An education cloud resource sharing interaction method and system under a big data platform

Abstract

This invention relates to the field of data processing technology, specifically to a method and system for sharing and interacting educational cloud resources under a big data platform. The method first acquires knowledge points from teachers' traditional teaching, work steps from job orders uploaded by enterprises, and IPDICE forms uploaded by students, removing coarse-grained and fine-grained steps from the work steps; based on the level of detail in the segmentation, the correlation between abilities, and the fluctuation of form scores, it determines the changing trends of students' different abilities under different knowledge points; based on students' access to different work steps, it determines students' employment preference index for different work steps; based on students' employment preference index and the changing trends of different abilities, it determines the degree of demand for different abilities under different knowledge points; and according to the order of the degree of demand, it pushes relevant educational cloud resources to students. This invention ensures that the push of educational resources matches the actual work needs of students.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and system for sharing and interacting educational cloud resources under a big data platform. Background Technology

[0002] In the context of educational cloud resource sharing, "shared interaction" refers to interactive behaviors such as two-way or multi-way information transmission, collaborative creation, and feedback interaction among different entities, such as teachers, students, schools, and educational institutions, through the cloud platform around educational resources. For example, teachers push learning resources on the platform, students read and provide feedback, and students share notes.

[0003] In vocational education, existing methods have a relatively singular interactive subject and limit shared interaction to subject cognition, while ignoring actual occupational needs and students' actual behavioral abilities. Existing methods only analyze changes in students' cognition based on teacher-student interaction in subject cognition, and then adjust shared educational resources accordingly. This ignores the actual dynamic needs and action logic in real work scenarios, resulting in a disconnect between teaching content and actual job requirements. It is impossible to adjust shared educational cloud resources in combination with students' actual abilities and the job requirements of enterprises. Summary of the Invention

[0004] To address the technical problem of adjusting shared educational cloud resources to match students' actual abilities with the job requirements of enterprises, the present invention aims to provide a method and system for sharing and interacting educational cloud resources under a big data platform. The specific technical solution adopted is as follows:

[0005] In a first aspect, embodiments of the present invention provide a method for sharing and interacting educational cloud resources under a big data platform, the method comprising:

[0006] The system acquires knowledge points from teachers' traditional teaching, work steps from job orders uploaded by enterprises, and IPDICE forms uploaded by students. Each work step is matched with a corresponding knowledge point and multiple IPDICE forms representing various student abilities.

[0007] Based on the number of IPDICE forms corresponding to each work step, the form abandonment rate, and the form completion time, the fineness of the work step division is determined, and the work steps are divided into coarse-precision steps and fine-precision steps. Coarse-precision steps and fine-precision steps are then removed from the work steps.

[0008] Based on the granularity of segmentation, the correlation of abilities, and the fluctuation of form scores, the changing trends of students' different abilities under different knowledge points are determined; based on students' access to different work processes, the employment preference index of students for different work processes is determined; based on students' employment preference index and the changing trends of different abilities, the degree of demand for students' different abilities under different knowledge points is determined; and relevant educational cloud resources are pushed to students according to the order of the degree of demand.

[0009] Furthermore, the method for matching work processes and knowledge points is as follows:

[0010] Based on the work steps in the job orders uploaded by the enterprise, a logic tree is constructed as the work logic tree; based on the knowledge points in the teacher's traditional teaching, a logic tree is constructed as the knowledge logic tree; wherein, the nodes in the work logic tree are work steps, and the nodes in the knowledge logic tree are knowledge points.

[0011] Taking any node corresponding to a work step in the work logic tree as the target node, calculate the cosine similarity between the word vector of the target node and the word vector of any node in the knowledge logic tree, as the first similarity; and calculate the cosine similarity between the word vector of the target node and the parent node corresponding to the node in the knowledge logic tree, as the second similarity; take the average of the first and second similarities as the similarity representation value of the target node; and match the target node with the node corresponding to the maximum value of the similarity representation value in the knowledge logic tree.

[0012] Furthermore, the determination of the fineness of work step division based on the number of IPDICE forms corresponding to each work step, the form abandonment rate, and the form completion time includes:

[0013] The percentage of unanswered questions in all forms corresponding to each work stage is used as the unanswered rate.

[0014] Obtain the percentage of form completion time for the current work stage in the total form completion time for all work stages, as the time percentage; obtain the variance of the completion time for each question in the form for the current work stage, as the variance; calculate the product of the time percentage and the variance as the time reference value.

[0015] Get the number of times the form corresponding to each work step was modified during the filling process;

[0016] The product of the abandonment rate, the reference value of the duration, and the number of revisions is used as the precision of the work process division.

[0017] Furthermore, the division of the working process into coarse-precision and fine-precision stages includes:

[0018] Work steps with a normalized division precision greater than the preset division range are marked as fine precision steps; work steps with a normalized division precision less than the preset division range are marked as coarse precision steps.

