Teaching system construction method, system and application based on event graph

Abstract

This invention provides a method, system, and application for constructing a teaching big data system based on event graphs. By constructing an event graph centered on events, including events and related databases, events are associated with related databases through event attributes. Events generated during the teaching process are acquired, and their event attributes are matched with related databases. Event data and application data are provided through analysis of events, related databases, and event-generated content. Compared to traditional knowledge graphs, this invention constructs an event-centered event graph that can utilize the spatiotemporal attributes of events and, based on the association between events and related databases, comprehensively record the entire teaching process and its dynamic changes, proactively acquiring more accurate student and teacher data from the entire teaching process.

Description

Technical Field

[0001] This invention relates to the field of teaching technology, and in particular to a method for constructing a teaching system based on event graphs. Background Technology

[0002] In the field of education, information technologies such as online classrooms, electronic blackboards, computer-based grading, intelligent classroom interaction, and automatic handwriting data collection have permeated every aspect of the teaching process. Teachers and students generate massive amounts of data during the teaching and learning process, making it possible to utilize this data to improve the quality of teaching and enhance students' learning abilities.

[0003] Currently, there are several publicly available learning systems, both commercially and through patents. Most of these systems are centered around knowledge points, radiating outwards to form intricate networks. They help students and teachers find corresponding teaching content, exam papers, exercises, and questions based on these knowledge points. However, these systems, starting from knowledge points rather than from the student's or teacher's perspective, provide a relatively passive approach to information acquisition. Users need to actively learn the relevant knowledge points to passively acquire their understanding. Consequently, the user profiles they provide are often biased, failing to offer accurate learning or teaching analyses. Therefore, these systems offer limited assistance to students' learning and teachers' teaching. Furthermore, existing learning systems lack spatiotemporal dimensions, making it impossible to analyze teaching situations using these systems. Summary of the Invention

[0004] This invention provides a method for constructing a teaching big data system based on event graphs to assist teachers in their teaching.

[0005] Firstly, a method for constructing a teaching system based on event graphs is proposed, including:

[0006] Construct an event graph, which is centered on events and includes events and related databases. Events are associated with related databases through event attributes.

[0007] Acquire events generated during the teaching process, and identify and extract the corresponding event attributes;

[0008] Match relevant databases based on event attributes;

[0009] The system analyzes events, related databases, and event generators, providing event data and application data for users to view or use, and updates the event graph based on the event data.

[0010] The relevant databases include a student information database, a school information database, a question bank, and an event-generated database. Event-generated data are defined as relevant information generated due to the occurrence of an event, including student answer information, teacher grading information, and student correction information. Event data includes student data and teacher data. The application data refers to suggestions pushed by the system based on the event data.

[0011] This invention constructs an event graph centered on events. Compared with traditional knowledge graphs, it can utilize the spatiotemporal attributes of events and record the entire teaching process and dynamic changes completely based on the association between events and related databases. This includes the learning status of students at each stage and the teaching status of teachers, and proactively obtains more accurate student and teacher data from the entire teaching process.

[0012] Preferably, the relationships between events include subordinate and parallel relationships, and are stored using a binary tree structure to achieve lightweight storage of event information and easy data partitioning. Specifically, the left node of the binary tree represents the subordinate relationship, and the right node represents the parallel relationship.

[0013] Preferably, the events are acquired through a service receiving device, which includes devices that can be used in the teaching process such as mobile phones, tablets, computers, smart pens, and electronic blackboards; the types of events include things that may happen in the teaching process such as answering questions, grading, correcting, evaluating, compiling test papers, asking questions, preparing lessons, writing on the blackboard, taking exams, and issuing warnings.

[0014] Preferably, the event attributes include event initiator, event participants, event location, event time, event generator, event type, parent event to which the event belongs, child event to which the event belongs, and sibling event to which the event belongs.

[0015] Preferably, event data can be used to obtain data on students' learning process, learning ability evaluation, exam results, test-taking ability evaluation, incorrect answers, similarity analysis and classification of incorrect answers, weak knowledge points analysis, exam scores, abnormal scores, and predicted exam scores, thereby generating student profiles. Event data can also be used to obtain teacher profiles. Finally, through the comprehensive analysis of student and teacher profile data, teaching effectiveness analysis data and suggestions for optimizing and adjusting teaching content can be obtained.

