Data acquisition method and device for school book teaching aid system

Abstract

The invention discloses a data acquisition method and device for a school book teaching aid system, and belongs to the technical field of intelligent teaching and big data processing, and the method comprises the steps: embedding an intelligent ID tag with a unique identifier in a teaching aid material, inputting the information of each electronic tag into a database of the school book teaching aid system, and forming a corresponding tag data set; reading the intelligent ID tag by using an intelligent reader-writer, and generating an original data record; original data records are transmitted to a data acquisition server in real time through a communication protocol, data cleaning and data formatting are carried out on the original data records, and a data set in a unified format is formed; according to the object ID, associating the original data record with object information in a database to form a complete event record; carrying out behavior frequency statistics and stay time calculation on the event records; and constructing a feature vector, training a prediction model for predicting the learning effect of the student by adopting a random forest algorithm, predicting the to-be-predicted data, and generating a personalized learning suggestion.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent teaching and big data processing, and in particular to a data collection method and device for a school-based teaching auxiliary system. Background Art

[0002] Traditional teaching auxiliary systems mainly rely on paper materials and manual records, with low data collection efficiency and poor accuracy, making it difficult to meet the needs of personalized teaching. In recent years, radio frequency identification technology (RFID) has been widely used in logistics management and identity recognition due to its high efficiency and accuracy.

[0003] The existing data collection method of school-based teaching auxiliary systems mainly relies on manual input from students and teachers or simple electronic records. This method has many limitations. First, manual records are prone to omissions and errors, resulting in incomplete or inaccurate data; second, the data is not timely enough and cannot reflect students' learning status in real time, making it difficult to provide timely teaching feedback; in addition, the existing system lacks in-depth analysis of students' learning behavior and cannot effectively extract students' learning characteristics, resulting in the lack of personalized teaching suggestions.

[0004] Although some systems have attempted to introduce automatic identification technologies such as RFID, they are still insufficient in data cleaning, association and in-depth analysis, and have failed to fully utilize the advantages of the technology. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract of the specification and the title of the invention of this application to avoid blurring the purpose of this section, the abstract of the specification and the title of the invention, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is that the existing data collection technology of school-based teaching auxiliary system has the problems of low data collection efficiency, poor accuracy and inability to analyze students' learning behavior in real time.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: embedding a smart ID tag with a unique identifier on the teaching materials, and entering the information of each electronic tag into the database of the school-based teaching system to form a corresponding tag data set;

[0009] Using an intelligent reader to read the smart ID tag on the teaching material, generating a raw data record including an object ID, a timestamp, and a location ID;

[0010] The raw data records are transmitted to a data acquisition server in real time through a communication protocol, and the data acquisition server performs data cleaning and data formatting on the received raw data records to form a data set D={object ID, T, location ID} in a unified format;

[0011] According to the object ID, the original data record is associated with the object information in the database to form a complete event record E=D∪{object type, object attribute};

[0012] Performing behavior frequency statistics and residence time calculation on the event record E to extract the learning behavior characteristics of the students;

[0013] Construct a feature vector X = [f, τ, other behavioral features], use the random forest algorithm to train a prediction model for predicting students' learning effects, and predict the data to be predicted to generate personalized learning suggestions.

[0014] As a preferred solution of the data collection method for the school-based teaching system described in the present invention, the tag information of the smart ID tag at least includes a tag ID with a unique identifier, a subject, and a grade;

[0015] The label information is entered into a database in the school-based teaching aid system to form a label data set.

[0016] As a preferred solution of the data collection method for the school-based teaching system of the present invention, the generated original data record at least includes an object ID, a timestamp T, and a location ID;

[0017] Among them, the object ID is the unique identifier of the electronic tag, the timestamp T is the exact time of reading, and the location ID is the location of the reader.

[0018] As a preferred solution of the data collection method for the school-based teaching auxiliary system of the present invention, the behavior characteristics of the students in the event record E, the behavior characteristics include the behavior frequency and the length of stay, and the behavior frequency statistics include:

[0019] Count the frequency of an object in a specific time period:

[0020]

[0021] Among them, N 出现次数 is the total number of times the object appears in the time period Δt, where Δt is the length of the time period.

[0022] As a preferred solution of the data collection method for the school-based teaching auxiliary system of the present invention, the calculation of the stay time includes:

[0023]

[0024] Where n is the number of entry to exit events, and are the timestamps of the i-th entry and exit, respectively.

