A teaching management method and system for a smart teaching platform

Abstract

The application discloses a kind of teaching management method and system for wisdom teaching platform, it is related to education big data technical field, including management center, the management center is connected with teaching acquisition module, course processing module, process analysis module and multi-source coordination module;Acquire courseware original text information and transform into courseware original text data chain;Courseware original text data chain is encrypted combination, obtains secret courseware data chain, sets up flow extraction function to courseware original text information and carries out feature conversion, obtains key data stream section, sets up and inputs the homogeneity conversion of reserve search feature word, obtains reserve search feature data stream section;According to the key data stream section of secret courseware data chain of reserve search feature data stream section is adapted comparison, obtains representative similarity node, according to representative similarity node carries out optimization learning to secret courseware data chain, obtains response learning record;Optimize teaching management process, protect courseware resources, improve search efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of educational big data, and particularly relates to a teaching management method and system for a smart teaching platform. BACKGROUND

[0002] In the field of education today, with the rapid development of information technology, the traditional teaching mode is facing many challenges, and the smart teaching platform emerges as the times require. The smart teaching platform can improve the teaching quality and efficiency by means of advanced technical means, and meet the diversified needs of modern education.

[0003] However, the prior art still has some deficiencies. The accuracy of teaching resource matching of some smart teaching platforms needs to be improved. The personalized teaching resource matching and learning training mode adjustment cannot be fully combined with the physical fitness, theoretical knowledge evaluation and other aspects of the students. In addition, the interactivity and convenience of teaching management need to be further optimized to better meet the needs of teachers, students, parents and other different roles. Therefore, the present application provides a teaching management method and system for a smart teaching platform, which improves the teaching quality and management efficiency by means of accurate resource allocation, comprehensive process monitoring, scientific evaluation system and intelligent retrieval matching, and promotes the development of smart education. SUMMARY

[0004] The purpose of the present application is to provide a teaching management method and system for a smart teaching platform.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] A teaching management system for a smart teaching platform, comprising a management center, the management center being connected with a teaching collection module, a course processing module, a process analysis module and a multi-source collaboration module;

[0007] The teaching collection module is used for collecting courseware original text information, marking the data creator, and converting the courseware original text information to obtain a courseware original data chain;

[0008] The course processing module is used for extracting and encrypting the courseware original data chain to obtain a keyword content segment and a hidden courseware data chain, performing data conversion on the keyword content segment to obtain a key segment coefficient, setting a flow extraction function and performing conversion segmentation to obtain a flow extraction segment;

[0009] The process analysis module is used for performing characteristic strengthening on the key segment coefficient according to the flow extraction segment to obtain a key data flow segment, setting a preliminary retrieval end, performing homogenous conversion on the input preliminary retrieval characteristic word through the preliminary retrieval end to obtain a preliminary retrieval characteristic data flow segment;

[0010] The multi-source collaborative module is used for adaptive comparison of the hidden encrypted courseware data chain according to the backup feature data stream segment, obtaining a representative similarity node, generating a similar hidden encrypted courseware sequence according to the representative similarity node, setting a hidden encrypted decoding port to optimize learning of the similar hidden encrypted courseware sequence, and obtaining a response learning record.

[0011] Preferably, the process of obtaining the courseware original text data chain comprises:

[0012] Data collection is performed on the intelligent teaching platform to obtain courseware original text information.

[0013] The obtained courseware original text information is marked based on the intelligent teaching platform to obtain a material creator.

[0014] The obtained courseware original text information is combined in form to obtain a courseware original text data chain.

[0015] Preferably, the process of obtaining the keyword content segment and the hidden encrypted courseware data chain comprises:

[0016] Core extraction is performed on the courseware original text data chain based on the material creator to obtain a keyword content segment.

[0017] The keyword content segment is sorted based on the order of core extraction to obtain a key segment sequence.

[0018] The courseware original text data chain is collected and encrypted to obtain a hidden encrypted courseware data chain, and the hidden encrypted courseware data chain is selected based on the courseware original text data chain to obtain an interactive learning node.

[0019] The obtained key segment sequence is uploaded to the interactive learning node of the corresponding hidden encrypted courseware data chain in the order of node selection.

[0020] Preferably, the process of obtaining the flow extraction segment comprises:

[0021] Data conversion is performed on the keyword content segment based on the key segment sequence to obtain a key segment coefficient.

[0022] A flow extraction function is set, wave variation adjustment is performed on the flow extraction function to obtain a collection parameter, and a segmentation parameter is obtained according to the obtained collection parameter.

