching content set numbered m in the teaching content cluster, The passing score for the teaching content numbered n in the knowledge point teaching content numbered m is The qualified score value range formed by the teaching content numbered k in the adjacent next knowledge point teaching content set; the teaching content mapping score range corresponding to the different scores of different teaching contents in each knowledge point teaching content set is collected to form interactive content hierarchical mapping data.

[0053] The purpose of the hierarchical mapping data to be obtained is to determine how to select the subsequent teaching content after the teaching subject has determined the score obtained on the previous teaching content in the teaching sequence defined by the teaching content cluster. After all, different teaching subjects will affect the difficulty level of the next learning content based on their mastery of the previous teaching content and their own individual knowledge learning. By using the teaching subject as the analysis reference, the possible score obtained by the same subject in the adjacent teaching content set after the score on the previous teaching content is determined in the next teaching content set is determined. In this way, the difficulty of the next teaching content and the teaching content that can be passed can be interactively selected based on the current teaching subject's score on the teaching content, as well as the corresponding score prediction. Here, for different teaching subjects, since the learning ability of the teaching subject is unknown during the subsequent analysis, if different teaching subjects obtain the same score in the current teaching content set, the range of possible scores for the teaching content in the next teaching content set can be determined. In this way, the teaching scores obtained by teaching subjects with different learning abilities can be predicted, making the subsequent interactive generation of teaching content more flexible and with a wider range of choices.

[0054] S4: Acquire real-time teaching result information, and perform interactive content generation guidance processing according to interactive content hierarchical mapping data to form real-time interactive teaching content.

[0055] Real-time teaching result information is obtained, and interactive content generation guidance processing is performed according to the interactive content hierarchical mapping data to form real-time interactive teaching content, including: using the connection relationship of the teaching content cluster as the generation guidance sequence of the teaching content, starting from the first knowledge point teaching content set, any teaching content at the middle level is generated to form the initial sequence teaching content; obtaining the real-time teaching normalized score of the initial sequence teaching content: if the real-time teaching normalized score corresponding to the initial sequence teaching content reaches the corresponding teaching qualified score, then the interactive content generation analysis of the next knowledge point teaching content set is performed; if the real-time teaching normalized score corresponding to the initial sequence teaching content does not reach the corresponding teaching qualified score, then the teaching content in the current knowledge point teaching content set that has a difficulty level adjacent to the initial sequence teaching content and has a lower difficulty level is used as the new sequence teaching content to continue the score qualification analysis until the formed real-time teaching normalized score reaches the corresponding teaching qualified score position, and then the interactive content generation analysis of the next knowledge point teaching content set is performed.

[0056] Of course, when generating real-time interactive content, the first step is to teach according to the order of the teaching content clusters, determine the initial sequence teaching content, and obtain a score for the initial sequence teaching content. Based on the score of the initial sequence teaching content, the next teaching content is analyzed and generated interactively. For the initial teaching content, since it starts with arbitrary teaching content of the middle level, the intermediate arbitrary teaching is just to select one of the two middle difficulty levels if the number of levels of teaching content is even, and to select the middle teaching content as the initial sequence teaching content if the number of levels is odd. If the score reaches the teaching passing score, it can be considered that the teaching subject has completed learning of the teaching content and can proceed to learning the next teaching content in the teaching content cluster. If the teaching passing score is not reached, the subject will continue to learn in the teaching content set at a lower difficulty level until the result of reaching the teaching passing score is obtained and the teaching content of the next teaching content set is selected.

[0057] Conduct interactive content generation analysis of the next knowledge point teaching content set, including: based on the interactive content hierarchical mapping data, use the most difficult teaching content with a mapping relationship in the adjacent next knowledge point teaching content set as the interactive generation content to conduct a mapping score range analysis in the following manner: if the formed real-time teaching normalized score belongs to the mapping score range, then use the real-time teaching normalized score as a reference to conduct interactive content generation analysis of the next knowledge point teaching content set; if the formed real-time teaching normalized score does not belong to the mapping score range, then use the teaching content in the current knowledge point teaching content set with a difficulty level adjacent to the current learning content and with a lower difficulty as the new sequential teaching content to continue to conduct score qualification analysis, until the formed real-time teaching normalized score belongs to the corresponding mapping score range, and then use the real-time teaching normalized score as a reference to conduct interactive content generation analysis of the next knowledge point teaching content set.