[0025] As a preferred solution of the data collection method for the school-based teaching auxiliary system of the present invention, a feature vector is constructed according to the behavior characteristics of the behavior frequency and the stay duration:

[0026] X=[f,τ,N 材料种类 , T 早晨 , T 下午 , T 晚上 ]

[0027] Among them, N 材料种类 is the number of teaching materials used, T 早晨 , T 下午 , T 晚上 Indicates the length of study in different time periods;

[0028] Build a prediction model based on the random forest algorithm and perform model training RF:X→Y;

[0029] Use the trained prediction model to predict the new feature vector X new Make predictions:

[0030]

[0031] Among them, Y is the student’s learning effect indicator, The predicted value of the student's learning effect indicator.

[0032] As a preferred solution of the data collection method for the school-based teaching system described in the present invention, the predicted value The value range of is:

[0033] When learning, the effect is excellent;

[0034] When learning is good,

[0035] When learning, the effect needs to be improved.

[0036] As a preferred solution of the data acquisition device for the school-based teaching auxiliary system described in the present invention, it includes:

[0037] The electronic tag module is used to embed a smart ID tag on the teaching materials to provide a unique identification. The smart ID tag adopts an ultra-high frequency RFID tag to achieve long-distance reading;

[0038] The reader / writer module includes an intelligent reader / writer for reading the electronic tag information and generating a raw data record including an object ID, a timestamp and a location ID;

[0039] A data transmission module is used to transmit the collected raw data records to the data acquisition server in real time through a communication protocol;

[0040] Data processing module, including hardware and software components for data preprocessing, data association, and data analysis and processing, configured with edge computing capabilities;

[0041] User interaction module, including display and terminal equipment, used to present analysis results to users and support multi-terminal access;

[0042] Among them, the reader / writer module supports Wi-Fi, Ethernet and LoRa communication protocols and adapts to different network environments.

[0043] As a preferred solution of the data acquisition device for the school-based teaching auxiliary system described in the present invention, it also includes:

[0044] one or more processors;

[0045] A memory stores operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors perform operations, wherein the operations include the process of the data collection method for the school-based teaching auxiliary system as described above.

[0046] As a preferred solution of the data acquisition device for a school-based teaching auxiliary system described in the present invention, it also includes a computer-readable medium storing software, wherein the software includes instructions that can be executed by one or more computers, and the instructions enable the one or more computers to perform operations through such execution, and the operations include the process of the data acquisition method for a school-based teaching auxiliary system as mentioned above.

[0047] Beneficial effects of the present invention:

[0048] 1. It improves the efficiency of teaching materials management, avoids the tediousness and errors of manual registration, ensures the accuracy and completeness of data, and provides a reliable material carrier for the data collection of students' learning behavior;

[0049] 2. Improve the efficiency and accuracy of data collection, ensure the real-time and reliability of data, and lay the foundation for in-depth analysis of students' learning behavior;

[0050] 3. Improved data quality, reduced data noise and anomalies, improved system stability and reliability, and provided a guarantee for accurate data analysis;

[0051] 4. Enhanced the readability and analytical value of data, supported the refined study of students' learning behavior, and provided an important basis for personalized teaching;

[0052] 5. Help teachers and education administrators to gain an in-depth understanding of students’ learning status, adjust teaching strategies in a timely manner, and improve the pertinence and effectiveness of teaching. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0054] Figure 1 It is a flow chart of a data collection method for a school-based teaching auxiliary system shown in the present invention;

[0055] Figure 2 It is a schematic diagram comparing the relationship between the total learning time and the predicted score before and after adjustment shown in the present invention. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0057] Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without making any creative work should fall within the scope of protection of the present invention.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0059] According to an embodiment of the present invention, Figure 1 The flowchart shown in the figure is a data collection method for a school-based teaching auxiliary system, which specifically includes the following steps:

[0060] S1. Embed a smart ID tag with a unique identifier on the teaching materials, and enter the information of each electronic tag into the database of the school-based teaching system to form a corresponding tag data set. Among them, what needs to be explained in this step is:

[0061] Embed smart ID tags on teaching materials, each tag contains a unique identifier (object ID);

[0062] Associating the object ID with the detailed information of the teaching materials in the database to form a complete label data set;

[0063] The tag information of the smart ID tag at least includes a tag ID with a unique identifier, a subject, and a grade;