[0023] The flow extraction function is segmented in equal amounts according to the obtained segmentation parameter to obtain a flow extraction segment.

[0024] Preferably, the process of performing characteristic enhancement on the key segment coefficient according to the flow extraction segment comprises:

[0025] The flow extraction segment is uploaded to the key segment coefficient, and the key segment coefficient is homogenized and extracted through the flow extraction segment to obtain a flow key coefficient.

[0026] The flow key coefficient is subjected to coefficient extraction to obtain an integrated coefficient maximum value, and the flow key coefficient is integrated by adding the integrated coefficient maximum value to obtain a strengthened key section base;

[0027] The obtained strengthened key section base is subjected to value assignment conversion to obtain a key data flow section.

[0028] Preferably, the process of obtaining the backup search characteristic data flow section comprises:

[0029] The backup search characteristic word is input through a backup search input end, and the obtained backup search characteristic word is subjected to data conversion to obtain a backup search characteristic coefficient;

[0030] The flow extraction section is obtained, and the backup search characteristic coefficient is subjected to characteristic strengthening according to the flow extraction section to obtain a strengthened backup search section base;

[0031] The obtained strengthened backup search section base is subjected to value assignment conversion to obtain a backup search characteristic data flow section.

[0032] Preferably, the process of comparing and adapting the hidden and secret courseware data chain according to the backup search characteristic data flow section comprises:

[0033] A sample hidden and secret data chain is set according to the hidden and secret courseware data chain, and the obtained backup search characteristic data flow section is uploaded to the sample hidden and secret data chain in the order of the interactive learning nodes;

[0034] The backup search characteristic data flow section is compared with the key data flow section of the interactive learning node of the sample hidden and secret data chain to obtain a flow section similarity;

[0035] The interactive learning node is subjected to traversal screening according to the obtained flow section similarity to obtain a representative similarity node.

[0036] Preferably, the process of preferentially learning the similar hidden and secret courseware sequence by setting a hidden and secret decoding port comprises:

[0037] The hidden and secret courseware data chain is set in rotation until all the hidden and secret courseware data chains are set as sample hidden and secret data chains, the process of comparing and adapting is repeated for each sample hidden and secret data chain, the obtained representative similarity node is sorted to obtain a similar hidden and secret courseware sequence;

[0038] The hidden and secret decoding port is set according to the obtained similar hidden and secret courseware sequence, the similar hidden and secret courseware sequence is uploaded to the hidden and secret decoding port, and a search completion instruction is issued to the student through the hidden and secret decoding port;

[0039] Autonomous learning is performed according to the received search completion instruction, and the autonomous learning process is subjected to time supervision to obtain a response learning record.

[0040] Preferably, the process of temporal supervision of the autonomous learning process comprises:

[0041] According to the preferred condition of the similar hidden courseware sequence, the similar hidden courseware sequence is optimized and pushed through the preferred condition, and the pushed hidden courseware is obtained;

[0042] The obtained pushed hidden courseware is subjected to autonomous learning, and the interactive learning node is subjected to feedback monitoring, and the response learning record is obtained.

[0043] Based on the above-mentioned teaching management system for a smart teaching platform, the present application further provides a teaching management method for a smart teaching platform, comprising the following steps:

[0044] Step one: collect courseware original text information and transform it to obtain courseware original text data chain;

[0045] Step two: extract and encrypt the courseware original text data chain to obtain the key word content segment and the hidden courseware data chain, and transform the key word content segment to obtain the key segment coefficient, set the flow extraction function and transform the segment to obtain the flow extraction segment;

[0046] Step three: according to the flow extraction segment, the key segment coefficient is subjected to characteristic strengthening to obtain the key data flow segment, and the input of the prepared search feature word is subjected to homogenization transformation through the prepared search end to obtain the prepared search feature data flow segment;

[0047] Step four: according to the prepared search feature data flow segment, the hidden courseware data chain is subjected to adaptive comparison to obtain the representative similarity node, the similar hidden courseware sequence is generated according to the representative similarity node, and the similar hidden courseware sequence is subjected to optimal learning through the hidden decoding port to obtain the response learning record.