[0019] Furthermore, the determination of the changing trends of students' different abilities under different knowledge points based on the granularity of segmentation, ability correlation, and the degree of fluctuation in form scores includes:

[0020] Use any kind of knowledge point as the target knowledge point, any kind of ability as the target ability, and the IPDICE form corresponding to the target ability as the target form.

[0021] The average score of the work ability of the target form corresponding to the target knowledge point in the knowledge logic tree within a single detection period is taken as the execution ability score of the target knowledge point in a single detection period.

[0022] For the target knowledge point, obtain the first-order difference sequence of the execution ability score of the target ability in all testing periods, and use it as the ability difference sequence of the student's target ability under the target knowledge point;

[0023] For a target knowledge point, the average of the Pearson correlation coefficients between the ability difference sequence of the target ability and the ability difference sequences of other abilities besides the target ability is used as the ability correlation coefficient of the student's target ability under the target knowledge point.

[0024] By combining the granularity of the segmentation, the ability correlation coefficient, and the size of the elements in the ability difference sequence, the changing trend of students' target abilities under the target knowledge points can be determined.

[0025] Furthermore, the determination of the changing trend of students' target abilities under the target knowledge point by combining the fineness of segmentation, the ability correlation coefficient, and the element size of the ability difference sequence includes:

[0026] The mean of the fineness of the division of all work steps corresponding to the student's target ability under the target knowledge point is denoted as the fine mean.

[0027] The absolute value of the mean of the elements in the ability difference sequence of students' target abilities under the target knowledge points is denoted as the fluctuation amplitude.

[0028] The percentage of elements in the ability difference sequence of students' target abilities under the target knowledge points that take negative values ​​is denoted as the decay percentage.

[0029] The product of the fine mean of the target ability, the ability correlation coefficient, the fluctuation amplitude, and the attenuation ratio is used as the trend of the student's target ability under the target knowledge point.

[0030] Furthermore, the determination of the demand for different abilities of students under different knowledge points based on the changing trends of students' employment preference index and different abilities includes:

[0031] Using any ability as the target ability, the changing trend of the target ability of the target knowledge point is processed by first-order difference in chronological order to obtain the changing trend difference sequence. The proportion of the number of elements with positive values ​​in the changing trend difference sequence is used as the effective unstable growth proportion of the target ability of the target knowledge point.

[0032] By combining the employment preference index, the proportion of effective unstable growth, and the element size of the trend difference sequence, the degree of demand for students' target abilities under the target knowledge points is determined; among them, the employment preference index, the proportion of effective unstable growth, and the element size of the trend difference sequence are all positively correlated with the degree of demand.

[0033] Furthermore, the determination of students' employment preference indices for different job stages based on their access to different job stages includes:

[0034] Using any knowledge point as the target knowledge point, calculate the product of the student's recent access index in the work process corresponding to the target knowledge point, the student's interaction frequency with other users on the relevant pages of the work process corresponding to the target knowledge point, and the percentage of time the student spends on the relevant pages of the work process corresponding to the target knowledge point. This product is used as the student's employment preference index for the work process corresponding to the target knowledge point.

[0035] Furthermore, the method for obtaining the student's recent access index in the work process corresponding to the target knowledge point is as follows:

[0036] For the target knowledge point, obtain the number of times the student fills out the corresponding IPDICE form in the work process;

[0037] For the target knowledge point, obtain the time interval between each two consecutive times that a student fills out the corresponding IPDICE form for each work step;

[0038] The ratio of the number of times a student fills out a form to the interval between forms is used as the student's recent access index for the work process corresponding to the target knowledge point.

[0039] Secondly, an educational cloud resource sharing and interaction system based on a big data platform is provided, the system comprising the following modules:

[0040] The data acquisition module is used to acquire knowledge points from teachers' traditional teaching, work steps from job orders uploaded by enterprises, and IPDICE forms uploaded by students. Each work step is matched with a corresponding knowledge point and multiple IPDICE forms representing various student abilities.

[0041] The process segmentation module is used to determine the fineness of the process segmentation based on the number of IPDICE forms corresponding to the process segment, the form abandonment rate, and the form filling time. The process segmentation is divided into coarse-precision process segment and fine-precision process segment, and then the coarse-precision process segment and fine-precision process segment are deleted from the process segment.

[0042] The resource recommendation module is used to determine the changing trends of students' different abilities under different knowledge points based on the granularity of segmentation, ability relevance, and the degree of fluctuation of form scores; to determine students' employment preference index for different work stages based on students' access to different work stages; to determine the degree of demand for different abilities under different knowledge points based on students' employment preference index and the changing trends of different abilities; and to recommend relevant educational cloud resources to students in order of the degree of demand.

[0043] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0044] Fourthly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0045] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.