[0064] As an example, the dataset can be stored in a relational database (such as MySQL) or a NoSQL database (such as MongoDB), and the label dataset is stored in a table form, as shown in Table 1 below:

[0065] Table 1. Label dataset table

[0066]

[0067] S2. Use the smart reader to read the smart ID tag on the teaching material and generate the original data record containing the object ID, timestamp and location ID. It should be noted that the smart reader automatically generates the original data record by scanning the RFID tag on the teaching material with the smart reader, including:

[0068] Object ID: unique identifier of the RFID tag;

[0069] Timestamp T: the exact time of data collection, in the format of YYYY-MM-DD HH:MM;

[0070] Location ID: unique identifier of the reader's location, such as classroom number CLASSROOM_A;

[0071] Question bank ID: The unique identifier of the question bank corresponding to the question information, such as the question number of the eighth grade English test, Y2TOPIC_B.

[0072] As an example, the records in the database are shown in Table 2 below:

[0073] Table 2. Original data record table

[0074] Object ID Timestamp Location ID MATH101 2023-10-01 08:30:00 CLASSROOM_A

[0075] As an example, the smart reader / writer may be a smart pen or a smart learning pen with advanced reading and writing functions.

[0076] S3, the original data records are transmitted to the data acquisition server in real time through the communication protocol, and the data acquisition server performs data cleaning and data formatting on the received original data records to form a unified format data set D = {object ID, T, location ID}. Among them, what needs to be explained in this step is:

[0077] The reader / writer transmits the original data records to the data acquisition server in real time through Wi-Fi, Ethernet or LoRa communication protocol, and adopts TLS encryption protocol to ensure the security of data during transmission;

[0078] The reader sends the data to the data acquisition server in the form of a POST request or message queue;

[0079] The data acquisition server receives and stores raw data records;

[0080] Check if there are duplicate records with the same object ID, timestamp, and location ID, and delete them if there are any;

[0081] Exclude abnormal data such as timestamp anomalies (such as future time) and object IDs that do not exist in the label data set;

[0082] The original data records are converted into a unified format, data set D = {object ID, T, location ID}.

[0083] As an example, the data set in a unified format is represented in the database as shown in Table 3 below:

[0084] Table 3. Datasets in unified format

[0085] Object ID Timestamp Location ID MATH101 2023-10-01 08:30:00 CLASSROOM_A ENG202 2023-10-01 09:15:00 LIBRARY_1

[0086] S4. According to the object ID, the original data record is associated with the object information in the database to form a complete event record E=D∪{object type, object attribute}. Among them, what needs to be explained in this step is:

[0087] Extract object ID from formatted data D;

[0088] Query the database to obtain the corresponding object type and object attributes;

[0089] Merge the query result with the data set D to form event record E;

[0090] As an example, the event record is saved in JSON format as follows:

[0091]

[0092] S5. Count the frequency of the behavior and calculate the duration of stay of the event record E to extract the learning behavior characteristics of the students. Among them, what needs to be explained in this step is:

[0093] In the event log, filter out all records for a specific student;

[0094] Count the number of times the student uses each supplementary material in the Δt period 出现次数 ;

[0095] Count the frequency of an object in a specific time period:

[0096]

[0097] Among them, N 出现次数 is the total number of times the object appears in the time period Δt, where Δt is the length of the time period;

[0098] Match the start and end time of each use of teaching materials;

[0099] Through continuous scanning records, determine and

[0100] Calculate the duration of stay:

[0101]

[0102] Where n is the number of entry to exit events, and are the timestamps of the i-th entry and exit respectively;

[0103] Accumulate all usage time and get τ.

[0104] For example, if student Zhang San used the mathematics teaching materials (MATH101) 14 times in the past 7 days, the frequency is calculated as follows:

[0105]

[0106] For example, Zhang San has two usage records on a certain day. The first time is from 08:30 to 09:00, and the duration is 30 minutes. The second time is from 14:00 to 14:45, and the duration is 45 minutes.

[0107] The total stay time is:

[0108] τ=30+45=75 minutes.

