WO2022042149A1 - 适合omo学习场景的智适应作业系统 - Google Patents

适合omo学习场景的智适应作业系统 Download PDF

Info

Publication number
WO2022042149A1
WO2022042149A1 PCT/CN2021/107812 CN2021107812W WO2022042149A1 WO 2022042149 A1 WO2022042149 A1 WO 2022042149A1 CN 2021107812 W CN2021107812 W CN 2021107812W WO 2022042149 A1 WO2022042149 A1 WO 2022042149A1
Authority
WO
WIPO (PCT)
Prior art keywords
homework
data
module
learning
unit
Prior art date
Application number
PCT/CN2021/107812
Other languages
English (en)
French (fr)
Inventor
王鑫
许昭慧
Original Assignee
上海松鼠课堂人工智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海松鼠课堂人工智能科技有限公司 filed Critical 上海松鼠课堂人工智能科技有限公司
Priority to DE212021000416.4U priority Critical patent/DE212021000416U1/de
Publication of WO2022042149A1 publication Critical patent/WO2022042149A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
    • G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
    • H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications

Definitions

  • the present application relates to the field of intelligent education technology, for example, to an intelligent adaptive operating system suitable for online and offline (Online Merge Offline, OMO) learning scenarios.
  • OMO Online Merge Offline
  • OMO learning scenarios refer to the comprehensive integration of online learning scenarios and offline learning scenarios, so that online and offline learning data are integrated into an ecosystem.
  • OMO learning scenarios for example: 1) Students pass the online and offline classes Teachers learn face-to-face teaching, and put part of the learning process online, for example: students complete homework through the online learning platform after class, teachers can give feedback on students' online homework in offline classrooms, 2) dual-teacher classroom model It is an online lecture given by a famous teaching teacher, and at the same time, there are offline tutors in the classroom to do homework correction, answering questions, supervising and other services.
  • the present application provides an intelligent adaptive homework system suitable for OMO learning scenarios, which can open up the isolated state of online and offline learning data, integrate data in the entire teaching and learning process, and help improve the matching degree of intelligently recommended homework.
  • the present application provides an intelligent adaptive operation system suitable for OMO learning scenarios, including: a field device and a remote server;
  • the field device includes a collection unit, a device used by teacher objects, and a device used by student objects;
  • the remote server includes a resource module , recommended modules, storage modules and layout modules;
  • the collection unit is configured to collect offline and/or online classroom learning status data of the student object, and upload the collected classroom learning status data to the recommendation module;
  • the device used by the teacher object includes a publishing unit, the publishing unit is configured to receive the homework task sequence sent by the recommendation module, and modify the received homework according to the selection operation of the received homework task sequence by the teacher object. at least one of a task sequence and a generated homework task sequence, and send a homework task confirmation signal to the arrangement module according to the teacher object's confirmation operation on the homework task in the selected homework task list;
  • the device used by the student object includes a submission unit, and the submission unit is configured to receive homework tasks completed by the student object, and submit the obtained homework results online;
  • the resource module is configured to store learning resources, wherein the learning resources include homework resources, test question analysis and explanation screen recording;
  • the recommendation module is configured to output the homework task sequence according to the received classroom learning state data in the collection unit and some or all of the data in the scene data in the storage module, and send the output homework task sequence to the publishing unit for confirmation by the teacher object;
  • the arrangement module is configured to, after receiving the homework task confirmation signal, determine the confirmed homework task according to the homework task confirmation signal, retrieve the learning resource corresponding to the confirmed homework task from the resource module, and transfer the learning resource corresponding to the confirmed homework task. remote feedback of the acquired learning resources to the device used by the student object;
  • the storage module is configured to record the scene data generated in the teaching scene and the homework scene, wherein the scene data includes the behavior data of the teacher object in the teaching situation, and the teacher object's behavior data in the case of explaining the homework. Behavior data, track data of the student object's homework tutoring by the parent object, and human-computer interaction data of the student object in the submission unit.
  • FIG. 1 is a block diagram of a system architecture provided by an embodiment of the present application.
  • FIG. 2 is a block diagram of a system architecture when a recommendation module acts as provided in an embodiment of the present application
  • FIG. 3 is a block diagram of a system architecture provided by an embodiment of the present application when a job assistant functions.
  • 100-field device 101-collection unit; 102-release unit; 103-submission unit; 104-instruction unit; 105-job assistant; 106-upload unit;
  • 200-remote server 201-resource module; 202-recommendation module; 203-arrangement module; 204-storage module;
  • the intelligent adaptive operation system for OMO learning scenarios includes: a field device and a remote server; the field device includes a collection unit, a device used by teacher objects, and a device used by student objects; the remote server includes a resource module , a recommendation module, a storage module and an arrangement module; the collection unit is configured to collect at least one of the offline classroom learning status data and online classroom learning status data of the student object, and collect the collected classroom learning status data.
  • the data is uploaded to the recommendation module;
  • the device used by the teacher object includes a release unit, and the release unit is configured to receive the homework task sequence sent by the recommendation module, according to the teacher object's selection of the received homework task sequence
  • the operation executes at least one of modifying the received homework task sequence and generating homework task sequence, and sending homework task confirmation to the arrangement module according to the confirmation operation of the teacher object on the homework task in the selected homework task list signal;
  • the device used by the student object includes a submission unit, the submission unit is configured to receive homework tasks completed by the student object, and submit the obtained homework results online;
  • the resource module is configured to store learning resources , wherein the learning resources include homework resources, test question analysis and explanation screen recording;
  • the recommendation module is set to receive classroom learning status data in the collection unit and/or scene data in the storage module Part of the data or all of the data in, output the homework task sequence, and send the output homework task sequence to the publishing unit for the teacher object to confirm;
  • the arrangement module is set to after receiving the homework task confirmation signal
  • Modifying the received job task sequence includes deleting job tasks in the job task sequence, adding job tasks in the job task sequence, and adjusting the order of job tasks in the job task sequence.
  • the teacher object deletes the homework task in the homework task sequence, it means that the teacher object does not use the deleted homework task in the homework task sequence for homework assignment.
  • the teacher object simply selects some homework tasks in the recommended homework task sequence, or directly accepts all the recommended homework task sequence, or rejects all the recommended homework task sequence.
  • the teacher object confirms the homework task in the selected homework task list, that is, the teacher object determines whether to publish the homework task in the current homework task list to the device used by the student object. If the teacher object does not confirm a homework task, it means that the homework task does not need to be assigned to the student object.
  • the recommendation module is provided with at least one job recommendation algorithm model, and a secondary development interface set to write a new job recommendation algorithm model; the recommendation module is set to receive the collection unit in the following way Classroom learning state data in and/or some or all of the data in the scene data in the storage module, output the homework task sequence: the classroom learning state data in the acquisition unit and/or the data in the storage module Part or all of the data in the scene data is used as the input of the at least one job recommendation algorithm model, and output all the data according to the output result of the at least one job recommendation algorithm model and the labels of the learning resources in the resource module. Describe the job task sequence.
  • the intelligent adaptive operation system suitable for the OMO learning scenario also includes at least one learning resource intelligent recommendation system, and the recommendation module is externally connected to the at least one learning resource intelligent recommendation system; the recommendation module is set to be based on the received The classroom learning state data in the acquisition unit and/or some or all of the data in the scene data in the storage module, output the homework task sequence: the classroom learning state data in the acquisition unit and the storage module Part of the data or all of the data in the scene data is sent to the at least one learning resource intelligent recommendation system, respectively, and the job task sequence is output according to the returned result and the label of the learning resource in the resource module.
  • the device used by the teacher object further includes a homework assistant; the homework assistant is configured to receive a voice homework assignment instruction of the teacher object; the placement module is further configured to assign the voice homework according to the voice homework assignment instruction Assign job tasks corresponding to instructions.
  • the device used by the teacher object further includes an uploading unit, and the remote server further includes a storage module;
  • the uploading unit is configured to receive offline files and upload the offline files to the storage module;
  • the warehousing module is configured to receive offline files from the uploading unit, and convert the format of the received offline files into the warehousing format of the resource module.
  • the remote server further includes a course arrangement module; the course arrangement module is configured to record the date data and attendance data of the student object taking classes, and provide the arrangement module with the date data required by the arrangement module; the The layout module is also configured to retrieve homework resources from the resource module and feed them back to the submission unit remotely, and can simultaneously retrieve the date data corresponding to the homework resources from the class scheduling module and send it to the submission unit. Send the date data corresponding to the completion of the job resource.
  • the arrangement module is further configured to delete the homework task content according to the preset rules and the date data and attendance data of the student object.
  • the homework task pre-assigned to the student object can be deleted.
  • the device used by the teacher object further includes a teaching unit; the teaching unit is configured to enable the object who can tutor the student's homework to explain or guide the student's homework in at least one of online and offline forms.
