Electronic student identity card intelligent early warning system and method based on AI technology

Abstract

The invention discloses an electronic student identity card intelligent early warning system and method based on an AI technology. The system comprises a data acquisition module, a data processing and storage module, a feature extraction module, an AI analysis module, an early warning mechanism module, a user interface module, a notification and feedback module, a decision support module and a security and privacy protection module. The security and privacy protection module is connected with the data acquisition module, the data processing and storage module, the feature extraction module, the AI analysis module, the early warning mechanism module, the notification and feedback module and the decision support module. Potential risks and abnormal conditions of students can be recognized and analyzed in time by collecting various data of the students and combining the AI technology, early warning information is generated to inform related personnel in time, decision support can be provided for a school management layer according to the abnormal conditions of the students, guardians and teachers can conveniently and timely educate the students, and the students can be conveniently and rapidly managed. And the early warning intelligence degree is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic student card intelligent early warning systems, and in particular to an electronic student card intelligent early warning system and method based on AI technology. Background Art

[0002] An electronic student ID card is a student ID card that has a high-tech chip installed on it based on an ordinary student ID card. It records the student's photo, name, age, etc. and contains a GPS positioning system. With the development of electronic technology, campuses are gradually moving towards informatization. Electronic student ID cards are one of the manifestations of campus informatization. Because mobile phones are limited to campus, electronic student ID cards can help solve the call needs of students and parents, and provide family calls, safe positioning, convenient life and other services for home-school interconnection. In addition, with the intelligent early warning system of electronic student ID cards, it is convenient for personnel to know the location of students in a timely manner;

[0003] The existing electronic student ID intelligent early warning system still has the following problems: it only has a single positioning early warning function, and its intelligence level has not been significantly improved. It cannot automatically analyze and predict potential risks and abnormal behaviors based on students' behavioral habits and locations. When students exhibit abnormal behaviors and risks, guardians and teachers cannot know in time, and thus cannot educate students in time. For this reason, we propose an electronic student ID intelligent early warning system and method based on AI technology. Summary of the invention

[0004] Based on the technical problems existing in the background technology, the present invention proposes an intelligent early warning system and method for electronic student ID cards based on AI technology.

[0005] The present invention proposes an intelligent early warning system for electronic student ID cards based on AI technology, including a data acquisition module, a data processing and storage module, a feature extraction module, an AI analysis module, an early warning mechanism module, a user interface module, a notification and feedback module, a decision support module, and a security and privacy protection module;

[0006] The security and privacy protection module is connected with the data acquisition module, the data processing and storage module, the feature extraction module, the AI ​​analysis module, the early warning mechanism module, the notification and feedback module and the decision support module;

[0007] The data processing and storage module is connected to the data acquisition module and the feature extraction module, the AI ​​analysis module is connected to the feature extraction module, the user interface module and the early warning mechanism module, and the notification and feedback module is connected to the early warning mechanism module and the decision support module.

[0008] Preferably, the data collection module is used to collect various data of students, including attendance records, time and place of entering and leaving the campus, behavioral habits and mental health information, etc.

[0009] Preferably, the data processing and storage module is used to perform data cleaning, format conversion and deduplication processing on the collected data, and the processed data is stored and managed using a database.

[0010] Preferably, the feature extraction module is used to extract useful features from the processed data, including absence frequency, abnormal entry and exit patterns, and changes in social behavior;

[0011] The mathematical expression used to calculate the absence frequency is:

[0012] When calculating the entry and exit distances, it is necessary to calculate the distance between two points. The mathematical expression used is: Where x and y represent the locations of two sampling points, and d represents the distance between the two points.

[0013] Preferably, the AI ​​analysis module is used to build an abnormal prediction model, and adopts machine learning or deep learning algorithms to train the model, and analyzes and mines new data monitored in real time to identify potential risks and abnormal behaviors;

[0014] The logical steps in building a training prediction model are as follows:

[0015] S101: Encode the extracted features, standardize or normalize the numerical features so that different features are on the same scale, and divide the data set into a training set, a validation set, and a test set, where 80% of the data is used as a training set and 20%-30% of the data is used as a validation and test set;

[0016] S102: Select a deep learning algorithm to build an abnormality prediction model, and set hyperparameters of the model;

[0017] S103: Use the training set to train the model built in S102, and use the validation set to monitor the performance of the model and adjust the hyperparameters to avoid overfitting;

[0018] S104: Use the test set to evaluate the model performance and calculate relevant indicators, including accuracy, precision and recall. The effectiveness of the model is determined based on the evaluation results.