[0046] The embodiments of the present invention have at least the following beneficial effects:

[0047] This invention adjusts the level of detail in work segmentation based on students' completion of the IPDICE forms corresponding to each work stage. This ensures that each work stage effectively reflects students' work abilities. Forms are then created based on these adjusted work stages, and students' abilities in different work stages are assessed using the IPDICE forms they submit, enabling a comprehensive evaluation of their various skills. Furthermore, by analyzing the fluctuations in students' abilities and their employment preferences, the invention identifies their needs for improving different skills. Based on the order of these needs, relevant educational cloud resources are recommended to students. This ensures that the recommended educational resources align with students' actual work requirements, going beyond structural chemistry knowledge to meet real-world employment needs. Attached Figure Description

[0048] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating a method for sharing and interacting educational cloud resources on a big data platform, provided in one embodiment of the present invention.

[0050] Figure 2 This is a system block diagram of an educational cloud resource sharing and interaction system under a big data platform, provided as an embodiment of the present invention. Detailed Implementation

[0051] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, describes the specific implementation, structure, features, and effects of an educational cloud resource sharing and interaction method and system based on a big data platform proposed by the present invention.

[0052] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0053] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.

[0054] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0056] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

[0057] The following description, in conjunction with the accompanying drawings, details the specific solution of the educational cloud resource sharing and interaction method and system provided by this invention under a big data platform.

[0058] Please see Figure 1 The diagram illustrates a flowchart of a method for sharing and interacting educational cloud resources under a big data platform, according to an embodiment of the present invention. The method includes the following steps:

[0059] Step S100: Obtain the knowledge points from teachers' traditional teaching, the work steps in the job orders uploaded by enterprises, and the IPDICE forms uploaded by students. Each work step is matched with a corresponding knowledge point and multiple IPDICE forms representing various abilities of students.

[0060] This invention is applicable to the enterprise-teacher-student educational cloud resource sharing platform in the field of vocational education.

[0061] In this process, enterprises upload job postings to the education cloud resource sharing platform. These postings include the specific job openings and the corresponding work processes. Preferably, the education cloud resource sharing platform can also use web crawlers to capture job postings from recruitment websites.

[0062] Teachers upload loose-leaf teaching materials to the education cloud resource sharing platform based on students' actual needs. These loose-leaf teaching materials are created by teachers and include knowledge points from traditional teaching, thus transforming real work tasks from enterprises into learning resources.

[0063] The student interface allows access to loose-leaf teaching materials uploaded by teachers and the upload of IPDICE forms corresponding to different work stages. It also stores student access logs and interaction records. The IPDICE form, constructed based on action logic, is filled out by students and used to assess their actual work abilities. Each IPDICE form includes a work ability score for different student skills, and one or more IPDICE forms correspond to one work stage.

[0064] The IPDICE form is a form in which students fill out the forms and teachers score the students' work performance. The teacher's score is the student's work performance score.

[0065] It should be noted that the IPDICE forms include an information sheet, a planning sheet, a decision-making sheet, an implementation sheet, a checklist, and an evaluation sheet. These six forms are used to assess students' abilities in different aspects of each work stage across six dimensions. In other words, each work stage corresponds to one of the six IPDICE forms, and each IPDICE form corresponds to one of the student's abilities in that stage. Specifically, the information sheet assesses information gathering and problem analysis skills; the planning sheet assesses solution design and resource coordination skills; the decision-making sheet assesses optimization capabilities, such as cost-effectiveness and safety; the implementation sheet assesses students' operational skills and execution ability; the checklist assesses students' deviation identification and quality control abilities; and the evaluation sheet assesses students' debriefing, reflection, and continuous improvement abilities.

[0066] Based on the work steps in the job orders uploaded by the enterprise, a logic tree is constructed as the work logic tree; based on the knowledge points in the teacher's traditional teaching, a logic tree is constructed as the knowledge logic tree; wherein, the nodes in the work logic tree are work steps, and the nodes in the knowledge logic tree are knowledge points.

[0067] The work process tree of the job order is mapped to the knowledge logic tree corresponding to the knowledge points. Taking a single work process as an example, the Word2Vec model first obtains the word vectors of each node in the above work logic tree. In this embodiment of the invention, the word vectors are set to 512 dimensions.

[0068] Taking any node corresponding to a work step in the work logic tree as the target node, the cosine similarity between the word vector of the target node and the word vector of any node in the knowledge logic tree is calculated as the first similarity. The cosine similarity between the word vector of the target node and the parent node corresponding to that node in the knowledge logic tree is also calculated as the second similarity. The mean of the first and second similarities is taken as the similarity representation value of the target node. The target node is then matched with the node corresponding to the maximum similarity representation value in the knowledge logic tree. It should be noted that different nodes in the work logic tree can match the same node in the knowledge logic tree; that is, different work steps can match the same knowledge point.

[0069] Taking the word vector of node i corresponding to a single work step as an example, calculate the word vector of node i and any node in the knowledge logic tree. cosine similarity of word vectors And obtain node i and node Cosine similarity of the word vectors of the corresponding parent node Calculate cosine similarity Similarity to cosine The mean value c is used as the similarity representation value to obtain the similarity representation value between node i and all nodes in the knowledge logic tree. Node i is then matched with the node corresponding to the maximum similarity representation value in the knowledge logic tree.