  • the remote server also includes a learning situation module; the learning situation module is configured to count and analyze the scene data in the storage module, and generate learning situation data, wherein the learning situation data includes student object homework progress data , student object homework completion data, student object weak knowledge point data, class object homework completion rate data, class object homework accuracy ranking and class common error data; the explanation unit is also set to call and view the learning situation The learning situation data generated by the module, and according to the learning situation data, the learning resources are retrieved from the resource module for explanation or tutoring; the collection unit is also set to collect the explanation process data in the explanation process, and collect the The explanation process data is uploaded to the recommendation module; the recommendation module is further configured to, after receiving the explanation process data each time, according to the received explanation process data, the classroom learning status data in the collection unit and/or the Part or all of the data in the scene data in the storage module, and output the job task sequence.
  • the learning situation module is configured to count and analyze the scene data in the storage module, and generate learning situation data, wherein the learning situation data includes student object homework progress
  • the publishing unit is further configured to actively initiate a job task; the arrangement module is further configured to call the corresponding job resource actively initiated by the publishing unit from the resource module for grouping according to the job task actively initiated by the publishing unit. roll.
  • the design data and explanation data of homework assignments can be used both online and offline, so as to achieve the purpose of free conversion of design data and explanation data at any time.
  • the teaching, learning, and practice in this system can be transferred to a new round of teaching.
  • the process forms a complete closed-loop data, so that the learning, practice, and tutoring of the student objects are progressive, which helps to improve the learning efficiency of the student objects.
  • an intelligent adaptive operating system suitable for OMO learning scenarios includes a field device 100 and a remote server 200 ;
  • the remote server 200 includes a resource module 201 , a recommendation module 202 , a storage module 204 and an arrangement Module 203;
  • the field device 100 includes a collection unit 101, a device used by the teacher object, and a device used by the student object;
  • the collection unit 101 is configured to collect the offline and/or online classroom learning status data of the student object, and Upload the collected classroom learning state data to the recommendation module 202 of the remote server 200; when the collection unit 101 collects the offline classroom learning state data, it may be the use of multiple types of sensors, cameras, brain rings, wristbands, handwriting Devices such as boards, smart pens, etc., take the perception and behavior of students in the classroom learning process as the data collection object, for example, use a camera to capture the face information of the target face in the camera screen, and use face recognition technology to combine the face information with The student object is associated with the
  • the camera can be installed in the learning equipment used by the student object, classroom classroom , or the camera is a mobile device with a camera function used by the teacher; for example, the acquisition unit 101 uses a brain-computer interface technology to collect brainwave information through a brain ring worn on the student's head, and obtains the brainwave information from the brainwave information. Data such as the attention of the student object in the classroom; when the collection unit 101 collects online classroom learning data, the collection device may be the camera, earpiece, etc. on the device used by the student object, and the camera on the device used by the teacher object, The receiver, etc., the teacher object can interact with one or more student objects through the device used by the teacher object, and the student object can interact with one or more teacher objects through the device used by the student object.
  • the whole process of interaction data is used as an online classroom. Learning state data; the whole process data includes text, voice, pictures, video, keyboard input, mouse trajectory, handwriting pad data, etc., which are not limited in this application, and dialogues and behaviors in actual classrooms can be restored from the whole process data , explanation and interaction of online live classes, etc.
  • the purpose of the collection unit 101 is to collect classroom learning status data under various scenarios in the learning process.
  • the device used by the teacher object includes a publishing unit 102; the device used by the student object includes a submission unit 103; the publishing unit 102 is configured to allow the teacher object to operate the arrangement module 203 of the remote server 200 to modify homework tasks and/or The homework task is generated, and the homework task can be confirmed.
  • the remote server 200 retrieves the learning resources corresponding to the homework task from the resource module 201 and remotely feeds it back to the device used by the student object; the submitting unit 103, It is set to allow students to complete homework tasks and submit the obtained homework results online; the resource module 201 is set to store learning resources, and the learning resources include homework resources, test question analysis and explanation screen recording; the recommendation module 202, set to output the homework task sequence according to the received classroom learning state data in the collection unit 101 and/or some or all of the data in the scene data in the storage module 204, and the output homework task sequence is provided by the publishing unit 102
  • the teacher object confirms that each time after receiving a homework task confirmation signal, the arrangement module 203 retrieves the corresponding learning resource from the resource module 201 according to the confirmed homework task and feeds it back to the device used by the student object remotely.
  • the acquisition unit 101 is also set to send the classroom learning status data to the storage module 204 for storage; the storage module 204 is set to record the scene data generated in the teaching scene and the homework scene, and the scene data includes the teacher objects when teaching.
  • the behavior data of the teacher object includes the teacher's action data, facial expression data, voice data, etc.; the trajectory data includes homework information during tutoring, student information, voice information of parents and students, etc.; the trajectory data may also include The operation behavior and duration performed by the parent object through the explanation unit 104, the operation behavior includes: opening the test question for explanation, the parent's comment on the completion of the student object's homework; the human-computer interaction data includes text, voice, picture, video, keyboard input , mouse track, smart pen, tablet data, etc., which are not limited in this application.
  • the perception and behavior data of the student object can be converted into data that can be calculated by the recommendation module 202, and used as the basis for homework recommendation, It realizes the effect that the teacher object can quickly locate the individual student object in the form of image information collection, and assign the homework to the individual student object.
  • the video image technology based on human behavior recognition is provided in the acquisition unit 101, when the teacher asks a question about a knowledge point, the student's hand-raising action or facial expression can be used to know the student's response to the learning content.
  • the teacher object to quickly locate the target student object, and to arrange homework tasks for the target student object.
  • face recognition technology can be used for positioning
  • brain ring positioning can also be used
  • speech recognition technology can also be used for positioning
  • different equipment can be selected for the acquisition unit 101 according to actual needs, such as cameras, brain rings, electronic bracelets, smart speakers, etc.
  • the collection unit 101 collects students' multi-class classroom learning status data, and a large amount of data can be obtained to provide a basis for the recommendation module 202 to recommend the homework task sequence. Make selections, and finally make the published tasks more accurate.
  • the recommendation module 202 is provided with one or more job recommendation algorithm models, and the recommendation module 202 is provided with a secondary development interface configured to write a new job recommendation algorithm model; the recommendation The module 202, according to the received classroom learning status data of the acquisition unit 101 and/or some or all of the data in the scene data in the storage module 204, when outputting the homework task sequence, converts the classroom learning status data and/or the scene data into the data. Part or all of the data is used as the input of the job recommendation algorithm model, and according to the output result of the job recommendation algorithm model, the job task sequence is output in combination with the tags of the learning resources in the resource module 201 .
  • the collection unit 101 collects various types of data, it may be necessary to update new job recommendation algorithms in the recommendation module 202 from time to time. Therefore, preparations can be made for this by setting a secondary development interface.
  • the input data required by different job recommendation algorithms are also different.
  • the job recommendation algorithm model written in the recommendation module 202 can be encapsulated into model units, and the corresponding data input can be configured for each model unit. interface, so that each model unit can retrieve the data it needs.
  • an assignment recommendation algorithm for example, the acquisition unit 101 collects the brainwave data of students and teachers. According to the brainwave data, the performance of students' attention when learning knowledge points is obtained, and the appropriate level of attention is recommended.
  • Another example is another homework recommendation algorithm that uses Case Based Reasoning (CBR) technology to solve the distance between the questions asked in the classroom and the same knowledge point test questions in the question bank, that is, the similarity between the two. to infer.
  • CBR Case Based Reasoning
  • the complexity requirements of the OMO learning scenario can be covered.
  • the teacher object When actually using the case-based reasoning (CBR) technology to solve the distance between the questions asked in the classroom and the same knowledge point test questions in the question bank, according to the classroom learning status data obtained by the acquisition unit 101, it is known that the teacher object has carried out the questioning of the student object in the classroom. Answering questions, the homework recommendation algorithm will recommend homework tasks based on the knowledge points at the time of answering questions, consolidating the weak parts of students. When the homework is set to answer the questions, you can view the analysis of the test questions and explain the screen recording, and the student object can also play the knowledge points repeatedly through the teaching screen recording. or test questions. By adopting this technical solution, the continuity of student objects from offline to online learning or online to offline learning is realized.
  • CBR case-based reasoning
  • the teacher object selects and assigns from the homework sequence.
  • the basic homework of all students, the mode is set to adaptive answering mode, and the amount of homework can also be selected according to the algorithm of brainwave technology (refer to the Chinese application with the application number of 201811581972.9) and the personalized recommendation of the student's learning status or delete.