[0016] Preferably, the application data includes error printing, personalized tutoring, precision teaching, review plan development, test question creation, student evaluation, teacher assessment, and anomaly alarms, which can provide teachers and students with accurate and effective teaching suggestions.

[0017] Preferably, since the event-generated data in the event attributes is complex and diverse, the event-generated attribute can be separated to establish an event-generated database, and the event-generated data can be further identified, analyzed and stored, so as to associate more information in the event with the database and record a more complete teaching process; the identification of event-generated data includes the identification of marking symbols (such as the correctness of answers), automatic judgment of the correctness of answer content, identification of the emotional tone of comments and keyword extraction, etc.

[0018] Secondly, a system for constructing a teaching big data system based on event graphs is provided, including:

[0019] The service receiving module receives events generated during the teaching process.

[0020] The data storage module stores an event graph, which includes events and related databases.

[0021] The data analysis module receives events collected by the business receiving module, identifies and extracts the event attributes corresponding to the events, matches the relevant databases through the event attributes, and finally analyzes the events, relevant databases, and event generators to provide event data and application data, and updates the event graph.

[0022] The relevant databases include a student information database, a school information database, a question bank, and an event-generated database; event-generated data are defined as relevant information generated due to the occurrence of an event, including student answer information, teacher grading information, and student correction information; event data includes student data and teacher data; the application data refers to suggestions pushed by the system based on the event data.

[0023] Preferably, the service receiving module uses a service receiving device, including a mobile phone, tablet, computer, smart pen, and electronic whiteboard. The service receiving device connects to the system's server via wireless communication and uploads data. In the data storage module, events are stored using a binary tree structure, where the left node represents a subordinate relationship and the right node represents a parallel relationship. Event types include answering questions, grading, correcting, evaluating, test paper generation, asking questions, lesson preparation, blackboard writing, exams, and warnings. Event attributes include event initiator, event participants, event location, event time, event generator, event type, parent event, child event, and sibling event. The system acquires student learning process data, student learning ability evaluation data, student exam result data, student test-taking ability evaluation data, student error data, error similarity analysis and classification data, student knowledge point weakness analysis data, student exam score data, score anomaly data, and predicted exam score data through event data to obtain student profiles. It can also acquire teacher profiles through event data. The system uses student and teacher profile data to obtain teaching effectiveness analysis data and suggestions for optimizing and adjusting teaching content. The system provides application data including error printing, personalized tutoring, precision teaching, review plan development, test question creation, student evaluation, teacher assessment, and anomaly alerts.

[0024] Thirdly, an event graph-based teaching big data system construction device is provided, comprising: a memory and a processor; the memory stores executable code, and when the executable code is executed by the processor, the processor executes the event graph-based teaching big data system construction method as described in the first aspect, or constructs the system described in the second aspect.

[0025] Fourthly, the present invention provides a non-transitory machine-readable storage medium storing executable code, wherein when the executable code is executed by a processor of an electronic device, the processor is able to at least implement the event graph-based teaching system construction method of the first aspect.

[0026] In this embodiment of the invention, a method, system, and application for constructing a teaching big data system based on event graphs are provided, which have the following beneficial effects:

[0027] 1. Construct an event graph centered on events. Compared with traditional knowledge graphs, it can utilize the spatiotemporal attributes of events and record the entire teaching process and dynamic changes completely based on the relationship between events and related databases. This includes the learning status of students at each stage and the teaching status of teachers, and actively obtains more accurate student and teacher data from the entire teaching process.

[0028] 2. The system provided by this invention collects event information generated in the business processing flow. The event information is structured data and combined with teaching characteristics. The event ontology designed by this big data system can adapt to the expression needs of various teaching event structured data.

[0029] 3. Use a binary tree method to organize the relationships between events, so as to achieve lightweight storage of event information and easy data partitioning;

[0030] 4. The system adopts the concept of "knowledge accumulation" to solve the problem of mining knowledge in event graphs. The knowledge accumulated after processing event information is stored in student profiles, teacher profiles and question banks, which can provide accurate and highly valuable event data and application data. Attached Figure Description

[0031] The accompanying drawings, which are provided to further illustrate the invention and constitute a part of this invention, are illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention.

[0032] in:

[0033] Figure 1 This is an example of an event graph in the teaching process;

[0034] Figure 2 This is a framework diagram of a big data system for the teaching activity process;

[0035] Figure 3 It is an event handling state machine. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, 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.