[0070] Step S200: Based on the number of IPDICE forms corresponding to each work step, the form abandonment rate, and the form completion time, determine the level of detail in dividing the work steps into coarse-precision steps and fine-precision steps, and then delete the coarse-precision steps and fine-precision steps from the work steps.

[0071] In the actual learning process, the action logic is implemented in the form of IPDICE forms. When job-related information is uploaded by companies or obtained through company surveys, the accuracy of the IPDICE forms in assessing students' abilities varies depending on the level of detail in the division of work steps. If the work steps are divided too finely, the content that students need to fill in may be too detailed. For example, if the "complaint handling" step is divided into multiple small steps such as "answering the phone, recording the complaint content, calming the customer, checking the order, and analyzing the reasons for the complaint," and an IPDICE form is created for each of these steps, the assessment content may be too trivial and low-value, failing to reflect the student's true work ability.

[0072] Therefore, based on the effectiveness of IPDICE form completion, the work process segmentation needs to be adjusted. When students spend a long time filling out the form, they may need to fill in more detailed information. When the time spent filling out the form varies significantly, some students may quickly skip it, while others may carefully consider each word. In these cases, the form content has a higher rate of abandonment and modification. In both situations, the work process corresponding to the current form may be too finely segmented, thus requiring adjustment. It should be noted that in the following steps, the IPDICE form will be referred to simply as "form," meaning that "form" specifically refers to the IPDICE form.

[0073] First, obtain the abandonment rate of the IPDICE forms corresponding to the work process. This abandonment rate is obtained by calculating the percentage of abandoned questions in all forms corresponding to the work process out of all questions. More specifically, the abandonment rate is calculated as the ratio of the number of abandoned questions in all forms corresponding to the work process to the total number of questions in all forms.

[0074] Obtain the percentage of time spent filling out the form for the current work stage relative to the total time spent filling out the form for all work stages, as the time percentage; obtain the variance of the time spent filling out each question in the form for the current work stage, as the variance. Calculate the product of the time percentage and the variance as a reference value for the time; the larger the time percentage, the longer it takes students to fill out the form for the current work stage.

[0075] Get the number of times the form corresponding to each work step was modified during the filling process;

[0076] The product of the abandonment rate, the reference value of the duration, and the number of revisions is used as the precision of the work process division.

[0077] In some embodiments, taking the k-th work step as an example, the granularity of the division of the k-th work step... The calculation formula is: ;in, Let be the abandonment rate of the k-th work stage; This represents the number of modifications made in the k-th work step. Let be the variance of the k-th work stage; This represents the percentage of time spent on the k-th work step. This represents the average time taken to complete all forms in the k-th work stage. The variance of the time taken to complete all forms across all work stages.

[0078] The division precision is normalized, and the normalized division precision ranges from (0, 1). Work steps with a normalized division precision greater than the preset division range are marked as fine precision steps; work steps with a normalized division precision less than the preset division range are marked as coarse precision steps.

[0079] In this embodiment of the invention, the preset division range is [0.3, 0.7]. In other embodiments, the implementer can adjust this value range according to the actual situation. That is, when the normalized division fineness value is greater than 0.7, it is marked as a fine-precision stage; when the normalized division fineness value is less than 0.3, it is marked as a coarse-precision stage. Based on the established working logic tree, coarse-precision stages that are too finely divided and their corresponding IPDICE forms are deleted, while the IPDICE forms established by the working stages corresponding to their parent nodes are retained; fine-precision stages that are too coarsely divided and their corresponding IPDICE forms are deleted, while the IPDICE forms established by the working stages corresponding to their child nodes are retained. Coarse-precision stages and fine-precision stages are deleted from the working stages, and the corresponding IPDICE forms are deleted, thereby realizing the updating of the working stages and their corresponding IPDICE forms.

[0080] Step S300: Based on the granularity of the segmentation, the correlation of abilities, and the fluctuation of form scores, determine the changing trends of students' different abilities under different knowledge points; based on students' access to different work processes, determine students' employment preference index for different work processes; based on students' employment preference index and the changing trends of different abilities, determine the degree of demand for students' different abilities under different knowledge points; and push relevant educational cloud resources to students according to the order of the degree of demand.

[0081] In the actual learning process, as students learn about work practice and behavioral logic-related processes, their abilities in different fields fluctuate over time, and there are certain correlations between different abilities. For example, when a student has strong information gathering ability in a certain action stage, it lays a good foundation for the corresponding action process, which may result in a higher score on the plan sheet. Therefore, based on the correlation between different abilities and the behavioral assessment results, we can analyze the degree of need for different abilities of students.

[0082] Based on the adjusted work steps and the adjusted IPDICE form, the corresponding work steps are matched and aligned with the knowledge points. For example, the node "insulation resistance test" in the work logic tree is matched with the node "high voltage insulation test" in the knowledge logic tree according to the method in step S200. If a student scores 3 on the implementation form of the IPDICE form for the work node "insulation resistance test" in a certain instance, then the student's work ability score in terms of operational skills and execution ability in the knowledge point "high voltage insulation test" is considered to be 3.