  • the recommendation module 202 can recommend assignments with lower difficulty levels to the students whose attention is lower than the threshold according to the brain wave data.
  • the teacher object can view the assignment content and select the assignment content, and the teacher object can confirm the assignment through the publishing unit 102.
  • the homework content the homework of the students whose attention is lower than the threshold is the common basic homework of the class plus the personalized recommended homework. Recommended by the brainwave algorithm.
  • the recommendation module 202 can make a recommendation for the next homework according to the behavior of processing the homework task and the difficulty of the homework. The higher the speed and the higher the accuracy rate, the more likely it is possible to complete the more challenging assignments. If the student object completes the assignment too slowly and the accuracy rate is low, the recommendation module 202 will adaptively adjust the recommendation difficulty of the next assignment.
  • the teacher object arranges pre-examination review assignments of various degrees of difficulty according to chapters/knowledge points in the publishing unit 102, and the recommendation module 202 is set to recommend students' wrong questions or wrong questions according to the wrong question book of the student objects in the same chapter/knowledge point range.
  • the arrangement module 203 intelligently organizes the papers according to the conditions.
  • the conditions can be a kind of difficulty ratio distribution, the number of questions, the time to answer, the form of the papers, whether the answer, analysis or video can be viewed.
  • the recommendation module 202 is externally connected with one or more intelligent recommendation systems for learning resources, and the recommendation module 202 is based on the received classroom learning status data of the collection unit 101 and/or stored in the storage module 204
  • the recommendation module 202 is based on the received classroom learning status data of the collection unit 101 and/or stored in the storage module 204
  • the result is combined with the labels of the learning resources in the resource module 201 to output the job task sequence.
  • Each of the external intelligent recommendation systems for learning resources can recommend learning resources according to specific data
  • the recommendation module 202 can preset data output rules, output different data to different intelligent recommendation systems for learning resources, and obtain returned results , and then output the job task sequence according to the returned result in combination with the tags of the learning resources in the resource module 201 .
  • the remote server 200 further includes a course scheduling module 207, and the course scheduling module 207 records the date data and attendance data of the student objects in class, and is also set for the arranging module 203 to retrieve the required date data;
  • the arrangement module 203 retrieves the job resource from the resource module 201 and feeds it back to the submission unit 103 remotely, the corresponding date data can be sent to the submission unit 103 at the same time.
  • the device used by the teacher object further includes the homework assistant 105, which is configured to receive a voice assignment instruction from the teacher object, and arrange corresponding homework tasks in the assignment module 203 of the remote server 200 through the instruction.
  • the teacher object can set the homework assistant 105 on the device used by the teacher object to the monitoring state by means of a wake-up word, clicking the start button of the homework assistant 105, etc., and the teacher object will teach knowledge in the classroom offline and face-to-face,
  • the teacher object operates the homework assistant 105 to issue voice homework assignment instructions;
  • the lecturer is teaching through a large-screen remote live broadcast, and the tutor can operate the homework assistant 105 to issue voice homework assignment instructions;
  • the used live broadcasting or recording broadcasting system can be embedded in the job assistant 105 , so that the voice command for assigning assignments can complete the corresponding assignment assignment tasks in the assignment module 203 of the remote server 200 . This can greatly reduce the labor intensity of teachers' homework assignments.
  • the teacher object assigns the homework through the homework assistant 105 according to the performance of the student object in answering the questions in the offline class.
  • the teacher object starts the homework assistant 105 through the wake-up word, and says in the class "Be careful, Wang, the trigonometric function formula goes back.
  • the homework assistant 105 fills in the word slot of the task-based conversation task, the homework assignment object is Wang Xiaoxiao, the homework content is the trigonometric function formula, the homework question type is copy, the number of times is 10 times, and the due date One day before the next class, in some cases, when the word slot that must be filled in the task-based conversation task is missing, the homework assistant 105 will ask the teacher through multiple rounds of conversations to complete the homework assignment task.
  • the teacher object can set the preset value of the word slot in advance according to the habit of assigning personal homework.
  • the homework assistant 105 assigns the homework to the teacher object. If the deadline for submitting assignments is not mentioned at the time, the system will automatically obtain the date one day before the next class from the date when the student object is in class recorded in the class scheduling module 207 .
  • the device used by the teacher object further includes an uploading unit 106
  • the remote server 200 further includes a storage module 206
  • the uploading unit 106 is configured to upload offline files, and upload the offline files to The storage module 206 of the remote server 200
  • the storage module 206 is configured to receive offline files from the uploading unit 106, and convert the format of the received offline files into the storage format of the resource module 201.
  • the uploaded offline files may be the electronic homework task descriptions and test questions of the teacher object.
  • the teacher object adds corresponding tags to the uploaded offline files to become the homework resources of the resource module 201;
  • the quality job converts picture information into text information through Optical Character Recognition (OCR), and uploads it to the storage module 206 of the remote server 200; it can also be associated with other The job resource at the address.
  • OCR Optical Character Recognition
  • the resource module 201 is not only configured to store learning resources such as homework resources, test question analysis, and explanation screen recordings, but also can be configured to label the learning resources with various types of labels that are convenient for the recommendation module 202 to use.
  • the online and offline homework resources can be used universally, and the purpose of free conversion of learning resources in various learning scenarios is achieved, so that the teaching and research resources and localized resources in multiple regions and offline can be stored in the centralized resource module 201,
  • the scale of resources is beneficial to the recommendation module 202 to have a large number and variety of operation resources that can be recommended.
  • the job assistant 105 and the uploading unit 106 may also be used in conjunction.
  • the teacher object learns the learning status of the students according to their answers to the paper practice questions in the double-teacher classroom, and then makes personalized assignments for one or more students through the homework assistant 105, and the teacher object starts the homework assistant.
  • 105 said, "This similar question has the same difficulty as 3 questions", and the homework assistant 105 asked, "What questions are you currently working on?" homework resources, and upload the offline file to the storage module 206 of the remote server 200. Since there is still a lack of filling in the homework assignment object for the necessary slot, the homework assistant 105 asks "who needs to complete this homework?", the teacher object said "Persons with student numbers 1 to 50".
  • the teacher object completes the assignment with the assistance of the homework assistant 105, and publishes the assignment uploaded from offline to the submitting unit 103 in the publishing unit 102, so that one or more student objects can complete the online homework.
  • the student object, the content of the assignment, and the word slot of the due date for assignment submission are extracted from the speech of the teacher object, and the student object extracted from the class scheduling module 207
  • the date and attendance of the class have achieved the effect of rapid homework assignment in the form of voice, greatly accelerated the work efficiency of personalized homework assignment, shortened its work flow, and made the work of this system more convenient and universal.
  • the device used by the teacher object further includes a teaching unit 104, and the teaching unit 104 is configured to allow the object who can tutor the student's homework to explain or guide the student's homework in an online and/or offline form.
  • the remote server 200 further includes a learning situation module 205, and the learning situation module 205 is configured to count and analyze the scene data in the storage module 204, and generate learning situation data, and the learning situation data includes student objects Homework progress data, student target homework completion data, student target weak knowledge point data, class target homework completion rate data, class target homework accuracy ranking and class common wrong question data;
  • the explanation unit 104 is also set to call View the learning situation data generated by the learning situation module 205, and retrieve the learning resources from the resource module 201 according to the learning situation data for explanation or tutoring;
  • the collection unit 101 is also set to collect the explanation process data in the explanation process, and use the The collected explanation process data is uploaded to the recommendation module 202 of the remote server 200; the recommendation module 202 is also set to, after each received an explanation process data, according to the explanation process data, classroom learning status data and/or the storage module 204 Some or all of the data in the scene data in the output job task sequence.
  • the online and offline tutoring resources of the teacher object and the parent object can be used universally, so as to achieve the purpose of free conversion of learning resources in various learning scenarios, so as to realize the learning, practice and tutoring of the student object. Progressively, it helps to improve the learning efficiency.
  • the collection unit 101 collects the offline or online classroom learning status data of the student objects, and uploads the collected classroom learning status data to the recommendation module 202 of the remote server 200; the recommendation module 202 receives the data of the collection unit 101, and combines with the resource module Labels of various resources in 201, various data in the storage module 204, output the assignment task sequence through the assignment recommendation algorithm; receive the voice assignment instruction of the teacher object through the assignment assistant 105, and according to the instruction in the assignment module of the remote server 200 203 completes the corresponding homework assignment task; the assignment module 203 receives the assignment of the teacher object in the publishing unit 102 and the assignment task after confirmation, and retrieves the corresponding assignment resource from the resource module 201 and feeds it back to the submitting unit 103 remotely; the assignment module 203 will The date and attendance of the student object recorded by the class scheduling module 207 are retrieved to simplify the operation procedure of the teacher object for homework assignment; the teacher object can also upload offline files through the uploading unit 106 and upload the offline files to the remote