[0037] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0038] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0039] There are some publicly available learning systems on the market or in patent technology. These systems radiate outward from knowledge points, forming intricate networks that help students or teachers find corresponding teaching content, exam papers, exercises, and questions. However, these systems, starting from knowledge points rather than from the student's or teacher's perspective, are relatively passive in acquiring information. Users need to learn the relevant knowledge points themselves to passively acquire their understanding. The resulting user profiles are often biased, failing to provide accurate learning or teaching analyses. Therefore, these systems offer limited assistance to students' learning and teachers' teaching. Furthermore, existing learning systems lack spatiotemporal dimensions, making it impossible to analyze teaching situations using these systems.

[0040] To address the aforementioned problems, this invention proposes a method for constructing a teaching big data system based on event graphs.

[0041] In the real world, events are the direct reflection of reality. Analyzing event information allows for a better understanding of the world. Compared to the static knowledge in knowledge graphs, connecting event information into a network to form an event graph, and utilizing the spatiotemporal attributes of event information, allows for a better understanding of the dynamic changes in the real world, thus facilitating more accurate predictions and decisions. The method proposed in this invention is a business-oriented information-based teaching system. Information generated during the teaching process is fed back to the teaching information platform in the form of events. Moreover, the event information is structured data, and with simple differentiation and processing, relevant events and their attribute information can be extracted. Compared to the analysis of unstructured text data, teaching process event information is more likely to generate reliable event graph data. Using event graphs can more realistically represent the teaching activity process, so using event graphs to represent teaching activity process data is an ideal choice. The implementation principles of the method, system, equipment, and media of this invention are similar and will not be elaborated here.

[0042] After introducing the basic principles of the present invention, various non-limiting embodiments of the present invention are described in detail below. It should be noted that the embodiments provided by the present invention are only shown to facilitate understanding of the spirit and principles of the present invention, and the embodiments of the present invention are not limited in any way. On the contrary, the embodiments of the present invention can be applied to any applicable system.

[0043] Example 1:

[0044] Methods for constructing a teaching big data system based on event graphs include:

[0045] S10: Construct an event graph, which is centered on events and includes events and related databases. Events are associated with related databases through event attributes.

[0046] This invention defines an event as something that occurs during the teaching process, such as...

[0047] Events generated during a complete student learning process include pre-class preparation, classroom listening, and post-class practice; events generated during a complete teacher teaching process include pre-class lesson preparation, classroom teaching, and post-class homework correction; student learning periodic evaluation events include weekly tests, monthly tests, mid-term tests, and final exams; corresponding teacher events for periodic evaluations include test question preparation, test paper correction, personalized student tutoring, and summarizing and evaluating student learning progress. Events can have subordinate or parallel relationships. In one embodiment, a binary tree structure is used for storage to achieve lightweight storage of event information and easy data partitioning. Specifically, the left node of the binary tree represents a subordinate relationship, and the right node represents a parallel relationship.

[0048] Related to the aforementioned events are relevant databases, such as student information databases, school information databases, question banks, and event-generated databases. Among them, event-generated databases are defined as relevant information generated as a result of an event, including student answer information, teacher grading information, and student correction information.

[0049] Events are mapped to relevant databases based on their event attributes. In one embodiment, these attributes include the event initiator, participants, location, time, generated event, type, parent event, child event, and sibling event. The event type can include types corresponding to events that may occur during the teaching process, such as answering questions, grading, correcting, evaluating, test paper creation, asking questions, lesson preparation, blackboard writing, exams, and warnings. Because the generated event data within the event attributes is complex and diverse, in one embodiment, the generated event attribute can be separated into an event generated event database. This database can then be further identified, analyzed, and stored, linking more information from the event to the database and recording a more complete teaching process. In a specific embodiment, the identification of generated events includes recognizing grading symbols (e.g., correct or incorrect answers), automatically judging the correctness of answer content, recognizing the emotional tone of comments, and extracting keywords.

[0050] S20: Acquire events generated during the teaching process, and identify and extract the corresponding event attributes.

[0051] In one embodiment, the event is acquired through a service receiving device, which includes devices that can be used in the teaching process such as mobile phones, tablets, computers, smart pens, and electronic blackboards, and the data is transmitted to the server of the big data platform through a communication protocol.

[0052] The server determines whether the received event needs to be recorded and processed based on the event type. For events that need to be recorded and processed, other event attributes are extracted based on structured information.