[0019] The calculation formula for accuracy is:

[0020] The calculation formula for accuracy is:

[0021] The calculation formula for recall is:

[0022] TP represents the number of actual abnormalities that are correctly identified as abnormal by the model; FP represents the number of actual normals that are incorrectly identified as abnormal by the model; TN represents the number of actual normals that are correctly identified as normal by the model; FN represents the number of actual abnormalities that are incorrectly identified as normal by the model;

[0023] S105: Based on the evaluation results, perform model optimization and deploy the trained and optimized model to the environment.

[0024] Preferably, the warning mechanism module is used to set warning rules and thresholds according to the analysis results of the AI ​​analysis module, automatically generate warning information, and set a certain probability threshold to determine whether to issue a warning based on the prediction results of the abnormal prediction model. When the model predicts that a student has a 70% chance of being absent, a warning is triggered. When a student is absent for more than 3 consecutive days or more than 5 times in a semester, the warning information is:

[0025] Student name: the student who was warned;

[0026] Warning reason: absence;

[0027] Trigger time: the time when the abnormal situation occurs;

[0028] Recommended measures: It is recommended to communicate with a counselor and attend counseling courses.

[0029] Preferably, the notification and feedback module is used to send the warning information to relevant personnel through SMS, email or mobile phone application. The recipient can feedback the warning information through the notification and feedback module and update the student status. In addition, the relevant personnel can be teachers, parents and counselors, etc.

[0030] The decision support module provides decision support to the school management based on the early warning information and related data, and recommends necessary intervention measures, such as psychological counseling and safety education;

[0031] The security and privacy protection module is used to ensure the security of data transmission and storage, implement privacy protection measures, and protect the security of students' personal information. The privacy protection measures implemented can be data encryption and access control, using TLS / SSL protocol to encrypt data transmission to ensure that data is not stolen or tampered with during network transmission, and implementing a strong identity authentication mechanism to ensure that only authorized users can access sensitive data;

[0032] The user interface module is used to provide an intuitive user interface for students, teachers and administrators to use, and to display real-time data, warning information and historical records.

[0033] The present invention also proposes an intelligent early warning method for electronic student ID cards based on AI technology, comprising the following steps:

[0034] S1: The data collection module collects various student data in real time through the sensors and positioning modules on the electronic student ID card, including attendance records, time and location of entering and leaving the campus, walking habits and mental health information;

[0035] S2: Clean, convert and remove duplicate data to ensure data quality and consistency;

[0036] S3: Extract useful features from the processed data, including absence frequency, abnormal entry and exit patterns, changes in social behavior, etc.

[0037] S4: The AI ​​analysis module builds an abnormality prediction model and trains the model using machine learning or deep learning algorithms;

[0038] S5: The AI ​​analysis module monitors new data in real time and inputs it into the trained anomaly prediction model for analysis. It identifies potential risks and anomalies by comparing the current data with the expected data of the anomaly prediction model.

[0039] S6: When abnormal behavior or risk is detected, the early warning mechanism module sets early warning rules and thresholds, and automatically generates early warning information according to the set early warning rules and thresholds;

[0040] S7: The notification and feedback module sends the warning information generated in S6 to relevant personnel through SMS, email, and mobile application push. At the same time, the recipient can provide feedback on the warning information and update the student status;

[0041] S8: The decision support module provides decision support to school management based on early warning information and related data, and recommends necessary intervention measures, such as psychological counseling and safety education.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] By collecting various data of students and combining it with AI technology, the present invention can timely identify and analyze students' potential risks and abnormal situations, and generate early warning information to notify relevant personnel in a timely manner. In addition, it can also provide decision-making support for school management based on students' abnormal situations, making it convenient for guardians and teachers to educate students in a timely manner and improving the intelligence level of early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a block diagram of an intelligent early warning system for electronic student ID cards based on AI technology proposed by the present invention;

[0045] Figure 2 This is a flow chart of an intelligent early warning method for electronic student ID cards based on AI technology proposed by the present invention. DETAILED DESCRIPTION

[0046] The present invention will be further explained below in conjunction with specific embodiments.