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Human Resources & Organizations (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Electrically Operated Instructional Devices (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种适合OMO学习场景的智适应作业系统，包括现场装置（100）和远程服务器（200）；现场装置（100）包括采集单元（101）、教师对象使用的装置和学生对象使用的装置；远程服务器（200）包括资源模块（201）、推荐模块（202）、存储模块（204）、布置模块（203）、入库模块（206）、排课模块（207）、学情模块（205）；采集单元（101）设置为采集课堂学习数据；教师对象使用的装置包括上传单元（106）、发布单元（102）、作业助手（105）、讲解单元（104），发布单元（102）设置为向布置模块（203）发送作业任务确认信号；学生对象使用的装置包括提交单元（103），提交单元（103）设置为将得到的作业结果在线提交；资源模块（201）设置为存储学习资源；推荐模块（202）设置为输出作业任务序列；布置模块（203）设置为从资源模块（201）中调取作业任务对应的学习资源并反馈至学生对象使用的装置。该智适应作业系统可以整合整个教育教学学习过程中的数据，利于提高智能推荐作业的匹配度。

Description

适合OMO学习场景的智适应作业系统
本申请要求在2020年08月31日提交中国专利局、申请号为202010899172.2的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能教育技术领域，例如涉及一种适合线上与线下融合(Online Merge Offline，OMO)学习场景的智适应作业系统。
背景技术
OMO学习场景是指将在线学习场景和线下学习场景全面整合，让线上线下的学习数据融合为一个生态体系，OMO的学习场景有多种，举例来说有：1)学生在线下课堂通过教师面对面授课的方式学习，并把一部分学习环节放到线上，例如：学生在课后通过在线学习平台完成作业，教师可以在线下课堂中对学生的在线作业给予反馈，2)双师课堂模式是教学名师在线上主讲授课，同时课堂中有线下辅导教师做作业批改、答疑、督学等服务，3)在线直播课/录播课模式，线上教学名师同时教育更多地区的学生，学生线下完成作业后上传，学生的学习反馈作为直播课/录播课的课件制作的重要参考。
相关技术通常是教师对象通过布置作业系统，做到自动分发、收取、批改和统计作业，这种方式虽然减轻了教师对象批改作业的工作量，却在布置作业时难以考虑到个别学生对象的学习状态，做到个性化的巩固练习，相关技术还需要教师对象根据学生对象的日常作业情况，在大量数据库中人工总结形成作业卷。通过智适应教育的智能作业布置，可以让学生对象只针对自己薄弱的地方进行作业练习，但由于线上和线下的学习数据孤立存在，在OMO学习场景中学生对象在完成线上作业前，必须先经过知识点的测试得到每个学生对象需要学习的薄弱知识点列表，反而增加了学生对象需要做的题量，造成其反抗心理。
发明内容
本申请提供一种适合OMO学习场景的智适应作业系统，其可以打通线上和线下的学习数据的孤立状态，整合整个教学学习过程中的数据，利于提高智能推荐作业的匹配度。
本申请提供一种适合OMO学习场景的智适应作业系统，包括：现场装置和远程服务器；所述现场装置包括采集单元、教师对象使用的装置和学生对象使用的装置；所述远程服务器包括资源模块、推荐模块、存储模块和布置模块；
所述采集单元，设置为采集所述学生对象在线下和/或线上的课堂学习状态数据，并将采集的课堂学习状态数据上传至推荐模块；
所述教师对象使用的装置包括发布单元，所述发布单元，设置为接收所述推荐模块发送的作业任务序列，根据所述教师对象对接收的作业任务序列的挑选操作执行修改所述接收的作业任务序列和生成作业任务序列中的至少之一，并根据所述老师对象对挑选后的作业任务列表中的作业任务的确认操作向所述布置模块发送作业任务确认信号；
所述学生对象使用的装置包括提交单元，所述提交单元，设置为接收所述学生对象完成的作业任务，并将得到的作业结果进行在线提交；
所述资源模块，设置为存储学习资源，其中，所述学习资源包括作业资源、试题解析和讲解录屏；
所述推荐模块，设置为根据接收到的所述采集单元中的课堂学习状态数据和所述存储模块中的场景数据中的部分数据或全部数据，输出作业任务序列，将输出的作业任务序列发送至所述发布单元供所述教师对象确认；
所述布置模块，设置为在接收到作业任务确认信号后，根据所述作业任务确认信号确定确认的作业任务并从所述资源模块中调取所述确认的作业任务对应的学习资源并将调取的学习资源远程反馈至所述学生对象使用的装置；
所述存储模块，设置为记录教学场景中和作业场景中所产生的场景数据，其中，所述场景数据包括所述教师对象在教学情况下的行为数据、所述教师对象在讲解作业情况下的行为数据、家长对象辅导所述学生对象作业的轨迹数据，所述学生对象在所述提交单元的人机交互数据。
附图说明
图1为本申请实施例提供的一种系统架构框图；
图2为本申请实施例提供的一种推荐模块作用时的系统架构框图；
图3为本申请实施例提供的一种作业助手作用时的系统架构框图。
附图标记说明:
100-现场装置；101-采集单元；102-发布单元；103-提交单元；104-讲解单元；105-作业助手；106-上传单元；
200-远程服务器；201-资源模块；202-推荐模块；203-布置模块；204-存储模块；205-学情模块；206-入库模块；207-排课模块。
具体实施方式
本申请实施例提供的OMO学习场景的智适应作业系统，包括：现场装置和远程服务器；所述现场装置包括采集单元、教师对象使用的装置和学生对象使用的装置；所述远程服务器包括资源模块、推荐模块、存储模块和布置模块；所述采集单元，设置为采集所述学生对象在线下的课堂学习状态数据和线上的课堂学习状态数据中的至少之一，并将采集的课堂学习状态数据上传至所述推荐模块；所述教师对象使用的装置包括发布单元，所述发布单元，设置为接收所述推荐模块发送的作业任务序列，根据所述教师对象对接收的作业任务序列的挑选操作执行修改所述接收的作业任务序列和生成作业任务序列中的至少之一，并根据所述老师对象对挑选后的作业任务列表中的作业任务的确认操作向所述布置模块发送作业任务确认信号；所述学生对象使用的装置包括提交单元，所述提交单元，设置为接收所述学生对象完成的作业任务，并将得到的作业结果进行在线提交；所述资源模块，设置为存储学习资源，其中，所述学习资源包括作业资源、试题解析和讲解录屏；所述推荐模块，设置为根据接收到的所述采集单元中的课堂学习状态数据和/或所述存储模块中的场景数据中的部分数据或全部数据，输出作业任务序列，将输出的所述作业任务序列发送至所述发布单元供所述教师对象确认；所述布置模块，设置为在接收到作业任务确认信号后，根据所述作业任务确认信号确定确认的作业任务并从所述资源模块中调取所述确认的作业任务对应的学习资源并将调取的学习资源远程反馈至所述学生对象使用的装置；所述存储模块，设置为记录教学场景中和作业场景中所产生的场景数据，其中，所述场景数据包括所述教师对象在教学情况下的行为数据、所述教师对象在讲解作业情况下的行为数据、家长对象辅导所述学生对象作业的轨迹数据，所述学生对象在所述提交单元的人机交互数据。
修改所述接收的作业任务序列包括删减该作业任务序列中的作业任务、增加该作业任务序列中的作业任务、和调整作业任务序列中的作业任务的顺序等。其中，若教师对象删减该作业任务序列中的作业任务则表示教师对象不采用该作业任务序列中的被删减的作业任务进行作业布置。一般情况下，教师对象只是简单地挑选推荐的作业任务序列中的部分作业任务，或者直接全部接受推荐的作业任务序列，或者全部拒绝推荐的作业任务序列。
老师对象对挑选后的作业任务列表中的作业任务进行确认，也就是老师对象确定是否将当前作业任务列表中的作业任务发布至学生对象使用的装置。老师对象若对一作业任务未进行确认，则表示该作业任务无需布置给学生对象。
所述推荐模块内设置有至少一种作业推荐算法模型，以及设置为写入新的作业推荐算法模型的二次开发接口；所述推荐模块，设置为通过如下方式根据 接收到的所述采集单元中的课堂学习状态数据和/或所述存储模块中的场景数据中的部分数据或全部数据，输出作业任务序列：将所述采集单元中的课堂学习状态数据和/或所述存储模块中的场景数据中的部分数据或全部数据作为所述至少一种作业推荐算法模型的输入，并根据所述至少一种作业推荐算法模型的输出结果，以及所述资源模块中的学习资源的标签输出所述作业任务序列。
适合OMO学习场景的智适应作业系统，还包括至少一个学习资源智能推荐系统，所述推荐模块外接所述至少一个学习资源智能推荐系统；所述推荐模块，设置为通过如下方式根据接收到的所述采集单元中的课堂学习状态数据和/或所述存储模块中的场景数据中的部分数据或全部数据，输出作业任务序列：将所述采集单元中的课堂学习状态数据和所述存储模块中的场景数据中的部分数据或全部数据分别发送至所述至少一个学习资源智能推荐系统，根据返回结果以及所述资源模块中的学习资源的标签输出所述作业任务序列。
所述教师对象使用的装置还包括作业助手；所述作业助手，设置为接收所述教师对象的语音作业布置指令；所述布置模块，还设置为根据所述语音作业布置指令布置所述语音作业布置指令对应的作业任务。