[0048] Compared with the prior art, the present application has the following advantages:

[0049] 1. Collecting courseware information of the smart teaching platform, extracting the key word content segment, and transforming the courseware information into an encrypted form of hidden courseware data chain can effectively protect the knowledge achievements of teachers and prevent unauthorized copying, dissemination and theft of courseware;

[0050] 2. The extracted key word content segment is subjected to feature integration and transformation into a data flow segment, and the searched prepared search feature word is subjected to the same transformation to obtain the same form of prepared search feature data flow segment, which is beneficial to improve the matching speed and can more efficiently perform matching search, greatly shorten the search time, and accurately locate the hidden courseware data chain related to the key word, thereby improving the accuracy of obtaining the required courseware information;

[0051] 3. By setting up a hidden decoding port, the hidden courseware data chain that is retrieved and matched is monitored and learned, and corresponding learning records are obtained. This ensures that the courseware materials are not known in advance during the learning process, avoids non-course participants from arbitrarily obtaining resources, ensures the fairness of students' access to learning resources, and maintains the teaching order. Attached Figure Description

[0052] To more clearly illustrate the technical solutions 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.

[0053] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0054] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] like Figure 1 As shown, a teaching management system for a smart teaching platform includes a management center, which is connected to a teaching acquisition module, a course processing module, a process analysis module, and a multi-source collaboration module.

[0056] The teaching data acquisition module is used to collect the original information of the courseware, mark the creator of the materials, and transform the original information of the courseware to obtain the original data chain of the courseware.

[0057] The course processing module is used to extract and encrypt the original courseware data chain to obtain keyword content segments and hidden courseware data chains, perform data transformation on the keyword content segments to obtain key segment coefficients, set the flow extraction function and perform transformation segmentation to obtain flow extraction segments.

[0058] The process analysis module is used to enhance the characteristics of key segment coefficients based on the flow extraction segmentation, obtain key data flow segments, set up a pre-retrieval terminal, and perform homogeneous transformation on the input test feature words through the pre-retrieval terminal to obtain test feature data flow segments.

[0059] The multi-source collaborative module is used for adaptive comparison of the hidden and secret courseware data chain according to the backup feature data stream section, obtaining a representative similarity node, generating a similar hidden and secret courseware sequence according to the representative similarity node, setting a hidden and secret decoding port to optimize learning of the similar hidden and secret courseware sequence, and obtaining a response learning record.

[0060] In actual use, although the teaching management of the intelligent teaching platform brings many conveniences and improvements, there are some vulnerabilities that cannot be ignored. Since the intelligent teaching platform stores a large amount of sensitive information, if the security protection measures of the platform are not in place, such as imperfect data encryption technology and vulnerabilities in access control, it is easy to be attacked by hackers, leading to data leakage and potential security risks to teachers and students. Therefore, it is necessary to encrypt and protect the learning materials uploaded by teachers, not to display them randomly, but to push them only to students who need to learn, and to improve the interaction frequency during learning to improve student engagement and increase learning effectiveness.

[0061] The process of collecting courseware original text information through the teaching collection module includes:

[0062] Collecting data of the intelligent teaching platform to obtain courseware original text information;

[0063] The data collection represents collecting learning information uploaded by teachers or management personnel in the intelligent teaching platform, which is the courseware original text information. The courseware original text information represents the data of the learning materials for students, including but not limited to text materials, audio and video materials, and image materials.

[0064] Based on the intelligent teaching platform, the obtained courseware original text information is marked with the uploader to obtain the material creator, and the obtained courseware original text information is associated with the corresponding material creator;

[0065] The uploader marking represents marking the uploader of each courseware original text information, which is the material creator. It represents the author or upload source of the courseware original text information, such as teachers, material authors, and platform management personnel.

[0066] Formally combining the obtained courseware original text information to obtain a courseware original text data chain;

[0067] The form combination represents combining the obtained courseware original text information into a long strip-shaped data chain form. For example, if the courseware original text information is audio and video materials, a long strip-shaped data chain is generated according to the playback duration in the audio and video materials, which is the courseware original text data chain. If the courseware original text information is image materials, the image materials are arranged in order to form a time axis form of image material sequence, which is the courseware original text data chain.

[0068] Further, converting the courseware original text information into a long strip of data chain form is not only conducive to observing the data volume of the courseware original text information, but also can directly obtain the learning progress of students learning the courseware original text information, facilitate encryption of the courseware original text data chain, prevent information from being illegally obtained or stolen during transmission and storage, prevent these materials from being unauthorized copied, spread and used, maintain the legal rights and interests of the creator, encourage the production of more high-quality teaching resources, help prevent some users from over-downloading and spreading materials, avoid platform resources from being abused, and ensure the normal operation of the platform.

[0069] The process of extracting and encrypting the courseware original text data chain includes:

[0070] Based on the core extraction of the courseware original text data chain by the material creator, the keyword content segment is obtained.