[0053] The data received by the big data platform is based on business processing flows, which involve various changes in processing states. This big data system employs a state machine to analyze and process the information generated by events. Furthermore, based on extracted event attribute information and the information from already processed events, the relationship between the current event and previously processed events is determined. Therefore, the relationship analysis module of the big data platform needs to use a queue to cache processed event information.

[0054] S30: Match the relevant database based on the event attributes.

[0055] S40: Analyze events, related databases, and event generators. The system provides event data and application data for users to view or use, and updates the event graph based on the event data.

[0056] In one embodiment, the event data includes student data and teacher data; the application data is the suggestions pushed by the system based on the event data.

[0057] Specifically, the system provides student data including data on students' learning process, learning ability evaluation, exam results, test-taking skills evaluation, incorrect answers, similarity analysis and classification of incorrect answers, analysis of students' knowledge weaknesses, exam scores, abnormal scores, and predicted exam scores. This data forms a student profile. The system also provides teacher data, including a teacher profile. Furthermore, by comprehensively analyzing both student and teacher profile data, the system can provide data on teaching effectiveness analysis and suggestions for optimizing and adjusting teaching content.

[0058] Finally, based on the aforementioned event data, the system can provide students, teachers, and schools with precise teaching suggestions. These suggestions can be implemented or selected through methods such as printing out incorrect answers, personalized tutoring, targeted teaching, review plan development, test question creation, student evaluation, teacher assessment, and anomaly alerts.

[0059] In summary, the event graph proposed in this embodiment is a complex data network system centered on an event (such as a student's complete learning process) and horizontally linked to corresponding entities (students or teachers) and related databases (such as a question bank, including specific test questions and their corresponding test points and difficulties). Through analysis of data within a certain range of the event graph, please refer to [link to relevant documentation]. Figure 1 This allows for the following big data applications:

[0060] 1. By analyzing event information in a timely manner, student profile data can be updated and generated in real time. The student profile data reflects the students' learning ability analysis data.

[0061] 2. By analyzing event information in a timely manner, teacher profile data can be updated in real time and generated. The teacher profile reflects the teacher's teaching characteristics and teaching effectiveness.

[0062] 3. Through comprehensive analysis of teachers and students, data on the effectiveness of teachers' teaching can be obtained;

[0063] 4. By analyzing the process of students learning new knowledge, data on students' learning ability can be obtained;

[0064] 5. By analyzing the results of students' important exams, we can obtain data on students' test-taking abilities;

[0065] 6. By analyzing the similarity of students' test questions, teachers can categorize students' incorrect answers, thereby guiding them to provide personalized tutoring to improve students' mastery of knowledge.

[0066] 7. By identifying and judging the content of test questions, we can obtain the distribution of students' weak knowledge points, which can help teachers optimize the selection of teaching content and improve classroom teaching efficiency.

[0067] 8. By analyzing the trends in students' exam scores, we can predict their exam performance and identify any abnormal situations.

[0068] In order to more fully disclose the technical solution proposed in this invention, some terms proposed in this invention are defined below:

[0069] 1. Event Attribute Definition

[0070] Event Producer: refers to the person or device that generates the event, such as students, teachers, parents, and devices that generate alarms;

[0071] Event Participant: refers to the people or devices involved in the event, such as students, teachers, parents, and the devices that generated the alarm;

[0072] Event Location: This refers to the location or system where the event occurred, such as a school, classroom, computer room, office, or home address. For information where the location cannot be determined, the system that generated the event information is used as the event location.

[0073] Event Time: This refers to the time included in the data uploaded to the server. If the data does not include a time, the first time the server receives it is taken as the event time.

[0074] Event Production: refers to related information generated as a result of an event, such as student answer information, teacher grading information, and student correction information.

[0075] Event Type: Refers to the event attributes used to describe different teaching activities, such as answering questions, grading, correcting, and evaluating.

[0076] Parent Event: This refers to the event that is the parent event of the event when it is a child event. For example, the weekly test event is the parent event of students answering questions and teachers grading papers.

[0077] Child Event: This refers to the child events contained within the main event, such as students answering questions and teachers grading papers being child events of the weekly test event.

[0078] Brother Event: This refers to other events that belong to the same parent event.

[0079] 1.1 Event Section Property Type Definition

[0080] Incident initiator types: divided into students, teachers, parents, devices, etc.;

[0081] Event participant type: This type shares the same type definition as the event initiator type;

[0082] Incident location types: These include schools, classrooms, computer labs, offices, and home addresses.