所述教师对象使用的装置还包括上传单元，所述远程服务器还包括入库模块；所述上传单元，设置为接收线下文件，并将所述线下文件上传至所述入库模块；所述入库模块，设置为从所述上传单元接收线下文件，并将接收到的线下文件的格式转化成所述资源模块的入库格式。
所述远程服务器还包括排课模块；所述排课模块，设置为记录所述学生对象上课的日期数据和出席数据，以及向所述布置模块提供所述布置模块所需的日期数据；所述布置模块，还设置为从所述资源模块中调取作业资源并远程反馈至所述提交单元，可同时从所述排课模块调取完成所述作业资源对应的日期数据并向所述提交单元发送所述完成所述作业资源对应的日期数据。
所述布置模块，还设置为根据预设规则及所述学生对象上课的日期数据和出席数据对作业任务内容进行删减。
例如，根据学生对象上课的日期数据和出席数据确定学生对象未参与课程的情况下，可以删减预布置给该学生对象的作业任务。
所述教师对象使用的装置还包括讲解单元；所述讲解单元，设置为使可辅导学生作业的对象通过在线和线下的至少之一形式针对所述学生对象的作业进行讲解或辅导。
所述远程服务器还包括学情模块；所述学情模块，设置为统计和分析所述存储模块中的场景数据，并生成学情数据，其中，所述学情数据包括学生对象 作业进行情况数据、学生对象作业完成情况数据、学生对象薄弱知识点数据，班级对象作业完成率数据、班级对象作业正确率排名和班级共同错题数据；所述讲解单元，还设置为调取查看所述学情模块生成的学情数据，并根据所述学情数据从所述资源模块调取学习资源用作讲解或辅导；所述采集单元，还设置为采集讲解过程中的讲解过程数据，并将采集的讲解过程数据上传至所述推荐模块；所述推荐模块，还设置为在每次接收到讲解过程数据后，根据接收的讲解过程数据、所述采集单元中的课堂学习状态数据和/或所述存储模块中的场景数据中的部分数据或全部数据，输出所述作业任务序列。
所述发布单元，还设置为主动发起作业任务；所述布置模块，还设置为根据所述发布单元主动发起的作业任务从所述资源模块调取所述发布单元主动发起的对应作业资源进行组卷。
通过本系统，使作业布置的设计数据和讲解数据在线上和线下通用，达到设计数据和讲解数据随时自由转换的目的，本系统中的授课、学习、练习再到新一轮的授课的教学过程形成了完整的闭环数据，使学生对象的学习、练习、辅导层层递进，有助于学生对象的学习效率的提升。通过采集学生对象在线下课堂和线上课堂的学习全过程数据，大幅加速了推荐算法的工作效率、避免了学生对象的学习过程数据缺失或部分学习过程不连续，实现了作业布置与学生对象的学习状态精准匹配的功能。通过作业助手的任务型会话，教师对象可以采用语音以更自然且快速的方式进行作业布置，大幅加速了个性化作业布置的工作效率、缩短了其工作流程，使得本系统的工作更为方便普适。可根据教学目标和学生反馈，提供最佳的作业推荐，根据学生上课学习状态智能推送作业，在学生答题过程中动态调整后续推送，完整收录学生完成作业的轨迹。
如图1、图2和图3所示，适合OMO学习场景的智适应作业系统，包括现场装置100和远程服务器200；所述远程服务器200包括资源模块201、推荐模块202、存储模块204和布置模块203；所述现场装置100包括采集单元101、教师对象使用的装置和学生对象使用的装置；所述采集单元101，设置为采集学生对象在线下和/或线上的课堂学习状态数据，并将采集的课堂学习状态数据上传至远程服务器200的推荐模块202；所述采集单元101采集线下课堂学习状态数据时，可以是在线下课堂使用多类传感器、摄像机和脑环、手环、手写板、智能笔等设备，将学生对象在课堂学习过程中的感知和行为作为数据采集对象，例如使用摄像机捕捉目标人脸在摄像画面中的人脸信息，通过人脸识别技术将人脸信息和学生对象在系统的账号信息做关联，另外使用摄像机捕捉学生对象的课堂行为，通过图像识别技术从学生对象的课堂行为得到听课状态数据，摄 像机可以是安设在学生对象使用的学习设备、课堂教室中，或者摄像机是教师对象使用的具有摄像功能的移动设备；还例如，采集单元101是通过佩戴在学生对象头上的脑环，使用脑机接口技术进行脑电波信息采集，通过脑电波信息得到学生对象在课堂上的注意力等数据；所述采集单元101采集线上课堂学习数据时，采集设备可以是学生对象使用的装置上的摄像头、听筒等，以及教师对象使用的装置上的摄像头、听筒等，教师对象通过教师对象使用的装置可以与一名或多名学生对象交互，学生对象通过学生对象使用的装置可以与一名或多名教师对象交互，交互的全过程数据作为线上课堂学习状态数据；所述全过程数据包括文本、语音、图片、视频、键盘输入、鼠标轨迹、手写板数据等，本申请在此不做限定，从全过程数据可以还原实际课堂中的对话和行为、在线直播课的讲解和交互等；所述采集单元101布设的目的在于收集学习过程中的多种情景下的课堂学习状态数据。所述教师对象使用的装置包括发布单元102；所述学生对象使用的装置包括提交单元103；所述发布单元102，设置为让教师对象操作远程服务器200的布置模块203，修改作业任务和/或生成作业任务，并可对作业任务进行确认，远程服务器200收到确认信号后，从资源模块201中调取对应作业任务的学习资源并远程反馈至学生对象使用的装置；所述提交单元103，设置为让学生对象完成作业任务，并将得到的作业结果进行在线提交；所述资源模块201，设置为存储学习资源，所述学习资源包括作业资源、试题解析和讲解录屏；所述推荐模块202，设置为根据接收到的采集单元101中的课堂学习状态数据和/或存储模块204中的场景数据中的部分数据或全部数据，输出作业任务序列，输出的作业任务序列通过发布单元102供教师对象确认，每接收到一个作业任务确认信号后，所述布置模块203根据确认的作业任务从资源模块201中调取对应的学习资源并远程反馈至学生对象使用的装置。所述采集单元101还设置为将课堂学习状态数据发往存储模块204存储；所述存储模块204，设置为记录教学场景中和作业场景中所产生的场景数据，场景数据包括教师对象教学时的行为数据、教师对象讲解作业时的行为数据、家长对象辅导学生对象作业的轨迹数据，学生对象在提交单元103的人机交互数据。
所述教师对象的行为数据包括教师的动作数据、表情数据、语音数据等等；所述轨迹数据包括辅导时的作业信息、学生信息、家长与学生的语音信息等；所述轨迹数据还可以包括家长对象通过讲解单元104执行的操作行为和时长，操作行为包括：打开进行讲解的试题、家长对学生对象作业完成情况的评语；所述人机交互数据包括文本、语音、图片、视频、键盘输入、鼠标轨迹、智能笔、手写板数据等，本申请在此不做限定。
通过设置采集单元101对学生对象的线下课堂或线上课堂中的课堂学习状态数据进行采集，可以把学生对象的感知和行为数据转化为推荐模块202可以 计算的数据，作为作业推荐的依据，实现了教师对象可以以图像信息采集的形式快速定位个别学生对象，并对该个别学生对象布置作业的效果。当所述采集单元101中设有基于人体行为识别的视频图像技术时，在教师对象针对一个知识点提问时，从学生的举手动作或者面部表情动作，即可得知学生对象对学习内容的兴趣程度和理解程度；当所述采集单元101中设有脑波技术时，采集学生对象在学习中的脑电波信号，可以得知其注意力情况；将学习全过程中多种课堂学习状态数据上传至远程服务器200，可大幅加速推荐模块202的工作效率和精准度，避免出现学生对象的学习过程数据缺失或部分过程不连续问题，避免出现作业布置不匹配或不精准的问题。
另外，通过采集单元101，还有利于教师对象快速定位到目标学生对象，针对目标学生对象进行作业任务布置。定位目标学生对象，可使用人脸识别技术定位，还可以使用脑环定位，还可以使用语音识别技术定位，可根据实际需要为所述采集单元101选择不同的设备，如摄像机、脑环、电子手环、智能音响等。
本申请通过采集单元101采集学生的多类课堂学习状态数据，可获取到海量的数据，为推荐模块202推荐作业任务序列提供依据，通过设置发布单元102，可让教师对象对推荐的作业任务序列进行挑选，最终使发布的作业任务更加精准。
本实施例中，所述推荐模块202内设置有一种或多种作业推荐算法模型，且所述推荐模块202上设置有设置为写入新的作业推荐算法模型的二次开发接口；所述推荐模块202根据接收到的采集单元101的课堂学习状态数据和/或存储模块204中的场景数据中的部分数据或全部数据，输出作业任务序列时，将课堂学习状态数据和/或场景数据中的部分数据或全部数据作为作业推荐算法模型的输入，并根据作业推荐算法模型的输出结果，结合资源模块201中学习资源的标签输出作业任务序列。
因为所述采集单元101采集的数据种类繁多，可能需要在推荐模块202中时常更新新的作业推荐算法进去，故通过设置二次开发接口，可为此做准备。另外，不同的作业推荐算法所需要的输入数据也不尽相同，可以对写入推荐模块202中的作业推荐算法模型进行封装，封装成一个个模型单元，为每个模型单元配置相应的数据输入接口，这样每个模型单元调取其所需的数据即可。在此处列举一种作业推荐算法：例如采集单元101采集到的是学生和教师的脑波数据，根据脑波数据得出学生在知识点学习时注意力的表现，根据注意力程度来推荐合适的作业任务；还例如另一种作业推荐算法通过基于事例推理(Case Based Reasoning，CBR)技术求解课堂提问的题目和题库同一知识点试题之间的 距离，也就是二者之间的相似度，来进行推题。
通过推荐模块202的设置，以及推荐模块202功能的可扩展性，可以覆盖OMO学习场景的复杂性需求。
实际使用基于事例推理(CBR)技术求解课堂提问的题目和题库同一知识点试题之间的距离时，根据采集单元101得到的课堂学习状态数据得知教师对象在课堂中针对学生对象的提问进行了答疑，作业推荐算法会就答疑时的知识点推荐作业任务，巩固学生薄弱部分，当该作业设置为答题后可查看试题解析、讲解录屏时，学生对象还可以通过教学录屏重复播放知识点或试题讲解。通过采用这种技术方案，实现学生对象线下到在线学习或在线到线下学习的连续性。