[0083] With one week as a testing cycle, for any student, any kind of knowledge point is used as the target knowledge point, any kind of ability is used as the target ability, and the IPDICE form corresponding to the target ability is used as the target form. The average of the work ability scores of the target form corresponding to the target knowledge point in the knowledge logic tree within a single testing cycle is used as the execution ability score of the target knowledge point in the single testing cycle.

[0084] For a target knowledge point, the first-order difference sequence of the execution ability scores for the target ability across all testing periods is obtained as the ability difference sequence for the student's target ability under the target knowledge point. More specifically: the execution ability scores for all testing periods are obtained, and the execution ability scores for different testing periods are arranged chronologically to obtain an execution ability sequence, which in turn yields a first-order difference sequence of the execution ability sequence, serving as the ability difference sequence. In this embodiment of the invention, the first-order difference sequence is a forward first-order difference sequence.

[0085] For a target knowledge point, the average of the Pearson correlation coefficients between the target ability's ability difference sequence and the ability difference sequences of other abilities besides the target ability is used as the ability correlation coefficient of the target ability.

[0086] If the difference amplitude is large in the first-order difference sequence corresponding to all detection cycles, there are many negative difference values, and the mean Pearson coefficient r of the execution ability sequence and the execution ability sequences of other abilities besides the target ability is large, it indicates that the student's ability is strongly correlated with other abilities. In this case, the fluctuation of this ability has a greater impact on other abilities, and the greater the degree of instability and fluctuation of the current ability, the greater the trend of change.

[0087] It should be noted that since there is a one-to-one correspondence between the nodes in the working logic tree and the nodes in the knowledge logic tree, and each node in the working logic tree represents a working step, and each working step has its own corresponding IPDICE form, the correspondence between the nodes in the knowledge logic tree and the IPDICE form can be obtained.

[0088] Furthermore, by combining the granularity of the segmentation, the ability correlation coefficient, and the element size of the ability difference sequence, the changing trend of students' target abilities under the target knowledge points can be determined.

[0089] The mean of the fineness of the division of all work processes corresponding to the target capability is denoted as the fine mean.

[0090] The mean of the fineness of the division of all work steps corresponding to the student's target ability under the target knowledge point is denoted as the fine mean.

[0091] The absolute value of the mean of the elements in the ability difference sequence of students' target abilities under the target knowledge points is denoted as the fluctuation amplitude.

[0092] The percentage of elements in the ability difference sequence of students' target abilities under the target knowledge points that take negative values ​​is denoted as the decay percentage.

[0093] The product of the fine mean of the target ability, the ability correlation coefficient, the fluctuation amplitude, and the attenuation ratio is used as the trend of the student's target ability under the target knowledge point.

[0094] In some embodiments, taking the y-th ability as the target ability as an example, the changing trend of students' target abilities under the target knowledge point. The calculation formula is: ;in, denoted as the fine mean of all work steps corresponding to the student's target ability under the target knowledge point; r is the ability correlation coefficient corresponding to the student's target ability under the target knowledge point. The fluctuation range corresponding to the student's target ability under the target knowledge point; The number of elements in the first-order difference sequence corresponding to the execution capability sequence; The number of elements with negative values ​​in the first-order difference sequence corresponding to the execution capability sequence; This represents the percentage decrease in a student's target ability for the target knowledge point. A larger percentage decrease indicates that the ability decreases more frequently over time.

[0095] This allows us to obtain the changing trends of different abilities of all students under different knowledge points.

[0096] In actual work, for a knowledge point, fluctuations in ability have a certain impact on behavior in the IPDICE form corresponding to the work process. If the ability corresponding to a certain work process has a faster growth trend in recent times, and if a student fills out the form for the work process more frequently, spends more time accessing relevant teaching materials for the corresponding ability, and interacts more frequently with other users on the relevant textbook pages (e.g., comments, Q&A, likes, favorites, etc.), then the student's recent employment preference is more focused on that work process, the weaker the student's ability in that area is, the more it needs to be improved, and the greater the student's demand for that ability in the current knowledge point.

[0097] For the target knowledge point, obtain the number of times the student fills out the corresponding IPDICE form in the work process;

[0098] For the target knowledge point, obtain the time interval between each two consecutive times that a student fills out the corresponding IPDICE form for each work step;

[0099] The ratio of the number of times a student fills out a form to the interval between forms is used as the recent access index for the work process corresponding to the target knowledge point.

[0100] By combining students' recent access index to the work process, the frequency of student interaction with other users on the relevant pages of the work process, and the percentage of time students spend on the relevant pages of the work process, the employment preference index for students' target knowledge points in the corresponding work process is determined. More specifically: taking any knowledge point as the target knowledge point, the employment preference index for students' target knowledge point in the corresponding work process is determined by combining students' recent access index to the work process corresponding to the target knowledge point, the frequency of student interaction with other users on the relevant pages of the work process corresponding to the target knowledge point, and the percentage of time students spend on the relevant pages of the work process corresponding to the target knowledge point.