[0047] Example

[0048] Reference Figure 1 ,This embodiment proposes an intelligent early warning system for electronic student cards based on AI technology, including a data acquisition module, a data processing and storage module, a feature extraction module, an AI analysis module, an early warning mechanism module, a user interface module, a notification and feedback module, a decision support module, and a security and privacy protection module;

[0049] The security and privacy protection module is connected with the data acquisition module, the data processing and storage module, the feature extraction module, the AI ​​analysis module, the early warning mechanism module, the notification and feedback module, and the decision support module;

[0050] The data processing and storage module is connected with the data acquisition module and the feature extraction module, the AI ​​analysis module is connected with the feature extraction module, the user interface module and the early warning mechanism module, and the notification and feedback module is connected with the early warning mechanism module and the decision support module;

[0051] The data collection module is used to collect various data of students, including attendance records, time and place of entering and leaving the campus, behavioral habits and mental health information, etc. The data processing and storage module is used to clean the collected data, convert the format and remove duplicates, and the processed data is stored and managed using a database;

[0052] The feature extraction module is used to extract useful features from the processed data, including absence frequency, abnormal entry and exit patterns, and changes in social behavior;

[0053] The mathematical expression used to calculate the absence frequency is:

[0054] When calculating the entry and exit distances, it is necessary to calculate the distance between two points. The mathematical expression used is: Where x and y represent the locations of two sampling points, and d represents the distance between the two points;

[0055] The AI ​​analysis module is used to build anomaly prediction models and use machine learning or deep learning algorithms to train the models. It also analyzes and mines new data from real-time monitoring to identify potential risks and abnormal behaviors.

[0056] The logical steps in building a training prediction model are as follows:

[0057] S101: Encode the extracted features, standardize or normalize the numerical features so that different features are on the same scale, and divide the data set into a training set, a validation set, and a test set, where 80% of the data is used as a training set and 20%-30% of the data is used as a validation and test set;

[0058] S102: Select a deep learning algorithm to build an abnormality prediction model, and set hyperparameters of the model;

[0059] The hyperparameters of the model include learning rate, batch size, number of training rounds, number of hidden layers and units, activation function, regularization method, optimizer and loss function. The learning rate is set to 0.01, the batch size is 32, 64 or 128, the number of training rounds is 50 to 200, the number of hidden layers and units starts from 1-3 layers, and the number of units in each layer can be set to 64, 128, 256, etc. The activation function uses the ReLU function, the regularization method uses L2 regularization, and its common value is 0.01 or 0.001, the optimizer uses Adam, and the loss function uses the mean square error function;

[0060] S103: Use the training set to train the model built in S102, and use the validation set to monitor the performance of the model and adjust the hyperparameters to avoid overfitting;

[0061] S104: Use the test set to evaluate the model performance and calculate relevant indicators, including accuracy, precision and recall. The effectiveness of the model is determined based on the evaluation results.

[0062] The calculation formula for accuracy is:

[0063] The calculation formula for accuracy is:

[0064] The calculation formula for recall is:

[0065] TP represents the number of actual abnormalities that are correctly identified as abnormal by the model; FP represents the number of actual normals that are incorrectly identified as abnormal by the model; TN represents the number of actual normals that are correctly identified as normal by the model; FN represents the number of actual abnormalities that are incorrectly identified as normal by the model;

[0066] S105: Optimize the model based on the evaluation results, and deploy the trained and optimized model to the environment;

[0067] When making predictions, the abnormal prediction model inputs the student's absence records, academic performance and other features into the model. The abnormal prediction model will predict whether the student's absence is "abnormal". If it is 0, it is normal, and if it is 1, it is abnormal. For example, if the student is absent for 3 days this week, the participation score is low, and the homework completion rate is 50%, the prediction output result is "1" abnormal, which may indicate that the student needs attention;

[0068] The early warning mechanism module is used to set early warning rules and thresholds according to the analysis results of the AI ​​analysis module, automatically generate early warning information, and set a certain probability threshold to determine whether to issue an early warning based on the prediction results of the abnormal prediction model. When the model predicts that a student has a 70% chance of being absent, an early warning is triggered. When a student is absent for more than 3 consecutive days or more than 5 times in a semester, the early warning information is:

[0069] Student name: the student who was warned;

[0070] Warning reason: absence;

[0071] Trigger time: the time when the abnormal situation occurs;

[0072] Recommended actions: It is recommended to communicate with a counselor and attend counseling courses;

[0073] The notification and feedback module is used to send warning information to relevant personnel through text messages, emails or mobile phone applications. The recipients can provide feedback on the warning information through the notification and feedback module and update the student status. In addition, the relevant personnel can be teachers, parents, counselors, etc.; the decision support module provides decision support to the school management based on the warning information and related data, and recommends necessary intervention measures, such as psychological counseling and safety education; the security and privacy protection module is used to ensure the security of data transmission and storage, implement privacy protection measures, and ensure the security of students' personal information. The privacy protection measures implemented can be data encryption and access control, using TLS / SSL protocol to encrypt data transmission to ensure that data is not stolen or tampered with during network transmission, and implement strong identity authentication mechanisms to ensure that only authorized users can access sensitive data; the user interface module is used to provide an intuitive user interface for students, teachers and administrators to display real-time data, warning information and historical records.

[0074] Reference Figure 2 This embodiment also proposes an intelligent early warning method for electronic student ID cards based on AI technology, including the following steps:

[0075] S1: The data collection module collects various student data in real time through the sensors and positioning modules on the electronic student ID card, including attendance records, time and location of entering and leaving the campus, walking habits and mental health information;

[0076] S2: Clean, convert and remove duplicate data to ensure data quality and consistency;

[0077] S3: Extract useful features from the processed data, including absence frequency, abnormal entry and exit patterns, changes in social behavior, etc.

[0078] S4: The AI ​​analysis module builds an abnormality prediction model and trains the model using machine learning or deep learning algorithms;

[0079] S5: The AI ​​analysis module monitors new data in real time and inputs it into the trained anomaly prediction model for analysis. It identifies potential risks and anomalies by comparing the current data with the expected data of the anomaly prediction model.

[0080] S6: When abnormal behavior or risk is detected, the early warning mechanism module sets early warning rules and thresholds, and automatically generates early warning information according to the set early warning rules and thresholds;

[0081] S7: The notification and feedback module sends the warning information generated in S6 to relevant personnel through SMS, email, and mobile application push. At the same time, the recipient can provide feedback on the warning information and update the student status;

[0082] S8: The decision support module provides decision support to school management based on early warning information and related data, and recommends necessary intervention measures, such as psychological counseling and safety education.

[0083] This embodiment collects various data of students and combines it with AI technology to timely identify and analyze students' potential risks and abnormal situations, and generates early warning information to notify relevant personnel in a timely manner. In addition, it can also provide decision-making support for school management based on students' abnormal situations, making it convenient for guardians and teachers to educate students in a timely manner and improve the intelligence level of early warning.

[0084] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent early warning system for electronic student ID cards based on AI technology, characterized in that: It includes data collection module, data processing and storage module, feature extraction module, AI analysis module, early warning mechanism module, user interface module, notification and feedback module, decision support module and security and privacy protection module; The security and privacy protection module is connected with the data acquisition module, the data processing and storage module, the feature extraction module, the AI ​​analysis module, the early warning mechanism module, the notification and feedback module and the decision support module; The data processing and storage module is connected to the data acquisition module and the feature extraction module, the AI ​​analysis module is connected to the feature extraction module, the user interface module and the early warning mechanism module, and the notification and feedback module is connected to the early warning mechanism module and the decision support module.

2. According to claim 1, an AI-based electronic student ID intelligent early warning system is characterized in that: The data collection module is used to collect various data of students, including attendance records, time and place of entering and leaving the campus, behavioral habits and mental health information.

3. According to the AI-based electronic student ID intelligent early warning system of claim 1, it is characterized in that: The data processing and storage module is used to perform data cleaning, format conversion and deduplication processing on the collected data, and the processed data is stored and managed using a database.

4. According to the AI-based electronic student ID intelligent early warning system of claim 1, it is characterized in that: The feature extraction module is used to extract useful features from the processed data, including absence frequency, abnormal entry and exit patterns, and social behavior changes; The mathematical expression used to calculate the absence frequency is: When calculating the entry and exit distance, it is necessary to calculate the distance between two points. The mathematical expression used is: Where x and y represent the locations of two sampling points, and d represents the distance between the two points.