实际中，在基于能力值自适应算法(可参考申请号为201910686317.8的中国申请)进行作业推荐时，根据基于学习目标的知识图谱关系推荐的作业任务序列，教师对象从该作业序列中选择布置给所有学生对象的基本作业，该模式被设置为自适应答题模式，同时还可以根据脑波技术的算法(可参考申请号为201811581972.9的中国申请)以及学生学习状态的个性化推荐进行作业量的选择或删减。例如，推荐模块202可以根据脑波数据，针对注意力低于阈值的学生对象，推荐题目难度较低的作业，教师对象可查看作业内容并对作业内容进行选择，在教师对象通过发布单元102确认作业内容后，注意力低于阈值的学生对象的作业就是班级共同的基本作业加上个性化推荐的作业，班级共同的基本作业可以通过基于能力值的自适应算法推荐，个性化推荐的作业则由脑波算法推荐。学生对象在提交单元103完成一个作业任务后，作业数据会保存在存储模块204，推荐模块202可以根据处理作业任务的行为和作业的难度做出下一道作业的推荐，学生对象完成作业的速度越快、正确率越高，越有可能做到较有挑战的作业，而学生对象完成作业的速度过慢，正确率偏低，推荐模块202会自适应调整下一道作业的推荐难度。通过采用这种技术方案，根据学生上课学习状态智能推送作业，学生答题中动态调整后续推送，完整收录学生完成作业的轨迹，实现对同一学生对象的历史推题情况的存储记录、从而实现对每个学生用户对多知识点掌握情况的大数据汇总统计，有利于推荐算法更精准的推荐作业。
实际中，教师对象在发布单元102按章节/知识点布置多种难度的考前复习作业，并设置推荐模块202根据同样章节/知识点范围的学生对象的错题本推荐学生错题或者错题的相似题，布置模块203根据条件智能组卷，所述的条件可以是一种难度比例分布，题量，作答时间，组卷形式，是否可查看答案、解析或视频等。
本申请的另一个实施例中，所述推荐模块202外接有一个或多个学习资源 智能推荐系统，所述推荐模块202根据接收到的采集单元101的课堂学习状态数据和/或存储模块204中的场景数据中的部分数据或全部数据，输出作业任务序列时：将课堂学习状态数据和/或场景数据中的部分数据或全部数据分别发送至一个或多个学习资源智能推荐系统，并根据返回结果结合资源模块201中学习资源的标签输出作业任务序列。
每个所述外接的学习资源智能推荐系统，可根据特定的数据进行学习资源推荐，所述推荐模块202可预设数据输出规则，向不同的学习资源智能推荐系统输出不同的数据，获取返回结果，然后根据返回结果结合资源模块201中学习资源的标签输出作业任务序列。
本实施例中，所述远程服务器200还包括排课模块207，所述排课模块207记录学生对象上课的日期数据和出席数据，还设置为供布置模块203调取所需的日期数据；所述布置模块203从资源模块201中调取作业资源并远程反馈至提交单元103时，可同时向提交单元103发送对应的日期数据。本实施例中，所述教师对象使用的装置还包括所述作业助手105，设置为接收教师对象的语音作业布置指令、并通过指令在远程服务器200的布置模块203布置相应的作业任务。
在教师对象的授课过程中，教师对象可以通过唤醒词、点击作业助手105启动按钮等方式将教师对象使用的装置上的作业助手105设为监听状态，教师对象在线下面对面地在课堂讲授知识，在课堂中教师对象操作作业助手105发布语音作业布置指令；在双师课堂主讲教师通过大屏幕远程直播进行授课，则可以由辅导教师操作作业助手105发布语音作业布置指令；在线课堂中教师对象所使用的直播或录播系统可嵌入作业助手105，使布置作业的语音指令能在远程服务器200的布置模块203完成相应的作业布置任务。这样可以大幅度地减轻教师的作业布置劳动强度。
在一个实施例中，教师对象根据学生对象回答线下课堂提问中的表现通过作业助手105进行作业布置，教师对象通过唤醒词启动作业助手105，并在课堂中说“王小心，三角函数公式回去抄写10遍，下次上课前交”，作业助手105做任务型会话任务的词槽填写，作业布置对象为王小心，作业内容为三角函数公式，作业题型为抄写，次数10遍，截止日为下次上课前一日，在一些情况，当任务型会话任务必须填写的词槽有缺失时，作业助手105会通过多轮会话跟教师对象进行询问以完成作业布置任务，为了简化课堂作业布置流程，教师对象可以根据个人作业布置的习惯，事先设定词槽的预设值，当截止日词槽的预设值事先设定为下次上课前一日，作业助手105在教师对象布置作业时没有提及作业提交期限的情况下，系统会自动从排课模块207所记录的学生对象上课 的日期得到下次上课前一日的日期。
本实施例中，所述教师对象使用的装置还包括上传单元106，所述远程服务器200还包括入库模块206；所述上传单元106设置为上传线下文件，并将该线下文件上传至远程服务器200的入库模块206；所述入库模块206设置为从上传单元106接收线下文件，并将接收到的线下文件的格式转化成资源模块201的入库格式。
上传的线下文件可能是教师对象已电子化的作业任务描述、试题，教师对象对上传的线下文件加上相应的标签，成为资源模块201的作业资源；也可以是通过拍照上传，把纸质作业通过光学字符识别(Optical Character Recognition，OCR)将图片信息转化成文字信息，并上传到远程服务器200的入库模块206；也可以通过扫描作业本上的二维码或条码，关联到其他地址上的作业资源。
所述资源模块201除了设置为存储作业资源、试题解析、讲解录屏等学习资源，还可设置为对学习资源标注多类便于推荐模块202使用的标签。
通过采用这种技术方案：实现线上线下作业资源通用，达到学习资源在多种学习场景自由转换的目的，从而实现多地区线下的教研资源、本地化资源能存储到集中的资源模块201，做到资源规模化，有利于推荐模块202能有大量且多样的作业资源可以推荐。
实际中，所述作业助手105和上传单元106还可配合使用。例如教师对象根据学生对象在双师课堂中的纸质练习题的答题情况，了解到其学习状态，然后通过作业助手105对一名或多名学生进行个性化的作业布置，教师对象启动作业助手105说“这个相似题同样难度的做3题”，作业助手105追问“当前在做什么题目呢？”教师对象可以通过上传单元106拍照上传线下文件或者通过扫描二维码或条码关联到该作业资源、并将该线下文件上传至远程服务器200的入库模块206，由于还缺失必要槽位作业布置对象的填写，作业助手105追问“哪些人需要完成这份作业？“，教师对象说“学号1至50的人”。教师对象在作业助手105协助下完成作业布置，并在发布单元102将从线下上传的作业发布到提交单元103，让一名或多名学生对象完成在线作业。
通过设置作业助手105的任务型会话词槽，将布置作业所需的学生对象、作业内容、作业提交截止日词槽从教师对象的语音中提取出来，以及从排课模块207提取到的学生对象上课的日期、出席情况，实现了以语音的形式快速进行作业布置的效果，大幅加速了个性化作业布置的工作效率、缩短了其工作流程，使得本系统的工作更为方便普适。
本实施例中，所述教师对象使用的装置还包括讲解单元104，所述讲解单元 104设置为让可辅导学生作业的对象通过在线和/或线下形式针对学生对象的作业进行讲解或辅导。
本实施例中，所述远程服务器200还包括学情模块205，所述学情模块205设置为统计和分析存储模块204中的场景数据，并生成学情数据，所述学情数据包括学生对象作业进行情况数据、学生对象作业完成情况数据、学生对象薄弱知识点数据，班级对象作业完成率数据、班级对象作业正确率排名和班级共同错题数据；所述讲解单元104，还设置为调取查看学情模块205生成的学情数据，并根据学情数据从资源模块201调取学习资源用作讲解或辅导；所述采集单元101，还设置为采集讲解过程中的讲解过程数据，并将采集的讲解过程数据上传至远程服务器200的推荐模块202；所述推荐模块202，还设置为在每次接收到一个讲解过程数据后，根据讲解过程数据、课堂学习状态数据和/或存储模块204中的场景数据中的部分数据或全部数据，输出作业任务序列。
通过设置学情模块205和讲解单元104，实现教师对象、家长对象在线上线下辅导资源通用，达到学习资源在多种学习场景自由转换的目的，从而实现学生对象的学习、练习、辅导是层层递进的，有助于学习效率的提升。
本申请在实践中其工作过程如下：
通过采集单元101采集学生对象在线下或线上的课堂学习状态数据，并将采集的课堂学习状态数据上传至远程服务器200的推荐模块202；推荐模块202接收采集单元101的数据，并结合资源模块201中多种资源的标签、存储模块204中的多种数据，经过作业推荐算法输出作业任务序列；通过作业助手105接收教师对象的语音作业布置指令，并根据该指令在远程服务器200的布置模块203完成相应的作业布置任务；布置模块203接收发布单元102中教师对象布置和确认后的作业任务，并从资源模块201中调取对应的作业资源并远程反馈至提交单元103；布置模块203会调取排课模块207所记录的学生对象上课的日期、出席情况，简化作业布置需要教师对象的操作程序；教师对象也可以通过上传单元106上传线下文件、并将该线下文件上传至远程服务器200的入库模块206，并在发布单元102将从线下上传的作业发布到提交单元103，让学生对象完成在线作业；提交单元103的作业数据实时发送到存储模块204，推荐模块202根据学生对象的数据做自适应作业的推荐；教师对象在线下课堂通过讲解单元104根据学情模块205的学生对象完成的作业情况进行课堂讲解。