[0083] Event occurrence time types: These include types specific to the second, the minute, the hour, the day, the month, the year, types with weekday information, and types with holiday information.

[0084] Event generated information types include: student answer information, teacher grading information, student correction information, student question information, teacher test paper compilation information, teacher comments information, parent feedback information, and abnormal alarm information.

[0085] 1.3 Event Type Definition

[0086] Answer type: refers to an event whose generator is the student's answering process;

[0087] Correction type: refers to an event whose generated product is correction information;

[0088] Correction type: refers to an event whose event generator is a correction marker;

[0089] Evaluation type: refers to events whose generated outputs are evaluation information such as comments, grades, and assessment levels;

[0090] Test Paper Generation Type: Refers to events that generate test papers or exercises;

[0091] Question type: refers to an event in which the event generator is a question submitted by a student;

[0092] Question type: refers to an event in which the teacher poses a question to the student;

[0093] Lesson preparation type: refers to events where the event generator is a lesson plan submitted by the teacher online;

[0094] Blackboard writing type: refers to events whose generated content is the teaching content saved on the electronic blackboard by the teacher during the lecture;

[0095] Exam type: refers to an event whose event generator is information about the exam participants;

[0096] Alarm type: refers to an event generated by the device due to an abnormality.

[0097] 2. Event Relationship Definition and Organization Methods

[0098] Definition: Event relationships are divided into parent-child relationships and sibling relationships. A parent-child relationship refers to the inclusion relationship where a large event contains smaller events, while a sibling relationship refers to the relationship between child events belonging to the same large event.

[0099] Organization method: Event relationships are stored using a binary tree structure based on parent-child relationships. The left node of the binary tree represents the parent-child relationship, and the right node represents the sibling relationship. The events are associated with each other using the parent event attribute, child event attribute, and sibling event attribute. Sibling events are sorted by the time they occurred and then associated with each other in the form of right nodes.

[0100] 3. The databases related to the teaching activity process are defined as follows:

[0101] 3.1 The question bank information includes:

[0102] Question stem content: refers to the question information presented to students that they need to answer the questions;

[0103] Knowledge points: refers to the knowledge points tested in the test questions;

[0104] Question release time: refers to the time when the question appears;

[0105] Difficulty level: refers to the level of difficulty of students answering the questions, which is divided into three levels: difficult, medium and easy. When the students answer less than 10% correctly, it is considered difficult; when the students answer more than 70% correctly, it is considered easy; and the rest are medium difficulty levels.

[0106] Number of citations: refers to the number of times a test paper is used by teachers or as practice exercises;

[0107] Error susceptibility: refers to the likelihood of students answering incorrectly, expressed as the probability of incorrect answers: number of students answering incorrectly / total number of students answering the question;

[0108] Related chapters: These refer to chapters related to the textbook, specifically those in the People's Education Press version. For other versions of the textbook, you need to compare and map the knowledge points to the chapters in the People's Education Press version.

[0109] 3.2 Student Profile Attribute Definition

[0110] Basic attribute: Linked to student information database;

[0111] The learning ability evaluation attributes are: weak knowledge points, error-prone knowledge points, error-prone question types, comprehensive problem analysis ability level, and ability to accept new knowledge points.

[0112] The test-taking ability evaluation attributes are: overall score level and the trend of score changes in each subject;

[0113] Teacher comments for each subject: including two parts: keywords and a complete descriptive text.

[0114] 3.3 Teacher Profile Attribute Definition (Customized design based on the needs of different schools)

[0115] 4. Event Graph and Knowledge Base Association Method: Various attributes are defined in the event ontology. Event attributes can be associated with corresponding related databases based on their type. For example, student type is associated with student information database, student profile database, and school information database; teacher type is associated with school information database and teacher profile database; answer information type and grading information are associated with question bank; and teacher comment information is associated with student profile database. This establishes a mapping relationship to achieve automatic association.

[0116] Example 2:

[0117] A system for constructing a teaching big data system based on event graphs, comprising:

[0118] The business receiving module receives events generated during the teaching process.

[0119] The data storage module stores an event graph, which includes events and related databases.

[0120] The data analysis module receives events collected by the business receiving module, identifies and extracts the event attributes corresponding to the events, matches the event attributes with relevant databases, and finally analyzes the events, relevant databases, and event generators to provide event data and application data, and updates the event graph.