[0109] S6. Construct a feature vector X = [f, τ, other behavioral features], use the random forest algorithm to train a prediction model for predicting student learning effects, and predict the data to be predicted to generate personalized learning suggestions. Among them, it should be noted that this step is:

[0110] Construct the feature vector:

[0111] X=[f,τ,N 材料种类 , T 早晨 , T 下午 , T 晚上 ]

[0112] Among them, N 材料种类 is the number of teaching materials used, T 早晨 , T 下午 , T 晚上 Indicates the length of study in different time periods;

[0113] Build a prediction model based on the random forest algorithm and perform model training RF:X→Y;

[0114] Target variable Y: student learning effect indicator, such as final exam score (value range 0-100 points);

[0115] Use the trained prediction model to predict the new feature vector X new Make predictions:

[0116]

[0117] Among them, Y is the student’s learning effect indicator, Predicted values ​​for students’ learning outcomes;

[0118] Predicted value The value range of is:

[0119] When learning, the effect is excellent;

[0120] When learning is good,

[0121] When learning, the effect needs to be improved.

[0122] In an optional implementation, after the model is trained, the contribution of each feature to the prediction result can be obtained, thereby generating personalized learning suggestions, such as:

[0123] Increase the frequency of use: If the f contribution is high and the student's f is low, it is recommended to increase the frequency of use of teaching materials;

[0124] Extend the study time: If τ is important and the student’s τ is short, it is recommended to extend the study time;

[0125] Optimize time allocation: According to T 早晨 , T 下午 , T 晚上 distribution, adjust the study time.

[0126] Preferably, in order to facilitate non-technical personnel to understand the method of the present invention, the implementation flow and calculation process of the data collection method for the school-based teaching system provided by the embodiment of the present invention are described in detail below by taking the English reading comprehension teaching material (ENG202) used by student Zhang San as an example, wherein:

[0127] Embed a smart ID tag with a unique identifier on the English reading comprehension teaching materials (ENG202), and the tag ID is "ENG202";

[0128] The tag ID "ENG202" and the detailed information of the supplementary teaching materials are entered into the database of the school-based supplementary teaching system to form a corresponding tag data set. The tag information includes:

[0129] Tag ID (object ID): ENG202;

[0130] Teaching materials name: English reading comprehension;

[0131] Subject: English;

[0132] Grade: Grade 2;

[0133] Publisher: Foreign Languages ​​Press;

[0134] Version number: Second edition;

[0135] Difficulty: Difficult;

[0136] The labeled dataset is stored in a relational database (such as MySQL) or a NoSQL database (such as MongoDB) in the form of a table;

[0137] Zhang San uses a smart reader to scan the RFID tag on the English reading comprehension teaching materials in the classroom (location ID is CLASSROOM_B). The reader automatically generates a raw data record containing the following information:

[0138] Object ID: ENG202;

[0139] Timestamp T: 2023-10-02 09:15:00;

[0140] Location ID: CLASSROOM_B;

[0141] The original data records in the database are represented as follows:

[0142] Table 4. Original data record table

[0143]

[0144]

[0145] The reader / writer transmits the original data records to the data acquisition server in real time via Wi-Fi;

[0146] The server checks whether there are duplicate records with the same object ID, timestamp and location ID in the received raw data records, and deletes them if any;

[0147] Exclude abnormal timestamps (such as future time) and abnormal data whose object ID does not exist in the label data set;

[0148] Convert the original data records into a unified format D = {object ID, T, location ID};

[0149] The sorted data set is as follows:

[0150] Table 5. Datasets in unified format

[0151] Object ID Timestamp Location ID ENG202 2023-10-02 09:15:00 CLASSROOM_B

[0152] Extract object ID "ENG202" from dataset D;

[0153] Get the teaching materials information with object ID "ENG202" from the label dataset (Table 1);

[0154] Merge the object information with the data set D to form an event record E = D∪{object type, object attribute};

[0155] Event record format: expressed in JSON format;

[0156] Assume that in the past 7 days, Zhang San has used English reading comprehension teaching materials many times, and the event records are as follows:

[0157] Table 6. Zhang San's event record

[0158]

[0159] Calculate the number of occurrences N 出现次数 :

[0160] In the past 7 days (Δt = 7 days), Zhang San used English reading comprehension teaching materials 7 times, that is, N 出现次数 =7;

[0161] Calculate the frequency f:

[0162]

[0163] Match the entry and exit times and calculate the residence time τ:

[0164]

[0165] Extract other behavioral features:

[0166] Assume that Zhang San also used Mathematics Synchronous Practice (MATH101) during this period, and used a total of 2 teaching materials, N 材料种类 =2;