[0101] Taking the z-th student and the k-th work stage as an example, this analysis examines the employment preference index of the z-th student in the k-th work stage. The calculation formula is: ;in, Let be the recent access index of the z-th student for the knowledge point corresponding to the k-th work step; The interaction frequency between the z-th student and other users on the relevant pages of the knowledge point in the k-th work stage; The time spent on the relevant page for the knowledge point corresponding to the z-th student in the k-th work stage; Let be the average time spent by the z-th student on the relevant pages for the knowledge points across all work stages; This represents the percentage of time spent by the z-th student on the relevant page for the knowledge point in the k-th work stage. A higher percentage indicates that the z-th student is more proactive in learning the knowledge point in the k-th work stage, and that the knowledge in the k-th work stage aligns more closely with their employment preferences. It should be noted that the knowledge point in the k-th work stage can also be understood as the target knowledge point.

[0102] For the target ability of the target knowledge point, the change trend of the target ability of the target knowledge point is processed by first-order difference according to the time sequence to obtain the change trend difference sequence. The proportion of the number of elements with positive values ​​in the change trend difference sequence is used as the effective unstable growth proportion of the target ability of the target knowledge point.

[0103] By combining the employment preference index, the proportion of effective unstable growth, and the element size of the trend difference sequence, the degree of students' demand for the target ability of the target knowledge point can be determined; among them, the employment preference index, the proportion of effective unstable growth, and the element size of the trend difference sequence are all positively correlated with the degree of demand.

[0104] More specifically: calculate the mean of the positive elements in the trend difference sequence as the effective unstable growth amplitude; calculate the product of the employment preference index of all work links corresponding to the target ability of the target knowledge point, the effective unstable growth ratio corresponding to the target ability of the target knowledge point, and the effective unstable growth amplitude as the demand level of the target ability of the target knowledge point.

[0105] In some embodiments, taking the y-th ability as the target ability as an example, the degree of demand for the target ability under the target knowledge point of the z-th student. The calculation formula is: ;in, Let be the average of the employment preference index for all work stages corresponding to the target ability under the target knowledge point for the z-th student; The number of elements with positive values ​​in the difference sequence of the changing trend of the target ability under the target knowledge point of the z-th student; The total number of elements in the difference sequence representing the changing trend of the target ability under the target knowledge point for the z-th student; The percentage of effective but unstable growth in target ability under the target knowledge point for the z-th student; Let be the effective unstable growth amplitude of the target ability under the target knowledge point for the z-th student.

[0106] The demand level is normalized, and this normalized demand level is used as the priority for pushing knowledge points to the z-th student's corresponding ability. This yields the push priority for different knowledge points under different abilities. Based on the normalized demand level, relevant educational cloud resources are pushed to students, that is, according to the push priority. Specifically, knowledge points are pushed based on the student's different abilities, in descending order of push priority. For example, for ability A1, the student is first pushed the knowledge point with the highest push priority, and finally the student is pushed the knowledge point with the lowest push priority.

[0107] Since teachers need to upload relevant teaching materials to the teaching system based on students' feedback on their work preferences and abilities, and help students improve their corresponding work abilities in a targeted manner, the higher the demand for a certain knowledge point's corresponding abilities among the student groups under the teacher's responsibility, the more effective the educational resources for that knowledge point should be, and the greater the update index of its corresponding teaching materials should be.

[0108] As a preferred embodiment of the present invention, taking a single teacher as the target teacher and the yth ability as the target ability as an example, the update index of the knowledge points corresponding to the target ability and the student group under the responsibility of the target teacher is analyzed.

[0109] The teacher's update index of the target competencies The calculation formula is: ;in, The mean of the degree of need for the target competency among the student group that has interacted with the target teacher within six months; The maximum value of the employment preference index for the target competency across all work stages for the student group that has interacted with the target teacher within the past six months; It represents the minimum employment preference index among all work stages of the target competency of the student group that has interacted with the target teacher within six months. The smaller the update index, the more consistent the needs and preferences of the students currently under the teacher's care regarding the corresponding work process for that ability, and the more necessary it is to update the educational resources for that knowledge point. The larger the update index, the more necessary it is to update the educational resources for that knowledge point.

[0110] By combining students' needs with the educational resource update index, the corresponding educational resources are updated based on information interaction between enterprises, students and teachers, so that the output of educational resources meets the actual needs of enterprises and the fluctuations in students' own work abilities.

[0111] Please see Figure 2 , Figure 2 This invention provides a system block diagram of an educational cloud resource sharing and interaction system under a big data platform, comprising:

[0112] The data acquisition module is used to acquire knowledge points from teachers' traditional teaching, work steps from job orders uploaded by enterprises, and IPDICE forms uploaded by students. Each work step is matched with a corresponding knowledge point and multiple IPDICE forms representing various student abilities.