[0071] The core extraction means that each courseware original text data chain has corresponding courseware content, and the key feature of the courseware information can be extracted according to the courseware content information, and is recorded as a keyword content segment. For courseware original text data chains with different contents, the corresponding keyword content segments are also different. Therefore, the extracted keyword content segment can represent the characteristics of the corresponding original text data chain, and the required courseware original text data chain can be screened by searching for the matching degree with the keyword content segment.

[0072] Based on the order of core extraction, the obtained keyword content segment is sorted to obtain a key segment sequence.

[0073] Obtain the courseware original text data chain, collect and encrypt the obtained courseware original text data chain, and obtain the hidden courseware data chain.

[0074] The collection and encryption means that the courseware original text data chain is invisibly encrypted, that is, after the operation is completed, the displayed courseware original text data chain is in a secret form, and all personnel in the intelligent teaching platform cannot view the detailed content of the courseware original text data chain. The invisible encryption operation means that the courseware original text data chain is hidden so that all personnel cannot clearly see the detailed material content, for example, the courseware original text data chain is processed by mosaic, and is processed into ciphertext form by using an encryption algorithm.

[0075] Based on the courseware original text data chain, the obtained hidden courseware data chain is selected to obtain an interactive learning node.

[0076] The node selection represents that the node for interaction with the student is set by the courseware author according to the courseware original data chain, that is, an interactive learning node, and the position of the interactive learning node in the hidden courseware data chain is determined by the courseware author, and the corresponding interactive behavior is set in the interactive learning node, wherein the interactive behavior includes but is not limited to topic discussion, question and answer, topic voting, homework assignment, questionnaire, aims to enable students to improve participation in the learning process, and is no longer one-way remote learning, at the same time, it is convenient for teachers to master the learning progress of students in real time, and is beneficial to arrange more suitable learning tasks for students; in particular, the number of interactive learning nodes is equal to the number of keyword content segments in the corresponding key segment sequence of the hidden courseware data chain;

[0077] The obtained key segment sequence is uploaded to the interactive learning node of the corresponding hidden courseware data chain according to the order of node selection, that is, the keyword content segment is uploaded to each interactive learning node of the hidden courseware data chain;

[0078] Based on the key segment sequence, the obtained keyword content segment is data-converted to obtain a key segment coefficient;

[0079] The data conversion represents that the obtained keyword content segment is converted into a signal form, that is, a key segment coefficient, wherein each keyword content segment of the key segment sequence is data-converted, and then the keyword content segment at each interactive learning node of each hidden courseware data chain is converted into a key segment coefficient;

[0080] A flow extraction function is set, and the flow extraction function is a corresponding wavelet function selected according to the signal characteristics of the key segment coefficient, wherein the wavelet function includes but is not limited to Symlets wavelet and Daubechies wavelet;

[0081] The obtained flow extraction function is wave-converted to obtain a collection parameter;

[0082] The wave conversion represents that the flow extraction function is controlled to be stretched and translated in the time dimension and the frequency dimension, and the interval distance of the stretching and translation is counted to obtain the collection parameter;

[0083] According to the obtained collection parameter, a segmentation parameter is obtained, and the obtained segmentation parameter is marked as FG, wherein, , FG represents the maximum value of the collection parameter in the flow extraction function, FG represents the minimum value of the collection parameter in the flow extraction function, FG represents the average value of the collection parameter in the flow extraction function, " represents the result of calculating " FG " after rounding up, and the obtained segmentation parameter is an integer form;

[0084] According to the obtained segmentation parameter, the flow extraction function is equally segmented to obtain flow extraction segments;

[0085] The equal segmentation means that the flow extraction function is equally length segmented according to the number of segmentation parameters to obtain flow extraction segments of equal length, and the number of obtained flow extraction segments is equal to the number of segmentation parameters.

[0086] The key segment coefficient is obtained, the key segment coefficient is enhanced in characteristics according to the obtained flow extraction segments, and the enhanced key segment base is obtained.

[0087] It needs to be further explained that in the specific implementation process, the process of characteristic enhancement includes:

[0088] The obtained flow extraction segments are uploaded to the key segment coefficient based on the order of equal segmentation, the obtained flow extraction segments are uniformly extracted with the key segment coefficient, and the flow key coefficient is obtained.

[0089] The uniform extraction mark convolves the elements of the flow extraction segment and the key segment coefficient to obtain the flow key coefficient, and according to the order of equal segmentation, the flow extraction segment and the key segment coefficient are uniformly extracted in sequence to obtain the flow key coefficient corresponding to each flow extraction segment.