[0058] Regarding the selection of teaching content in the next teaching content set, since the scores obtained in the initial sequence teaching content have a mapping relationship in the interactive content grading mapping data, the teaching content and the corresponding score range that are suitable for the different difficulty levels of the teaching objects in the next teaching content set can be determined. Usually, the teaching content with the greatest difficulty is chosen as the first choice. If the score after learning is within the corresponding score range, it is considered that the learning state of the teaching object is in a reasonable state, and the learning of the teaching content is passed. The teaching content of the next teaching content set can be selected based on the score reference interactive content grading mapping data. If the score is not within the corresponding range, it is considered that the corresponding teaching effect has not been achieved or has exceeded the expected teaching effect. Here, it is usually considered that the expectation has not been achieved, so learning is carried out again by obtaining teaching content with lower difficulty until the score is within the corresponding range before selecting the teaching content of the next teaching content set.

[0059] The present invention also provides an interactive content generation system for AR intelligent teaching, which includes: a teaching data acquisition unit, which is used to obtain AR intelligent teaching content data and real-time teaching result information; a teaching database, which is used to store the AR intelligent teaching content data acquired by the teaching data acquisition unit; a feature analysis unit, which is used to perform clustering connection analysis on the AR intelligent teaching content data in the teaching database to form teaching content clusters, and perform hierarchical mapping analysis based on the teaching results to form interactive content hierarchical mapping data; an interactive content generation unit, which is used to obtain the real-time teaching result information acquired by the teaching data acquisition unit, and perform interactive content generation guidance processing based on the teaching content clusters and interactive content hierarchical mapping data formed by the feature analysis unit to form real-time interactive teaching content.

[0060] The system forms a complete interactive content generation system through the teaching data acquisition unit, teaching database, feature analysis unit and interactive content generation unit. Different units have different functions and work closely together to complete different content processing tasks, effectively ensuring the rationality and accuracy of interactive content generation, and is an important material basis for realizing interactive content generation.

[0061] In summary, the interactive content generation method and system for AR intelligent teaching provided by the embodiments of the present invention have the following beneficial effects:

[0062] This method establishes a database of AR intelligent teaching content and clusters different teaching contents based on the connection relationship of knowledge points to form teaching content clusters that can guide the teaching sequence. On this basis, the adaptability of teaching content of different knowledge points is analyzed in combination with the scores of different teaching contents by teaching objects in the history teaching process, that is, the teaching relationship of teaching content of adjacent knowledge points in the teaching effect with score as reference is determined, which provides reasonable and accurate data reference for real-time teaching to select teaching content that adapts to teaching objects for interactive generation of content, greatly improving the personalization level of teaching content and improving the overall teaching effect and teaching quality.

[0063] The system forms a complete interactive content generation system through the teaching data acquisition unit, teaching database, feature analysis unit and interactive content generation unit. Different units have different functions and work closely together to complete different content processing tasks, effectively ensuring the rationality and accuracy of interactive content generation, and is an important material basis for realizing interactive content generation.

[0064] In the embodiment of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association relationship between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can also be achieved by means of the arrangement order of each piece of information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each piece of information can also be identified and indicated uniformly to reduce the indication overhead caused by indicating the same information separately.

[0065] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0066] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0067] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An interactive content generation method for AR intelligent teaching, characterized by: include: Acquire AR intelligent teaching content data and establish an AR intelligent teaching content database; Performing a knowledge point-based clustering analysis on the teaching contents in the AR intelligent teaching content database to form teaching content clusters; Collecting historical teaching result data of the teaching content cluster, and performing hierarchical mapping analysis based on the teaching results to form interactive content hierarchical mapping data; Real-time teaching result information is obtained, and interactive content generation guidance processing is performed according to the interactive content hierarchical mapping data to form real-time interactive teaching content.