[0121] The relevant databases include a student information database, a school information database, a question bank, and an event-generated database; event-generated data are defined as relevant information generated due to the occurrence of an event, including student answer information, teacher grading information, and student correction information; event data includes student data and teacher data; the application data refers to suggestions pushed by the system based on the event data.

[0122] In this embodiment, the service receiving module uses service receiving devices, including mobile phones, tablets, computers, smart pens, and electronic whiteboards. The service receiving devices connect to the system's server via wireless communication and upload data.

[0123] In the data storage module, events are stored using a binary tree structure, where the left node of the binary tree represents a subordinate relationship and the right node represents a parallel relationship.

[0124] Event types include answering questions, grading, correcting, evaluating, compiling test papers, asking questions, preparing lessons, writing on the blackboard, taking exams, and issuing warnings. Event attributes include event initiator, event participants, event location, event time, event generator, event type, parent event, child event, and sibling event.

[0125] The system uses event data to obtain data on students' learning process, learning ability evaluation, exam results, test-taking skills evaluation, incorrect answers, similarity analysis and classification of incorrect answers, weaknesses in students' knowledge points, exam scores, score anomalies, and predicted exam scores, thereby generating student profiles. Teacher profiles are also obtained through event data. The system uses both student and teacher profile data to obtain data on teaching effectiveness analysis and suggestions for optimizing and adjusting teaching content. Application data provided by the system includes printing incorrect answers, personalized tutoring, precision teaching, review plan development, test creation, student evaluation, teacher assessment, and anomaly alerts.

[0126] To fully disclose the technical solution proposed in this invention, the entire system can also be divided into three layers: an event graph generation layer, an event graph layer, and an event graph application layer. Specifically:

[0127] 1. Event Graph Generation Layer: This layer mainly has the following functions:

[0128] 1.1 Event Reception: A big data system first needs a business receiving and response server. On this server, business requests sent from terminals are received and processed through various communication protocols. In this system, business requests are defined as events.

[0129] 1.2 Event Attribute Extraction: The event processing server determines the event type based on the business type, and determines whether the received event needs to be recorded and processed based on the event type. For events that need to be recorded and processed, the event attributes are extracted based on the structured information.

[0130] 1.3 Event Relationship Analysis: Based on the extracted event attribute information and the information of the events that have been processed, the relationship between the current event and the events that have been processed is determined. Therefore, the relationship analysis module needs to use a queue to cache the information of the events that have been processed.

[0131] 1.4 Event Generator Recognition: Event generators need to be further analyzed and recognized so that more information in the event can be associated with the knowledge base, such as recognizing grading symbols as correct or incorrect answers, automatically judging the correctness or incorrectness of answer content, recognizing the emotional color of comments, and extracting keywords.

[0132] Event handling is a continuous process of receiving data requests from the terminal. This is a multi-round interaction process, and the event handling module in the server needs to have a state machine mechanism (such as...). Figure 3 The server handles events in several states: waiting for a request, processing a request, receiving and processing data, and providing feedback on the result. When processing a terminal business request, the server obtains attribute information such as the event type, initiator, occurrence time, and location. Receiving and processing data is a cyclical process in which the attribute information of the event generator is obtained. After the event processing is completed, the server analyzes and determines the event relationships.

[0133] 2. Event Graph Layer: This layer uses the event attribute library as its core data. The relevant attributes in the event attribute library are linked to the student information library, school information library, and question bank. Since the event generated data in the event attributes is complex and diverse, it is necessary to separate the event generated attributes and establish an event generated library.

[0134] 3. Event Graph Application Layer: The application layer uses event information to generate the required application knowledge. The application knowledge is mainly stored in student profiles and teacher profiles. In the application layer, on the one hand, the application knowledge is analyzed and updated in real time based on event information. The knowledge is updated not only for student profiles and teacher profiles, but also for dynamic parameters in the question bank (such as the number of citations and the degree of error). On the other hand, it responds to application business needs and extracts the required information from the knowledge base according to different needs.

[0135] Example 3:

[0136] An event graph-based teaching big data system construction device includes: a memory and a processor; the memory stores executable code, and when the executable code is executed by the processor, the processor executes the event graph-based teaching system construction method as described in Embodiment 1, or constructs the system as described in Embodiment 2.