[0090] The obtained flow key coefficient is coefficient extracted to obtain the integrated coefficient maximum value, and the integrated coefficient maximum value means that the convolution values of the corresponding position elements obtained after the elements of the flow extraction segment and the key segment coefficient are convolved are compared to obtain the maximum value of the convolution in the flow key coefficient, that is, the integrated coefficient maximum value.

[0091] The obtained flow key coefficient is integrated according to the obtained integrated coefficient maximum value to obtain the enhanced key segment base.

[0092] The integrated coefficient maximum value means that the average value of the obtained integrated coefficient maximum value is obtained, the center integrated coefficient value is obtained, the obtained flow key coefficient is summed based on the key segment coefficient to obtain the comprehensive key segment base, and the comprehensive key segment base is enhanced according to the obtained center integrated coefficient value to obtain the enhanced key segment base, wherein the enhanced key segment base = center integrated coefficient value x comprehensive key segment base.

[0093] Further, the key word content segment at each interactive learning node on the hidden course data chain is feature transformed to obtain the corresponding enhanced key segment base, the specific information of the key word content segment cannot be directly observed, the knowledge achievements of the material creator are effectively protected, and the quality and pertinence of the learning materials are guaranteed.

[0094] The obtained enhanced key segment base is assigned and transformed to obtain the key data flow segment.

[0095] The assignment transformation represents the conversion of the obtained reinforced key segment base into a data stream composed of binary symbols, and the encoding rule of the transformation is the same, then for each interactive learning node of the hidden courseware data chain, the reinforced key segment base after the key word content segment feature extraction has a transformed key data stream segment, which is used to match the student's learning materials needed by comparing the search key words searched by the students;

[0096] In particular, after obtaining the key data stream segment, all the interactive learning nodes of the hidden courseware data chain inserted into the key word content segment are in the form of key data stream segment;

[0097] A preliminary search end is provided, which is used to provide a material search port for students and teachers, and the feature key word content that wants to learn or publish learning tasks is input into the preliminary search end to search for the adapted courseware materials;

[0098] In particular, the preliminary search end can receive multiple feature key word contents, since there are multiple key word content segments in a courseware material, the student may input one or two most critical ones when searching, in order to improve the success rate of search matching, the number of input feature key words needs to be increased to improve the matching degree, and find the courseware materials most needed by students or teachers;

[0099] The input search feature word is input through the preliminary search end;

[0100] Further, the input search feature word can be the key content information of the courseware that the student wants to learn, or the key word of the courseware material that matches the search task when the teacher publishes the learning task, for example, if the student wants to learn the content related to the quadratic equation, the input search feature word can be "quadratic equation", and if the teacher wants to publish the courseware material related to the judgment of straight line, plane parallel and its properties in the problem of spatial geometry, the search feature word can be "straight line, plane parallel judgment and its properties";

[0101] The obtained search feature word is data-converted to obtain a search feature coefficient;

[0102] The data conversion means that the obtained search feature word is converted into a signal form, and since there can be more than one search feature word, all the obtained search feature coefficients are data-converted to obtain a search feature coefficient;

[0103] The obtained search feature coefficient is homogenized to obtain a search feature data stream segment;

[0104] It needs to be further explained that in the specific implementation process, the homogenization transformation process includes:

[0105] obtaining a flow extraction segment, performing characteristic enhancement on the obtained flow extraction segment, and obtaining an enhanced search feature segment;

[0106] performing value assignment transformation on the obtained enhanced search feature segment, and obtaining a search feature data stream segment;

[0107] In particular, the search content is converted into the same data form as the courseware keywords, which is conducive to protecting courseware resources, preventing unauthorized copying, dissemination and theft of courseware, and ensuring that teachers' knowledge achievements are not leaked. At the same time, the keywords and search terms are converted into binary code data stream form, and the ability of computers to quickly process binary data can be used to more efficiently perform matching searches, greatly shorten the search time, and accurately locate the relevant hidden courseware, thereby improving the accuracy of obtaining the required courseware materials.

[0108] Based on the obtained search feature data stream segment, the hidden courseware data chain is adapted and compared on the wisdom teaching platform to obtain a similarity node;

[0109] It should be further explained that in the specific implementation process, the keyword content segment of the interactive learning node of the hidden courseware data chain in the wisdom teaching platform is in the form of binary code data stream, which is the same as the data form of the search feature data stream segment and can be matched. The process of the adaptive comparison includes:

[0110] According to the obtained hidden courseware data chain, a sample hidden data chain is set, and the obtained search feature data stream segment is uploaded to the sample hidden data chain in the order of the interactive learning nodes;

[0111] The sample hidden data chain indicates that in the wisdom learning platform, an optional hidden courseware data chain is recorded as a sample hidden data chain. After comparing the search feature data stream segment with the sample hidden data chain, the sample hidden data chain is replaced, and an optional one of the remaining hidden courseware data chains is recorded as a sample hidden data chain, until all the hidden courseware data chains are selected as sample hidden data chains.