Claims (10)

  1. 适合线上与线下融合OMO学习场景的智适应作业系统，包括：现场装置和远程服务器；
    所述现场装置包括采集单元、教师对象使用的装置和学生对象使用的装置；所述远程服务器包括资源模块、推荐模块、存储模块和布置模块；
    所述采集单元，设置为采集所述学生对象在线下的课堂学习状态数据和线上的课堂学习状态数据中的至少之一，并将采集的课堂学习状态数据上传至所述推荐模块；
    所述教师对象使用的装置包括发布单元，所述发布单元，设置为接收所述推荐模块发送的作业任务序列，根据所述教师对象对接收的作业任务序列的挑选操作执行修改所述接收的作业任务序列和生成作业任务序列中的至少之一，并根据所述老师对象对挑选后的作业任务列表中的作业任务的确认操作向所述布置模块发送作业任务确认信号；
    所述学生对象使用的装置包括提交单元，所述提交单元，设置为接收所述学生对象完成的作业任务，并将得到的作业结果进行在线提交；
    所述资源模块，设置为存储学习资源，其中，所述学习资源包括作业资源、试题解析和讲解录屏；
    所述推荐模块，设置为根据接收到的所述采集单元中的课堂学习状态数据和所述存储模块中的场景数据中的部分数据或全部数据，输出作业任务序列，将输出的所述作业任务序列发送至所述发布单元供所述教师对象确认；
    所述布置模块，设置为在接收到作业任务确认信号后，根据所述作业任务确认信号确定确认的作业任务并从所述资源模块中调取所述确认的作业任务对应的学习资源并将调取的学习资源远程反馈至所述学生对象使用的装置；
    所述存储模块，设置为记录教学场景中和作业场景中所产生的场景数据，其中，所述场景数据包括所述教师对象在教学情况下的行为数据、所述教师对象在讲解作业情况下的行为数据、家长对象辅导所述学生对象作业的轨迹数据，所述学生对象在所述提交单元的人机交互数据。
  2. 按照权利要求1所述的适合OMO学习场景的智适应作业系统，其中，所述推荐模块内设置有至少一种作业推荐算法模型，以及设置为写入新的作业推荐算法模型的二次开发接口；
    所述推荐模块，设置为通过如下方式根据接收到的所述采集单元中的课堂学习状态数据和所述存储模块中的场景数据中的部分数据或全部数据，输出作业任务序列：将所述采集单元中的课堂学习状态数据和所述存储模块中的场景 数据中的部分数据或全部数据作为所述至少一种作业推荐算法模型的输入，并根据所述至少一种作业推荐算法模型的输出结果，以及所述资源模块中的学习资源的标签输出所述作业任务序列。
  3. 按照权利要求1所述的适合OMO学习场景的智适应作业系统，还包括至少一个学习资源智能推荐系统，所述推荐模块外接所述至少一个学习资源智能推荐系统；
    所述推荐模块，设置为通过如下方式根据接收到的所述采集单元中的课堂学习状态数据和所述存储模块中的场景数据中的部分数据或全部数据，输出作业任务序列：将所述采集单元中的课堂学习状态数据和所述存储模块中的场景数据中的部分数据或全部数据分别发送至所述至少一个学习资源智能推荐系统，根据返回结果以及所述资源模块中的学习资源的标签输出所述作业任务序列。
  4. 按照权利要求1所述的适合OMO学习场景的智适应作业系统，其中，所述教师对象使用的装置还包括作业助手；
    所述作业助手，设置为接收所述教师对象的语音作业布置指令；
    所述布置模块，还设置为根据所述语音作业布置指令布置所述语音作业布置指令对应的作业任务。
  5. 按照权利要求1所述的适合OMO学习场景的智适应作业系统，其中，所述教师对象使用的装置还包括上传单元，所述远程服务器还包括入库模块；
    所述上传单元，设置为接收线下文件，并将所述线下文件上传至所述入库模块；
    所述入库模块，设置为从所述上传单元接收线下文件，并将接收到的线下文件的格式转化成所述资源模块的入库格式。
  6. 按照权利要求1所述的适合OMO学习场景的智适应作业系统，其中，所述远程服务器还包括排课模块；
    所述排课模块，设置为记录所述学生对象上课的日期数据和出席数据，以及向所述布置模块提供所述布置模块所需的日期数据；
    所述布置模块，还设置为从所述资源模块中调取作业资源并远程反馈至所述提交单元，可同时从所述排课模块调取完成所述作业资源对应的日期数据并向所述提交单元发送所述完成所述作业资源对应的日期数据。
  7. 按照权利要求6所述的适合OMO学习场景的自适应作业系统，其中，所述布置模块，还设置为根据预设规则及所述学生对象上课的日期数据和出席数据对作业任务内容进行删减。
  8. 按照权利要求1所述的适合OMO学习场景的智适应作业系统，其中，所述教师对象使用的装置还包括讲解单元；
    所述讲解单元，设置为使可辅导学生作业的对象通过在线和线下的至少之一形式针对所述学生对象的作业进行讲解或辅导。
  9. 按照权利要求8所述的适合OMO学习场景的智适应作业系统，其中，所述远程服务器还包括学情模块；
    所述学情模块，设置为统计和分析所述存储模块中的场景数据，并生成学情数据，其中，所述学情数据包括学生对象作业进行情况数据、学生对象作业完成情况数据、学生对象薄弱知识点数据，班级对象作业完成率数据、班级对象作业正确率排名和班级共同错题数据；
    所述讲解单元，还设置为调取查看所述学情模块生成的学情数据，并根据所述学情数据从所述资源模块调取学习资源用作讲解或辅导；
    所述采集单元，还设置为采集讲解过程中的讲解过程数据，并将采集的讲解过程数据上传至所述推荐模块；
    所述推荐模块，还设置为在每次接收到讲解过程数据后，根据接收的讲解过程数据、所述采集单元中的课堂学习状态数据和所述存储模块中的场景数据中的部分数据或全部数据，输出所述作业任务序列。
  10. 按照权利要求1所述的适合OMO学习场景的自适应作业系统，其中，
    所述发布单元，还设置为主动发起作业任务；
    所述布置模块，还设置为根据所述发布单元主动发起的作业任务从所述资源模块调取所述发布单元主动发起的对应作业资源进行组卷。
PCT/CN2021/107812 2020-08-31 2021-07-22 适合omo学习场景的智适应作业系统 WO2022042149A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
DE212021000416.4U DE212021000416U1 (de) 2020-08-31 2021-07-22 Intelligentes adaptives Hausaufgabensystem, das für das Omo-Lernszenario geeignet ist