[0113] The process segmentation module is used to determine the fineness of the process segmentation based on the number of IPDICE forms corresponding to the process segment, the form abandonment rate, and the form filling time. The process segmentation is divided into coarse-precision process segment and fine-precision process segment, and then the coarse-precision process segment and fine-precision process segment are deleted from the process segment.

[0114] The resource recommendation module is used to determine the changing trends of students' different abilities under different knowledge points based on the granularity of segmentation, ability relevance, and the degree of fluctuation of form scores; to determine students' employment preference index for different work stages based on students' access to different work stages; to determine the degree of demand for different abilities under different knowledge points based on students' employment preference index and the changing trends of different abilities; and to recommend relevant educational cloud resources to students in order of the degree of demand.

[0115] Alternatively, the transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic cable and digital subscriber line, or a wireless link, such as, but not limited to, wireless Fidelity (WIFI), Bluetooth and mobile device networks.

[0116] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0117] This invention provides a computer device. Exemplarily, the computer device includes: a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the computer device can execute any of the aforementioned educational cloud resource sharing and interaction methods under a big data platform.

[0118] Furthermore, embodiments of the present invention also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the educational cloud resource sharing and interaction method under a big data platform provided by embodiments of the present invention.

[0119] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.

[0120] When each module is divided according to its function, the device may also include a signal uploading module, a determination module, and an adjustment module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0121] It should be understood that the apparatus provided in this embodiment of the invention is used to execute the above-described method for sharing and interacting educational cloud resources under the big data platform, and therefore can achieve the same effect as the above-described implementation method.

[0122] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as described in this disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of Digital Signal Processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0123] In addition, the device provided in the embodiments of the present invention may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the educational cloud resource sharing and interaction method under the big data platform provided in the above embodiments.

[0124] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the educational cloud resource sharing and interaction method under the big data platform provided in the above embodiments.

[0125] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to realize the educational cloud resource sharing and interaction method under the big data platform provided in the above embodiments.

[0126] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.

[0127] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0128] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0129] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0130] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0131] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A method for sharing and interacting educational cloud resources under a big data platform, characterized in that, The method includes the following steps: The system acquires knowledge points from teachers' traditional teaching, work steps from job orders uploaded by enterprises, and IPDICE forms uploaded by students. Each work step is matched with a corresponding knowledge point and multiple IPDICE forms representing various student abilities. The IPDICE forms include information forms, planning forms, decision forms, implementation forms, inspection forms, and evaluation forms. Based on the number of IPDICE forms corresponding to each work step, the form abandonment rate, and the form completion time, the fineness of the work step division is determined, and the work steps are divided into coarse-precision steps and fine-precision steps. Coarse-precision steps and fine-precision steps are then removed from the work steps. Based on the granularity of segmentation, the correlation of abilities, and the fluctuation of form scores, the changing trends of students' different abilities under different knowledge points are determined; based on students' access to different work processes, the employment preference index of students for different work processes is determined; based on students' employment preference index and the changing trends of different abilities, the degree of demand for students' different abilities under different knowledge points is determined; and relevant educational cloud resources are pushed to students according to the order of the degree of demand.

2. The method for sharing and interacting educational cloud resources under a big data platform according to claim 1, characterized in that, The method for matching work processes and knowledge points is as follows: Based on the work steps in the job orders uploaded by the enterprise, a logic tree is constructed as the work logic tree; based on the knowledge points in the traditional teaching of teachers, a logic tree is constructed as the knowledge logic tree; wherein, the nodes in the work logic tree are work steps, and the nodes in the knowledge logic tree are knowledge points. Taking any node corresponding to a work step in the work logic tree as the target node, calculate the cosine similarity between the word vector of the target node and the word vector of any node in the knowledge logic tree, as the first similarity; and calculate the cosine similarity between the word vector of the target node and the parent node corresponding to the node in the knowledge logic tree, as the second similarity; take the average of the first and second similarities as the similarity representation value of the target node; and match the target node with the node corresponding to the maximum value of the similarity representation value in the knowledge logic tree.

3. The method for sharing and interacting educational cloud resources under a big data platform according to claim 1, characterized in that, The granularity of work step division is determined based on the number of IPDICE forms corresponding to each work step, the form abandonment rate, and the form completion time, including: The percentage of unanswered questions in all forms corresponding to each work stage is used as the unanswered rate. Obtain the percentage of form completion time for the current work stage in the total form completion time for all work stages, as the time percentage; obtain the variance of the completion time for each question in the form for the current work stage, as the variance; calculate the product of the time percentage and the variance as a time reference value. Get the number of times the form corresponding to each work step was modified during the filling process; The product of the abandonment rate, the reference value of the duration, and the number of revisions is used as the precision of the work process division.

4. The method for sharing and interacting educational cloud resources under a big data platform according to claim 1, characterized in that, The process of dividing the work into coarse-precision stages and fine-precision stages includes: Work steps with a normalized division precision greater than the preset division range are marked as fine precision steps; work steps with a normalized division precision less than the preset division range are marked as coarse precision steps.