[0167] Study duration in different time periods:

[0168] Morning (6:00-12:00): 135 minutes in total (30+30+30+45);

[0169] Afternoon (12:00-18:00): 105 minutes in total (45+30+30);

[0170] Night (18:00-24:00): 0 minutes;

[0171] Construct the feature vector:

[0172] X=[f,τ,N 材料种类 ,T 上午 ,T 下午 ,T 晚上 ]=[1,240,2,135,105,0]

[0173] Predict Zhang San's feature vector:

[0174] Target variable Y: student learning effect indicator, such as English test score (0-100 points);

[0175] Use the random forest algorithm to train the prediction model RF, i.e. RF:X→Y;

[0176] Input: Zhang San’s feature vector X = [1,240,2,135,105,0];

[0177] Prediction results:

[0178]

[0179] That is, predict that Zhang San's English test score is 85 points;

[0180] For example, according to the range of predicted values, it can be known that:

[0181] When learning, the effect is excellent;

[0182] When learning is good,

[0183] When learning, the effect needs to be improved.

[0184] As an example, based on the prediction of Zhang San's English test score mentioned above, the generated personalized learning suggestions are analyzed through the feature contribution degree analysis "The model shows that the evening study time has a greater impact on the score, but Zhang San's evening study time is 0". It can be seen that the suggestion content is: increase the evening study time, that is, it is recommended that Zhang San increase the study time in the evening (such as arranging 30 minutes of English reading time in the evening).

[0185] It should be noted that this embodiment inputs the parameters involved in the above-mentioned application scenario into the MATLAB simulation software and runs it (after adjustment) to verify the relationship between the total learning time and the predicted score. Before inputting the example data of the application scenario of this embodiment, a simulation is performed on the recorded data of Zhang San's learning of teaching materials in the school-based teaching system (before adjustment) to verify that the data collection and feedback method provided by this embodiment can help students learn more effectively.

[0186] Reference Figure 2 Before the adjustment, Zhang San’s study time and predicted scores showed a gentle growth trend. After applying the method of the present invention, as the total study time increased, the predicted scores significantly improved, and the growth trend became more obvious. This shows that the method of the present invention not only helps students increase their study time, but more importantly, improves their learning efficiency.

[0187] It should be noted that some other aspects disclosed in the embodiments of the present invention further provide a data acquisition device for a school-based teaching auxiliary system, including:

[0188] The electronic tag module is used to embed smart ID tags on teaching materials to provide unique identification. The smart ID tags use ultra-high frequency RFID tags to achieve long-distance reading;

[0189] The reader / writer module includes an intelligent reader / writer for reading the electronic tag information and generating a raw data record including an object ID, a timestamp and a location ID;

[0190] A data transmission module is used to transmit the collected raw data records to the data acquisition server in real time through a communication protocol;

[0191] Data processing module, including hardware and software components for data preprocessing, data association, and data analysis and processing, configured with edge computing capabilities;

[0192] User interaction module, including display and terminal equipment, used to present analysis results to users and support multi-terminal access;

[0193] Among them, the reader / writer module supports Wi-Fi, Ethernet and LoRa communication protocols to adapt to different network environments.

[0194] Furthermore, the data acquisition device also includes one or more processors and a memory.

[0195] The memory is used to store operable instructions, which, when executed by the one or more processors, cause the one or more processors to perform operations, including the process of the data collection method for the school-based teaching system of the aforementioned embodiment, especially Figure 1 The process of the method shown.

[0196] In other aspects disclosed in the embodiments of the present invention, a computer-readable medium storing software is provided. The software includes instructions that can be executed by one or more computers. The instructions enable one or more computers to perform operations through such execution. The operations include the process of the data collection method for the school-based teaching system of the aforementioned embodiment, especially Figure 1 The process of the method shown.

[0197] It should be appreciated that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory.

[0198] The method may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes a computer to operate in a specific and predefined manner.

[0199] Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system, however, the program can be implemented in assembly or machine language if desired.

[0200] In any case, the language may be a compiled or interpreted language.

[0201] Furthermore, the program can be run on an application specific integrated circuit programmed for this purpose.

[0202] The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that can be executed by one or more processors.

[0203] Further, the method may be implemented in any type of computing platform operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device.

[0204] Various aspects of the present invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage media, RAM, ROM, etc., so that it can be read by a programmable computer, which, when the storage medium or device is read by the computer, can be used to configure and operate the computer to perform the processes described herein.