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010899172.2A CN112085630B (zh) 2020-08-31 2020-08-31 适合omo学习场景的智适应作业系统
CN202010899172.2 2020-08-31

Publications (1)

Publication Number Publication Date
WO2022042149A1 true WO2022042149A1 (zh) 2022-03-03

Family

ID=73731771

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/107812 WO2022042149A1 (zh) 2020-08-31 2021-07-22 适合omo学习场景的智适应作业系统

Country Status (3)

Country Link
CN (1) CN112085630B (zh)
DE (1) DE212021000416U1 (zh)
WO (1) WO2022042149A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112085630B (zh) * 2020-08-31 2021-06-29 上海松鼠课堂人工智能科技有限公司 适合omo学习场景的智适应作业系统
CN113077671B (zh) * 2021-04-12 2023-03-21 武汉华莘科技有限公司 基于知识点的学、问、测闭环在线学习系统
CN113657302B (zh) * 2021-08-20 2023-07-04 重庆电子工程职业学院 基于表情识别的状态分析系统
CN113902349A (zh) * 2021-11-22 2022-01-07 北京迈动健康体医融合服务中心 一种运动负荷监测与评价系统
US11838107B2 (en) 2022-01-21 2023-12-05 Dell Products L.P. Bio-telemetry extraction from online sessions
US11689378B1 (en) * 2022-01-21 2023-06-27 Dell Products L.P. Determining loss of focus in online sessions

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140127667A1 (en) * 2012-11-05 2014-05-08 Marco Iannacone Learning system
CN106547815A (zh) * 2016-09-23 2017-03-29 厦门市杜若科技有限公司 一种基于大数据的针对性作业生成方法与系统
CN107733780A (zh) * 2017-09-18 2018-02-23 上海量明科技发展有限公司 任务智能分配方法、装置及即时通信工具
CN110489602A (zh) * 2019-07-25 2019-11-22 上海乂学教育科技有限公司 知识点能力值预估方法、系统、设备及介质
CN110853434A (zh) * 2019-11-29 2020-02-28 史刚 基于大数据和人工智能的教学训练方法及平台
CN112085630A (zh) * 2020-08-31 2020-12-15 上海松鼠课堂人工智能科技有限公司 适合omo学习场景的智适应作业系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107180568A (zh) * 2017-06-30 2017-09-19 楼志刚 一种基于过程控制和结果评价的交互式学习平台及方法
US10911624B2 (en) * 2018-11-30 2021-02-02 Ricoh Company, Ltd. Server, method of controlling data communication, and storage medium
CN110363691A (zh) * 2019-07-04 2019-10-22 科谊达(北京)智能科技有限公司 一种智慧校园的家校共育系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140127667A1 (en) * 2012-11-05 2014-05-08 Marco Iannacone Learning system
CN106547815A (zh) * 2016-09-23 2017-03-29 厦门市杜若科技有限公司 一种基于大数据的针对性作业生成方法与系统
CN107733780A (zh) * 2017-09-18 2018-02-23 上海量明科技发展有限公司 任务智能分配方法、装置及即时通信工具
CN110489602A (zh) * 2019-07-25 2019-11-22 上海乂学教育科技有限公司 知识点能力值预估方法、系统、设备及介质
CN110853434A (zh) * 2019-11-29 2020-02-28 史刚 基于大数据和人工智能的教学训练方法及平台
CN112085630A (zh) * 2020-08-31 2020-12-15 上海松鼠课堂人工智能科技有限公司 适合omo学习场景的智适应作业系统

Also Published As

Publication number Publication date
CN112085630B (zh) 2021-06-29
CN112085630A (zh) 2020-12-15
DE212021000416U1 (de) 2023-03-22

Similar Documents

Publication Publication Date Title
WO2022042149A1 (zh) 适合omo学习场景的智适应作业系统
CN106485964B (zh) 一种课堂教学的录制和点播的方法及系统
KR100466709B1 (ko) 학습 시스템
CN109697904B (zh) 机器人智慧课堂辅助教学系统及方法
CN105469662A (zh) 教学过程中学生答题信息实时采集、高效智能批改系统及使用方法
WO2023131361A2 (zh) 一种基于大数据的教学规划方法及系统
CN112652200A (zh) 人机交互系统、方法、服务器、交互控制设备及存储介质
KR102035088B1 (ko) 스토리텔링 기반 멀티미디어 무인 원격 1:1 맞춤형 교육시스템
KR20200057562A (ko) 다자간 실시간 화상 강의 시스템 및 그 방법
Dominguez et al. Scaling and adopting a multimodal learning analytics application in an institution-wide setting
KR20150071439A (ko) 실시간/비 실시간 문제풀이 학습시스템 및 방법
CN110046290B (zh) 一种个性化自主教学课程系统
VanDeGrift et al. Promoting interaction in large classes with a computer-mediated feedback system
KR20200033700A (ko) 개인 수준별 교육이 가능한 1:n 그룹수업을 위한 화상 다중 분할 교육 시스템
KR20130099381A (ko) 교육 평가 시스템
JP2004333525A (ja) 双方向通信システム、サーバ、電子講義方法、ならびに、プログラム
Hargis et al. Differences, limitations and advantages of effective online and face-to-face teaching methods for a Media Arts course
Haiguang et al. Research on human-computer cooperative teaching supported by artificial intelligence robot assistant
Washbourne Training and education, theory and practice
CN113268512B (zh) 基于互联网平台的企业岗位职业技能培训系统
WO2021131954A1 (ja) 情報処理装置、情報処理方法、及びプログラム
JP2014235557A (ja) 協働活動支援システム
KR20130012652A (ko) 온라인 원격 강의 제어 시스템 및 온라인 원격 강의 제어 방법
Uskov et al. Software/hardware systems and technology for smart engineering education
Saito et al. Supporting classroom activities with the BSUL environment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21859989

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09.08.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21859989

Country of ref document: EP

Kind code of ref document: A1