[0112] The obtained search feature data stream segment is compared with the first interactive learning node of the sample hidden data chain to obtain a stream segment similarity;

[0113] The process of the stream segment comparison includes:

[0114] aligning the first binary symbol of the first segment of the candidate characteristic data stream with the first binary symbol of the key data stream of the interactive learning node, and comparing whether the binary symbols at the same position are identical, if the binary symbols at the same position are identical, marking the position element as 0, otherwise, marking the position element as 1, until the binary symbols at all positions are compared, obtaining a binary string, and marking the binary string as a same position judgment code;

[0115] obtaining the stream segment similarity according to the obtained same position judgment code, wherein the stream segment similarity represents the number of 0s in the same position judgment code, and the more the number of 0s, the higher the similarity of the two data stream segments; in particular, if the number of binary symbols of the candidate characteristic data stream and the number of binary symbols of the key data stream are not identical, the comparison ends at the binary symbol with the shorter number of bits;

[0116] comparing the obtained candidate characteristic data stream with the second interactive learning node of the sample secret data chain, obtaining the stream segment similarity, until the stream segment comparison with the last interactive learning node of the sample secret data chain is completed, and the obtained stream segment similarity is counted;

[0117] performing traversal screening on the interactive learning nodes according to the obtained stream segment similarity, and obtaining a representative similarity node;

[0118] The traversal screening means that the obtained stream segment similarity is sorted in descending order, and the interactive learning node corresponding to the stream segment similarity with the first sorting is marked as the representative similarity node, that is, the highest similarity interactive learning node in the sample secret data chain is selected as the representative, which represents the maximum similarity point between the sample secret data chain and the candidate characteristic data stream;

[0119] performing rotation setting on the remaining secret courseware data chains until all the secret courseware data chains are set as sample secret data chains, repeating the adaptive comparison process for each sample secret data chain, and sorting the obtained representative similarity nodes in descending order to obtain a similar secret courseware sequence, and marking the keyword content segment at the interactive learning node position of the secret courseware data chain of the similar secret courseware sequence, that is, the interactive learning node of each secret courseware data chain of the similar secret courseware sequence displays the keyword content segment instead of the transformed key data stream, so that the searcher can directly obtain the main content of the secret courseware data chain, and it is convenient to select the secret courseware data chain to be learned;

[0120] The rotation setting means that the remaining hidden course data chain is sequentially set as a sample hidden data chain, and the process of repeated adaptive comparison is performed on each set sample hidden data chain, the representative similarity node corresponding to each hidden course data chain is found, and then the hidden course data chain corresponding to the representative similarity node is sorted according to the similarity, to obtain a similar hidden course sequence, which represents the similarity of the hidden course data chain to the test characteristic word.

[0121] In particular, each search can obtain a similar hidden course sequence. If the input test characteristic word is greater than or equal to two during the sequential search process, the number of test characteristic data stream segments to be compared is also greater than or equal to two, then in the adaptive comparison process, the first test characteristic data stream segment is compared with the sample hidden data chain first to obtain a stream segment similarity, and then the second test characteristic data stream segment is compared with the sample hidden data chain to obtain a stream segment similarity, the two stream segment similarities are added to obtain a comprehensive similarity, and the maximum comprehensive similarity is selected from the sample hidden data chain as the stream segment similarity representing the sample hidden data chain, and then sorted to obtain the similar hidden course sequence of this search.

[0122] According to the obtained similar hidden course sequence, a hidden decoding port is set, which is used to decrypt the hidden course data chain in the similar hidden course sequence and provide a port for students to learn. In this hidden decoding port, the hidden course data chain is not directly decrypted once, but is decrypted in real time following the learning progress of the students, that is, the hidden decoding port opens the hidden course data chain to which position the students have learned to which position, and the position which has not been learned still maintains the hidden state and cannot display detailed data content, and the course data can still be protected in real time.

[0123] The obtained similar hidden course sequence is uploaded to the hidden decoding port, and a search completion instruction is sent to the students through the hidden decoding port;

[0124] According to the received search completion instruction, autonomous learning is performed, and a time state supervision is performed on the autonomous learning process to obtain a response learning record.