2. The interactive content generation method for AR intelligent teaching according to claim 1 is characterized in that: The performing of cluster connection analysis based on knowledge points on the teaching contents in the AR intelligent teaching content database to form teaching content clusters includes: Calibrate teaching knowledge points and related knowledge points for different teaching contents in the AR intelligent teaching content database; Clustering different teaching contents in the AR intelligent teaching content database according to the corresponding teaching knowledge points to form different knowledge point teaching content sets; According to the different knowledge point teaching content sets, all the related knowledge points corresponding to all the teaching contents are analyzed for connections to establish the teaching content cluster.

3. The interactive content generation method for AR intelligent teaching according to claim 2 is characterized in that: The connection analysis of all the related knowledge points corresponding to all the teaching contents in the different knowledge point teaching content sets to establish the teaching content cluster includes: Any set of the above-mentioned knowledge point teaching content is determined as an analysis object set, and the following connection analysis is performed: For the analysis object set, determining the knowledge point teaching content sets in which the teaching knowledge points of other knowledge point teaching content sets are the related knowledge points of the analysis object set, and forming connection directions from the teaching knowledge points to the related knowledge points on different knowledge point teaching content sets; For each of the knowledge point teaching content sets determined to be associated with the analysis object set, continue to perform connection analysis on all the related knowledge points to determine all the corresponding associated knowledge point teaching content sets, until all the knowledge point teaching content sets are linked together to form the teaching content cluster.

4. The interactive content generation method for AR intelligent teaching according to claim 3 is characterized in that: The collecting of historical teaching result data of the teaching content cluster and performing hierarchical mapping analysis based on the teaching results to form interactive content hierarchical mapping data includes: Determining history teaching score data for different teaching contents in different knowledge point teaching content sets based on the history teaching result data; Dividing the difficulty of different teaching contents in the different knowledge point teaching content sets based on the history teaching scores to form corresponding teaching content difficulty classification data; Performing qualified screening based on the history teaching score on the different difficulty classification data of the teaching content to form corresponding history teaching qualified score data; According to the history teaching passing score data corresponding to the different teaching content difficulty classification data, a score mapping analysis based on the teaching object is performed to form the interactive content grading mapping data.

5. The interactive content generation method for AR intelligent teaching according to claim 4 is characterized in that: The difficulty classification of different teaching contents in the different knowledge point teaching content sets based on the history teaching scores is performed to form corresponding teaching content difficulty classification data, including: For different sets of teaching content for the knowledge points, extract the historical scores of all teaching objects corresponding to the different teaching contents; Normalize the historical scores of all teaching objects to form a historical normalized score, and determine the total historical score of the teaching content; According to the total historical scores of the teaching contents, different teaching contents are sorted in descending order to form the teaching content difficulty classification data corresponding to the knowledge point teaching content set.

6. The interactive content generation method for AR intelligent teaching according to claim 5 is characterized in that: The method of performing qualified screening on the different teaching content difficulty classification data based on the history teaching score to form corresponding history teaching qualified score data includes: Setting corresponding teaching passing scores for different difficulty classification data of the teaching content; For different teaching contents in the teaching content difficulty classification data, all the historical normalized scores that reach the teaching qualified score are determined as historical normalized qualified scores, and teaching objects are calibrated; All the history normalized passing scores under different teaching contents in the teaching content difficulty division data are collected to form the history teaching passing score data.