5. According to the AI-based electronic student ID intelligent early warning system of claim 1, it is characterized in that: The AI ​​analysis module is used to build an abnormal prediction model, and use machine learning or deep learning algorithms to train the model, and analyze and mine new data in combination with real-time monitoring to identify potential risks and abnormal behaviors; The logical steps in building a training prediction model are as follows: S101: Encode the extracted features, standardize or normalize the numerical features so that different features are on the same scale, and divide the data set into a training set, a validation set, and a test set, where 80% of the data is used as a training set and 20%-30% of the data is used as a validation and test set; S102: Select a deep learning algorithm to build an abnormality prediction model, and set hyperparameters of the model; S103: Use the training set to train the model built in S102, and use the validation set to monitor the performance of the model and adjust the hyperparameters to avoid overfitting; S104: Use the test set to evaluate the model performance and calculate relevant indicators, including accuracy, precision and recall. The effectiveness of the model is determined based on the evaluation results. The calculation formula for accuracy is: The calculation formula for accuracy is: The calculation formula for recall is: TP represents the number of actual abnormalities that are correctly identified as abnormal by the model; FP represents the number of actual normals that are incorrectly identified as abnormal by the model; TN represents the number of actual normals that are correctly identified as normal by the model; FN represents the number of actual abnormalities that are incorrectly identified as normal by the model; S105: Based on the evaluation results, perform model optimization and deploy the trained and optimized model to the environment.

6. According to the AI-based electronic student ID intelligent early warning system of claim 1, it is characterized in that: The warning mechanism module is used to set warning rules and thresholds according to the analysis results of the AI ​​analysis module, automatically generate warning information, and set a certain probability threshold to determine whether to issue a warning based on the prediction results of the abnormal prediction model. When the model predicts that a student has a 70% chance of being absent, a warning is triggered. When a student is absent for more than 3 consecutive days or more than 5 times in a semester, the warning information is: Student name: the student who was warned; Warning reason: absence; Trigger time: the time when the abnormal situation occurs; Recommended measures: It is recommended to communicate with a counselor and attend counseling courses.

7. According to claim 1, the intelligent early warning system for electronic student ID cards based on AI technology is characterized in that: The notification and feedback module is used to send the warning information to relevant personnel through SMS, email or mobile phone application. The recipient can provide feedback on the warning information and update the student status through the notification and feedback module. In addition, the relevant personnel can be teachers, parents and counselors; The decision support module provides decision support to the school management based on the early warning information and relevant data, and recommends necessary intervention measures; The security and privacy protection module is used to ensure the security of data transmission and storage, implement privacy protection measures, and protect the security of students' personal information. The privacy protection measures implemented can be data encryption and access control, using TLS / SSL protocol to encrypt data transmission to ensure that data is not stolen or tampered with during network transmission, and implementing a strong identity authentication mechanism to ensure that only authorized users can access sensitive data; The user interface module is used to provide an intuitive user interface for students, teachers and administrators to use, and to display real-time data, warning information and historical records.

8. An intelligent early warning method for electronic student ID cards based on AI technology, characterized in that: The following steps are involved: S1: The data collection module collects various student data in real time through the sensors and positioning modules on the electronic student ID card, including attendance records, time and location of entering and leaving the campus, walking habits and mental health information; S2: Clean, convert and remove duplicate data to ensure data quality and consistency; S3: Extract useful features from the processed data, including absence frequency, abnormal entry and exit patterns, and changes in social behavior; S4: The AI ​​analysis module builds an abnormality prediction model and trains the model using machine learning or deep learning algorithms; S5: The AI ​​analysis module monitors new data in real time and inputs it into the trained anomaly prediction model for analysis. It identifies potential risks and anomalies by comparing the current data with the expected data of the anomaly prediction model. S6: When abnormal behavior or risk is detected, the early warning mechanism module sets early warning rules and thresholds, and automatically generates early warning information according to the set early warning rules and thresholds; S7: The notification and feedback module sends the warning information generated in S6 to relevant personnel through SMS, email, and mobile application push. At the same time, the recipient can provide feedback on the warning information and update the student status; S8: The decision support module provides decision support to school management based on early warning information and related data, and recommends necessary intervention measures.

Images