[0125] It needs to be further explained that in the specific implementation process, the time state supervision process includes:

[0126] According to the obtained similar hidden course sequence, an optimization condition is set, the similar hidden course sequence is optimized and pushed through the optimization condition, and a pushed hidden course is obtained.

[0127] The preferred condition is to determine the secret courseware data chain that needs to be learned in the similar secret courseware sequence, and determine the secret courseware data chain that needs to be learned or the learning task that needs to be arranged by the teacher according to the keyword content segment corresponding to the interactive learning node of the secret courseware data chain; for example, after the student retrieves the similar secret courseware sequence, the top three secret courseware data chains are determined as the courseware data required for retrieval through the keyword content segment at the interactive learning node, and then the three secret courseware data chains are recorded as the pushed secret courseware.

[0128] Autonomous learning is performed on the obtained pushed secret courseware, and feedback monitoring is performed on the interactive learning node to obtain response learning records.

[0129] The autonomous learning means that the pushed secret courseware is uploaded to a secret decoding port, the student learns the received pushed secret courseware, and performs real-time decryption through the secret decoding port, sequentially plays and learns according to the data chain form of the pushed secret courseware, answers the interactive behavior set by the interactive learning node, records the content of the answered interactive behavior, and generates response learning records. The response learning records represent all learning behaviors of the student during the learning of the pushed secret courseware, the learning situation of the interactive learning node, the learning time, the learning problem message, and the self-evaluation of the courseware learning situation, so as to master the learning state of the student, provide more accurate help, adjust the teaching strategy, realize precise teaching, and enable the student to more clearly understand his own learning situation by self-evaluating the completion of the pushed secret courseware, thereby adjusting the learning method and rhythm and improving the autonomous learning consciousness and ability.

[0130] Based on the above-mentioned teaching management system for a smart teaching platform, the present application further provides a teaching management method for a smart teaching platform, comprising the following steps:

[0131] Step one: collect courseware original text information and perform transformation to obtain a courseware original text data chain;

[0132] Step two: extract and encrypt the courseware original text data chain to obtain a keyword content segment and a secret courseware data chain, perform data transformation on the keyword content segment to obtain a key segment coefficient, set a flow extraction function and perform transformation segmentation to obtain a flow extraction segment;

[0133] Step three: perform characteristic strengthening on the key segment coefficient according to the flow extraction segment to obtain a key data flow segment, set a preliminary retrieval end to perform homogenization transformation on the input preliminary retrieval characteristic word to obtain a preliminary retrieval characteristic data flow segment;

[0134] Step four: according to the check feature data stream section, the hidden encryption course data chain is compared and adapted, the representative similarity node is obtained, the similar hidden encryption course sequence is generated according to the representative similarity node, the similar hidden encryption course sequence is optimized and learned by setting the hidden encryption decoding port, and the response learning record is obtained.

[0135] The preferred embodiments of the application disclosed above are only used to help explain the application. The preferred embodiments do not describe all the details and limit the application to the specific embodiments. Obviously, many modifications and variations can be made according to the content of the specification. The specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited by the claims and their full scope and equivalents.

Claims

1. A teaching management system for a smart teaching platform, comprising a management center, characterized in that, The management center is connected with a teaching collection module, a course processing module, a process analysis module and a multi-source coordination module; The teaching collection module is used for collecting courseware original text information, marking data creators and transforming the courseware original text information to obtain a courseware original data chain; The course processing module is used for extracting and encrypting the courseware original data chain to obtain a keyword content segment and a secret courseware data chain, and the process includes: extracting the courseware original data chain based on the data creators to obtain the keyword content segment; sorting the keyword content segment based on the order of the core extraction to obtain a key segment sequence; collecting and encrypting the courseware original data chain to obtain a secret courseware data chain, and selecting nodes of the secret courseware data chain based on the courseware original data chain to obtain an interactive learning node; uploading the obtained key segment sequence to the interactive learning node of the corresponding secret courseware data chain in the order of the node selection; transforming the keyword content segment to obtain a key segment coefficient, setting a flow extraction function and transforming the segment to obtain a flow extraction segment; the process of obtaining the flow extraction segment includes: transforming the keyword content segment based on the key segment sequence to obtain the key segment coefficient; setting the flow extraction function, adjusting the flow extraction function, obtaining collection parameters, and obtaining a segmentation parameter based on the obtained collection parameters; segmenting the flow extraction function based on the obtained segmentation parameter to obtain the flow extraction segment; The process analysis module is used for strengthening the characteristics of the key segment coefficient based on the flow extraction segment to obtain a key data flow segment; the process of strengthening the characteristics of the key segment coefficient based on the flow extraction segment includes: uploading the flow extraction segment to the key segment coefficient, homogenizing the key segment coefficient through the flow extraction segment to obtain a flow key coefficient; extracting the flow key coefficient to obtain an integrated coefficient maximum value, integrating the flow key coefficient based on the integrated coefficient maximum value to obtain a strengthened key segment base number; assigning and transforming the obtained strengthened key segment base number to obtain the key data flow segment; setting a preliminary retrieval end, homogenizing the input preliminary retrieval characteristic word through the preliminary retrieval end to obtain a preliminary retrieval characteristic data flow segment; The multi-source coordination module is used for adapting and comparing the secret courseware data chain based on the preliminary retrieval characteristic data flow segment to obtain a representative similarity node, generating a similar secret courseware sequence based on the representative similarity node, and optimizing learning of the similar secret courseware sequence through a secret decoding port to obtain a response learning record.