[0205] Additionally, the machine-readable code, or portions thereof, can be transmitted over a wired or wireless network.

[0206] The invention described herein includes these and other various types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor.

[0207] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A data collection method for a school-based teaching system, characterized in that: include: Embed a smart ID tag with a unique identifier on the teaching materials, and enter the information of each electronic tag into the database of the school-based teaching system to form a corresponding tag data set; Using an intelligent reader to read the smart ID tag on the teaching material, generating a raw data record including an object ID, a timestamp, and a location ID; The raw data records are transmitted to a data acquisition server in real time through a communication protocol, and the data acquisition server performs data cleaning and data formatting on the received raw data records to form a data set D={object ID, T, location ID} in a unified format; According to the object ID, the original data record is associated with the object information in the database to form a complete event record E=D∪{object type, object attribute}; Performing behavior frequency statistics and residence time calculation on the event record E to extract the learning behavior characteristics of the students; Construct a feature vector X = [f, τ, other behavioral features], use the random forest algorithm to train a prediction model for predicting students' learning effects, and predict the data to be predicted to generate personalized learning suggestions.

2. The data collection method for a school-based teaching system according to claim 1, characterized in that: The tag information of the smart ID tag at least includes a tag ID with a unique identifier, a subject, and a grade; The label information is entered into a database in the school-based teaching aid system to form a label data set.

3. The data collection method for a school-based teaching system according to claim 1, characterized in that: The generated original data record contains at least an object ID, a timestamp T, and a location ID; Among them, the object ID is the unique identifier of the electronic tag, the timestamp T is the exact time of reading, and the location ID is the location of the reader.

4. The data collection method for a school-based teaching system according to claim 1, characterized in that: The behavior characteristics of the students in the event record E include the behavior frequency and the duration of stay. The behavior frequency statistics include: Count the frequency of an object in a specific time period: Among them, N 出现次数 is the total number of times the object appears in the time period Δt, where Δt is the length of the time period.

5. The data collection method for a school-based teaching system according to claim 4, characterized in that: The calculation of the duration of stay includes: Where n is the number of entry to exit events, and are the timestamps of the i-th entry and exit, respectively.

6. The data collection method for a school-based teaching system according to claim 4, characterized in that: According to the behavior characteristics of the behavior frequency and the stay duration, a feature vector is constructed: X=[f,τ,N 材料种类 ,T 早晨 ,T 下午 ,T 晚上 ] Among them, N 材料种类 is the number of teaching materials used, T 早晨 , T 下午 , T 晚上 Indicates the length of study in different time periods; Build a prediction model based on the random forest algorithm and perform model training RF:X→Y; Use the trained prediction model to predict the new feature vector X new Make predictions: Among them, Y is the student’s learning effect indicator, The predicted value of the student's learning effect indicator.

7. The data collection method for a school-based teaching system according to claim 6, characterized in that: The predicted value The value range of is: When learning, the effect is excellent; When learning is good, When learning, the effect needs to be improved.

8. A data acquisition device for a school-based teaching system, characterized in that: include: The electronic tag module is used to embed a smart ID tag on the teaching materials to provide a unique identification. The smart ID tag adopts an ultra-high frequency RFID tag to achieve long-distance reading; The reader / writer module includes an intelligent reader / writer for reading the electronic tag information and generating a raw data record including an object ID, a timestamp and a location ID; A data transmission module is used to transmit the collected raw data records to the data acquisition server in real time through a communication protocol; Data processing module, including hardware and software components for data preprocessing, data association, and data analysis and processing, configured with edge computing capabilities; User interaction module, including display and terminal equipment, used to present analysis results to users and support multi-terminal access; Among them, the reader / writer module supports Wi-Fi, Ethernet and LoRa communication protocols and adapts to different network environments.

9. The data acquisition device for the school-based teaching system according to claim 8, characterized in that: Also includes: one or more processors; A memory storing operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors perform operations, wherein the operations include the process of the data collection method for a school-based teaching auxiliary system as described in any one of claims 1 to 7.

10. A computer-readable medium storing software, characterized in that: The software includes instructions that can be executed by one or more computers, and the instructions enable the one or more computers to perform operations through such execution, and the operations include the process of the data collection method for a school-based teaching auxiliary system as described in any one of claims 1 to 7.

Images