7. The interactive content generation method for AR intelligent teaching according to claim 6, characterized in that: The score mapping analysis based on the teaching object is performed on the history teaching qualified score data corresponding to the different teaching content difficulty classification data to form the interactive content classification mapping data, including: For different history teaching passing score data, the following score mapping analysis is performed based on the teaching object as the analysis standard: According to the sequential relationship of the different knowledge point teaching content sets in the teaching content cluster, for different teaching objects, the corresponding teaching content and the history normalized passing score under any of the history teaching passing score data are determined; For different teaching objects, the historical normalized qualified score of the same teaching object in the next history teaching qualified score data is determined based on the connection relationship of the teaching content cluster, and the historical normalized qualified score of the next history teaching qualified score data is continuously obtained until the historical normalized qualified score of the same teaching object is no longer obtained, and all the historical normalized qualified scores of the teaching objects are calibrated with the corresponding teaching content and sequentially connected based on the teaching content cluster to form an object score mapping relationship; For different teaching objects, the order of the connection relationship of the teaching content clusters is used to determine the different normalized qualified scores of different objects with the same normalized qualified score on the same teaching content in the previous history teaching qualified score data, and then the different normalized qualified scores of different teaching contents in the next history teaching qualified score data are formed. The teaching content mapping score range of different teaching contents in the next knowledge point teaching content set corresponding to the determined score on the teaching content of each previous knowledge point teaching content set is formed. m represents the number of the different knowledge point teaching content sets, m+1 represents the next knowledge point teaching content set adjacent to the knowledge point teaching content set numbered m in the connection relationship of the teaching content cluster, represents the passing score value corresponding to the teaching content numbered n in the knowledge point teaching content set numbered m, n represents the number of the different teaching content corresponding to the knowledge point teaching content set numbered m, k represents the number of the different teaching content in the next knowledge point teaching content set adjacent to the knowledge point teaching content set numbered m in the connection relationship of the teaching content cluster, The qualified score value determined under the teaching content numbered n in the teaching content numbered m is The passing score range formed by the teaching content numbered k in the next adjacent knowledge point teaching content set; The teaching content mapping score ranges corresponding to different scores of different teaching contents in each of the knowledge point teaching content sets are collected to form the interactive content hierarchical mapping data.

8. The interactive content generation method for AR intelligent teaching according to claim 7, characterized in that: The acquiring of real-time teaching result information and performing interactive content generation guidance processing according to the interactive content hierarchical mapping data to form real-time interactive teaching content includes: Taking the connection relationship of the teaching content clusters as the guiding sequence for generating teaching content, starting from the first knowledge point teaching content set, any teaching content at the intermediate level is generated to form the initial sequence teaching content; Obtain the real-time teaching normalized score of the initial sequential teaching content: If the real-time teaching normalized score corresponding to the initial sequential teaching content reaches the corresponding teaching passing score, then performing interactive content generation analysis for the next knowledge point teaching content set; If the real-time teaching normalized score corresponding to the initial sequence teaching content does not reach the corresponding teaching qualified score, the teaching content in the current knowledge point teaching content set with a difficulty level adjacent to the initial sequence teaching content and with a lower difficulty level will be used as the new sequence teaching content to continue the score qualification analysis until the formed real-time teaching normalized score reaches the corresponding teaching qualified score position, and then the interactive content generation analysis of the next knowledge point teaching content set will be carried out.

9. The interactive content generation method for AR intelligent teaching according to claim 8, characterized in that: The interactive content generation analysis of the next knowledge point teaching content set includes: According to the interactive content hierarchical mapping data, the teaching content with the greatest difficulty in the next adjacent knowledge point teaching content set with a mapping relationship is used as the interactive generated content and the mapping score range analysis is performed in the following manner: If the formed real-time teaching normalized score falls within the mapping score range, then the interactive content generation analysis of the next knowledge point teaching content set is performed based on the real-time teaching normalized score; If the normalized score of real-time teaching formed does not fall within the mapping score range, the teaching content in the current knowledge point teaching content set with a difficulty level adjacent to the current learning content and with a lower difficulty level will be used as the new sequential teaching content to continue the score qualification analysis until the normalized score of real-time teaching formed falls within the corresponding mapping score range, and then the interactive content generation analysis of the next knowledge point teaching content set will be performed with reference to the normalized score of real-time teaching.

10. An interactive content generation system for AR intelligent teaching, adopting the interactive content generation method for AR intelligent teaching according to any one of claims 1 to 9, characterized in that: include: Teaching data acquisition unit, used to obtain AR intelligent teaching content data and real-time teaching result information; A teaching database, used to store the AR intelligent teaching content data acquired by the teaching data acquisition unit; a feature analysis unit, configured to perform cluster connection analysis on the AR intelligent teaching content data in the teaching database to form teaching content clusters, and perform hierarchical mapping analysis based on teaching results to form interactive content hierarchical mapping data; The interactive content generation unit is used to obtain the real-time teaching result information obtained by the teaching data acquisition unit, and perform interactive content generation guidance processing based on the teaching content clusters and interactive content hierarchical mapping data formed by the feature analysis unit to form real-time interactive teaching content.

Images