2. The teaching management system for the smart teaching platform according to claim 1, wherein, The process of obtaining the courseware original data chain includes: collecting data on the intelligent teaching platform to obtain courseware original information; marking the obtained courseware original information based on the intelligent teaching platform to obtain data creators; formally combining the obtained courseware original information to obtain a courseware original data chain.

3. The teaching management system for the smart teaching platform as claimed in claim 1, wherein, The process of obtaining the preliminary retrieval characteristic data flow segment includes: inputting the preliminary retrieval characteristic word through the preliminary retrieval end, transforming the obtained preliminary retrieval characteristic word to obtain a preliminary retrieval characteristic coefficient; obtaining a flow extraction segment, and strengthening the characteristics of the preliminary retrieval characteristic coefficient based on the flow extraction segment to obtain a strengthened preliminary retrieval segment base number; The obtained reinforced pre-examination base is valued and converted to obtain a pre-examination characteristic data stream section.

4. The teaching management system for the smart teaching platform according to claim 3, wherein, The process of adapting and comparing the hidden course data chain according to the pre-examination characteristic data stream section comprises: According to the hidden course data chain, a sample hidden data chain is set, and the obtained pre-examination characteristic data stream section is uploaded to the sample hidden data chain according to the order of the interactive learning nodes. The pre-examination characteristic data stream section is compared with the key data stream section of the interactive learning node of the sample hidden data chain, and the stream section similarity is obtained. According to the obtained stream section similarity, the interactive learning nodes are traversed and screened to obtain representative similarity nodes.

5. The teaching management system for the smart teaching platform as claimed in claim 1, wherein, The process of optimizing and learning the similar hidden course sequence by setting the hidden decoding port comprises: The hidden course data chain is set in rotation until all the hidden course data chains are set as sample hidden data chains. For each sample hidden data chain, the process of adapting and comparing is repeated, the representative similarity nodes are sorted, and the similar hidden course sequence is obtained. According to the obtained similar hidden course sequence, the hidden decoding port is set, the similar hidden course sequence is uploaded to the hidden decoding port, and the student is instructed to complete the search through the hidden decoding port. According to the received search completion instruction, autonomous learning is carried out, the process of autonomous learning is time-regulated, and response learning records are obtained.

6. The teaching management system for the smart teaching platform according to claim 5, wherein, The process of time-regulating the autonomous learning process comprises: According to the similar hidden course sequence, an optimization condition is set, the similar hidden course sequence is optimized and pushed through the optimization condition, and a pushed hidden course is obtained. The obtained pushed hidden course is autonomously learned, and the interactive learning nodes are feedback monitored to obtain response learning records.

7. The teaching management method of the teaching management system for the smart teaching platform according to any one of claims 1 to 6, characterized in that, The method comprises the following steps: Step 1: Collect course original text information and convert it to obtain a course original text data chain; Step 2: Extract and encrypt the course original text data chain to obtain a keyword content section and a hidden course data chain. Data conversion is performed on the keyword content section to obtain a key section coefficient. A flow extraction function is set and converted to obtain a flow extraction section; Step 3: According to the flow extraction section, the key section coefficient is characterized and reinforced to obtain a key data stream section. A pre-examination retrieval port is set to homogenously convert the input pre-examination characteristic words to obtain a pre-examination characteristic data stream section; Step 4: Adapt and compare the hidden course data chain according to the pre-examination characteristic data stream section to obtain representative similarity nodes. The representative similarity nodes are used to generate a similar hidden course sequence, and the similar hidden course sequence is optimized and learned by setting a hidden decoding port to obtain response learning records.

Images