[0137] Example 4:

[0138] A non-transitory machine-readable storage medium storing executable code, wherein when the executable code is executed by a processor of an electronic device, the processor is able to at least implement the method for constructing a teaching big data system based on event graphs as described in Embodiment 1.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a teaching big data system based on event graphs, characterized in that, include: Construct an event graph, which includes events and related databases. Events are associated with related databases through event attributes. The relationships between events include subordinate relationships and parallel relationships. The graph is stored using a binary tree structure, where the left node of the binary tree represents a subordinate relationship and the right node represents a parallel relationship. Acquire events generated during the teaching process, and identify and extract the corresponding event attributes; Match relevant databases based on event attributes; Analyze events, related databases, and event generators to provide event data and application data, and update the event graph; The relevant databases include a student information database, a school information database, a question bank, and an event-generated database. Event-generated data are defined as relevant information generated due to the occurrence of an event, including student answer information, teacher grading information, and student correction information. Event data includes student data and teacher data. The application data refers to suggestions pushed by the system based on the event data.

2. The method according to claim 1, characterized in that, The events are acquired through service receiving devices, including mobile phones, tablets, computers, smart pens, and electronic blackboards; the types of events include answering questions, grading, correcting, evaluating, compiling test papers, asking questions, preparing lessons, writing on the blackboard, taking exams, and issuing warnings.

3. The method according to claim 1 or 2, characterized in that, The event attributes include event initiator, event participants, event location, event time, event generator, event type, parent event, child event, and sibling event.

4. The method according to claim 1, characterized in that, By acquiring data on student learning process, student learning ability evaluation, student exam results, student test-taking ability evaluation, student incorrect answers, incorrect answer similarity analysis and classification, student knowledge weakness analysis, student exam scores, score anomalies, and predicted exam scores through event data, student profile data is generated. Teacher profiles are generated through event data. Teaching effectiveness analysis data and suggestions for optimizing and adjusting teaching content are obtained through student profile data and teacher profile data.

5. The method according to claim 1, characterized in that, The application data includes error printing, personalized tutoring, precision teaching, review plan development, test question creation, student evaluation, teacher assessment, and anomaly alerts.

6. The method according to claim 1, characterized in that, Establish an independent event generator library, and further identify, analyze and store the event generators; the identification of event generators includes the identification of marking symbols, automatic judgment of the correctness of answers, identification of the emotional tone of comments and keyword extraction.

7. A system for constructing a teaching big data system based on event graphs, characterized in that, include: The service receiving module receives events generated during the teaching process. The data storage module stores an event graph, which includes events and related databases. The data analysis module receives events collected by the business receiving module, identifies and extracts the event attributes corresponding to the events, and matches the relevant databases through the event attributes. The relationships between events include subordinate and parallel relationships, and are stored in a binary tree structure. The left node of the binary tree represents the subordinate relationship, and the right node represents the parallel relationship. Finally, the module analyzes the events, relevant databases, and event generators, provides event data and application data, and updates the event graph. The relevant databases include a student information database, a school information database, a question bank, and an event-generated database; event-generated data are defined as relevant information generated due to the occurrence of an event, including student answer information, teacher grading information, and student correction information; event data includes student data and teacher data; the application data refers to suggestions pushed by the system based on the event data.

8. The system according to claim 7, characterized in that, The service receiving module uses service receiving devices, including mobile phones, tablets, computers, smart pens, and electronic whiteboards. The service receiving devices connect to the system's server via wireless communication and upload data. In the data storage module, events are stored using a binary tree structure, where the left node represents a subordinate relationship and the right node represents a parallel relationship. Event types include answering questions, grading, correcting, evaluating, test paper generation, asking questions, lesson preparation, blackboard writing, exams, and warnings. Event attributes include event initiator, event participants, event location, event time, event generator, event type, parent event, child event, and sibling event. The system uses event data to acquire student learning process data, student learning ability evaluation data, student exam result data, student test-taking ability evaluation data, student error data, error similarity analysis and classification data, student knowledge point weakness analysis data, student exam score data, score anomalies, and predicted exam score data, thereby generating student profiles. It also acquires teacher profiles through event data. The system uses student and teacher profile data to acquire teaching effectiveness analysis data and teaching content optimization and adjustment suggestions. The system provides application data including error printing, personalized tutoring, precision teaching, review plan development, test question creation, student evaluation, teacher assessment, and anomaly alerts.

9. A teaching system construction device based on event graphs, characterized in that, include: Memory, processor; The memory stores executable code, which, when executed by the processor, causes the processor to execute the event graph-based teaching system construction method as described in claims 1 to 6.

Images