5. The method for sharing and interacting educational cloud resources under a big data platform according to claim 1, characterized in that, The method for determining the changing trends of students' different abilities under different knowledge points based on the granularity of segmentation, the correlation of abilities, and the degree of fluctuation in form scores includes: Use any kind of knowledge point as the target knowledge point, any kind of ability as the target ability, and the IPDICE form corresponding to the target ability as the target form. The average score of the work ability of the target form corresponding to the target knowledge point in the knowledge logic tree within a single detection period is taken as the execution ability score of the target knowledge point in a single detection period. For the target knowledge point, obtain the first-order difference sequence of the execution ability score of the target ability in all testing periods, and use it as the ability difference sequence of the student's target ability under the target knowledge point; For a target knowledge point, the average of the Pearson correlation coefficients between the ability difference sequence of the target ability and the ability difference sequences of other abilities besides the target ability is used as the ability correlation coefficient of the student's target ability under the target knowledge point. By combining the granularity of the segmentation, the ability correlation coefficient, and the size of the elements in the ability difference sequence, the changing trend of students' target abilities under the target knowledge points can be determined.

6. The method for sharing and interacting educational cloud resources under a big data platform according to claim 5, characterized in that, The method of determining the changing trend of students' target abilities under the target knowledge point by combining the fineness of segmentation, ability correlation coefficient, and the size of the elements in the ability difference sequence includes: The mean of the fineness of the division of all work steps corresponding to the student's target ability under the target knowledge point is denoted as the fine mean. The absolute value of the mean of the elements in the ability difference sequence of students' target abilities under the target knowledge points is denoted as the fluctuation amplitude. The percentage of elements in the ability difference sequence of students' target abilities under the target knowledge points that take negative values ​​is denoted as the decay percentage. The product of the fine mean of the target ability, the ability correlation coefficient, the fluctuation amplitude, and the attenuation ratio is used as the trend of the student's target ability under the target knowledge point.

7. The method for sharing and interacting educational cloud resources under a big data platform according to claim 1, characterized in that, The method of determining the demand for different abilities of students under different knowledge points based on students' employment preference index and the changing trends of different abilities includes: Using any ability as the target ability, the changing trend of the target ability of the target knowledge point is processed by first-order difference in chronological order to obtain the changing trend difference sequence. The proportion of the number of elements with positive values ​​in the changing trend difference sequence is used as the effective unstable growth proportion of the target ability of the target knowledge point. By combining the employment preference index, the proportion of effective unstable growth, and the element size of the trend difference sequence, the degree of demand for students' target abilities under the target knowledge points can be determined; among them, the employment preference index, the proportion of effective unstable growth, and the element size of the trend difference sequence are all positively correlated with the degree of demand.

8. The method for sharing and interacting educational cloud resources under a big data platform according to claim 1, characterized in that, The determination of students' employment preference indices for different job stages based on their access to different job stages includes: Using any knowledge point as the target knowledge point, calculate the product of the student's recent access index in the work process corresponding to the target knowledge point, the student's interaction frequency with other users on the relevant pages of the work process corresponding to the target knowledge point, and the percentage of time the student spends on the relevant pages of the work process corresponding to the target knowledge point. This product is used as the student's employment preference index for the work process corresponding to the target knowledge point.

9. The method for sharing and interacting educational cloud resources under a big data platform according to claim 8, characterized in that, The method for obtaining the student's recent access index in the work process corresponding to the target knowledge point is as follows: For the target knowledge point, obtain the number of times the student fills out the corresponding IPDICE form in the work process; For the target knowledge point, obtain the time interval between each two consecutive times that a student fills out the corresponding IPDICE form for each work step; The ratio of the number of times a student fills out a form to the interval between forms is used as the student's recent access index for the work process corresponding to the target knowledge point.

10. An educational cloud resource sharing and interaction system based on a big data platform, characterized in that, The system includes the following modules: The data acquisition module is used to acquire knowledge points from teachers' traditional teaching, work steps from job orders uploaded by enterprises, and IPDICE forms uploaded by students. Each work step is matched with a corresponding knowledge point and multiple IPDICE forms representing various student abilities. The IPDICE forms include information forms, planning forms, decision forms, implementation forms, inspection forms, and evaluation forms. The process segmentation module is used to determine the fineness of the process segmentation based on the number of IPDICE forms corresponding to the process segment, the form abandonment rate, and the form filling time. The process segmentation is divided into coarse-precision process segment and fine-precision process segment, and then the coarse-precision process segment and fine-precision process segment are deleted from the process segment. The resource recommendation module is used to determine the changing trends of students' different abilities under different knowledge points based on the granularity of segmentation, ability relevance, and the degree of fluctuation of form scores; to determine students' employment preference index for different work stages based on students' access to different work stages; to determine the degree of demand for different abilities under different knowledge points based on students' employment preference index and the changing trends of different abilities; and to recommend relevant educational cloud resources to students in order of the degree of demand.

Images