Student mental health monitoring and early warning system based on big data and artificial intelligence

Abstract

The present invention discloses a student mental health monitoring and early warning system based on big data and artificial intelligence, and relates to the field of electronic digital data processing technology. The student mental health monitoring and early warning system based on big data and artificial intelligence includes: a first data acquisition module, a first judgment module, a second judgment module, a third judgment module and a fourth judgment module. The present invention obtains the first student data through the main data source to obtain the first classification result and then evaluates to obtain the first data quality. If the first data quality and the first data quantity evaluation value do not meet the standard, the second student data obtained from the auxiliary data source obtains the second data quality. If the second data quality and the second data quantity evaluation value do not meet the standard, a warning signal is triggered, otherwise it indicates that the data has diversity, thereby achieving an improvement in the diversity of data acquisition, and solving the problem of single data in the student psychological data acquisition system in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a student mental health monitoring and early warning system based on big data and artificial intelligence. Background Art

[0002] In today's educational environment, students' mental health issues are increasingly receiving widespread attention. However, with the rapid development of big data and artificial intelligence technologies, more and more educational and medical institutions are beginning to explore how to use these technologies to improve mental health services. The mental health monitoring systems used by many schools and educational institutions still rely mainly on a single data source, which can easily lead to a one-sided interpretation of students' mental health and ignore potential psychological distress. Multi-dimensional data can help build a more three-dimensional and dynamic mental health portrait, thereby discovering potential risks earlier. Therefore, adopting a diversified data collection and analysis method is the key to ensuring students' mental health.

[0003] In the existing technology, data is used to build a model to predict students' mental health risks. The system continuously monitors students' relevant data and can issue timely warnings when abnormal situations are detected, thereby monitoring students' mental health conditions and providing early warnings.

[0004] For example, the invention patent with announcement number: CN114780995B discloses an Internet-based student mental health archive encryption management system and method, including: a student mental health data fitness acquisition module, a student mental health data calibration module, and an encryption and early warning module; the student mental health data fitness acquisition module is used to obtain the fitness between the mental health data corresponding to different students; the student mental health data calibration module calibrates the collected data in the student mental health data collection module according to the results obtained by the student mental health data fitness acquisition module, and obtains the calibrated student mental health data; the encryption and early warning module encrypts the calibrated student mental health data and saves it in the database, analyzes the calibrated student mental health data, and provides feedback to teachers and parents on the unqualified calibrated student mental health data and the corresponding students.

[0005] For example, the intelligent monitoring system for mental health index announced by the invention patent with announcement number: CN103914800B includes: a first-level monitoring device and a second-level monitoring device. The first-level monitoring device includes a first psychological factor calculation modeling module and a mental health index primary processing module that are interconnected. The mental health index primary processing module is connected to the second-level monitoring device; the second-level monitoring device includes a second psychological factor calculation modeling module and a mental health index secondary processing module that are interconnected.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the existing technology, due to the limitations of data collection, most systems rely solely on psychological assessment results. This single data source may not be able to fully and deeply reflect the students' psychological state. Data in other key dimensions also have an important impact on the students' psychological state. There is a problem of single data in the student psychological data collection system. Summary of the invention

[0008] The embodiment of the present application solves the problem of single data in the student psychological data collection system in the prior art by providing a student mental health monitoring and early warning system based on big data and artificial intelligence, and achieves an improvement in the diversity of data collection.

[0009] The embodiment of the present application provides a student mental health monitoring and early warning system based on big data and artificial intelligence, including: a first data acquisition module, a first judgment module, a second judgment module, a third judgment module and a fourth judgment module; the first data acquisition module is used to obtain the first student data of the student to be monitored within a preset time period through the main data source, classify the obtained first student data according to the preset classification standard to obtain the first classification result, and then evaluate to obtain the first data quality, the main data source is a mental education platform constructed according to the platform used by the students at school, and the main data source includes learning platform data, psychological platform data, and social platform data; the first judgment module is used to compare the first data quality with the historical data to obtain a first data quantity evaluation value when the first data quality does not meet the preset data standard; the second judgment module is used to compare the first data quality with the historical data to obtain a first data quantity evaluation value when the first data quantity evaluation value does not meet the preset data standard When setting an evaluation value, the second student data of the student to be monitored within a preset time period obtained through the auxiliary data source is merged with the first student data to obtain the third student data, and the third student data is classified according to the preset classification standard to obtain the second classification result, and then evaluated to obtain the second data quality. The auxiliary data source represents an external data source used to supplement the main data source, and the auxiliary data source includes monitoring data, questionnaire data and classroom external activity data; the third judgment module is used to compare the second data quality that does not meet the preset data standard with the historical data to obtain a second data quantity evaluation value when the second data quality does not meet the preset data standard; the fourth judgment module is used to feedback that the data has diversity when the first data quality meets the preset data standard and the second data quality meets the preset data standard, and trigger a warning signal when the second data quantity evaluation value does not meet the preset evaluation value.

[0010] Furthermore, the first data acquisition module includes a first data acquisition unit, a first data classification unit and a first data evaluation unit; the first data acquisition unit is used to acquire first student data through a main data source, and transmit the acquired first student data to the first data classification unit; the first data classification unit is used to classify and preprocess the received first student data according to a preset classification standard to obtain a first classification result, and transmit the obtained first classification result to the first data evaluation unit, the first classification result includes first learning data, first social data and first psychological data; the first data evaluation unit is used to evaluate the received first classification result to obtain first data quality, and the first data quality is used to quantitatively evaluate the diversity of data.

[0011] Furthermore, the first data quality includes a first data integrity coefficient and a first data timeliness coefficient, and the specific method for obtaining the first data integrity coefficient is as follows: E1, obtaining preset student data from a preset database, when the first classification result meets the data missing condition, the first data integrity coefficient is recorded as 0, otherwise execute E2; E2, when the first classification result meets the first data missing condition, the first data integrity coefficient is obtained according to the ratio of the first learning data quantity to the preset learning data quantity and the ratio of the first psychological data quantity to the preset psychological data quantity, otherwise execute E3; E3, when the first classification result meets the second data missing condition, the first data integrity coefficient is obtained according to the ratio of the first learning data quantity to the preset learning data quantity and the ratio of the first social The first data integrity coefficient is obtained by the ratio of the number of data to the preset number of social data, otherwise E4 is executed; E4, when the first classification result meets the third data missing condition, the first data integrity coefficient is obtained according to the ratio of the first psychological data number to the preset psychological data number and the ratio of the first social data number to the preset social data number, otherwise E5 is executed, and the first data integrity coefficient is used to quantitatively evaluate the integrity of data acquisition; E5, the first data integrity coefficient is obtained according to the ratio of the first learning data number to the preset learning data number, the ratio of the first psychological data number to the preset psychological data number, and the ratio of the first social data number to the preset social data number; the first data integrity coefficient is calculated by the following formula:

[0012] ;

[0013] In the formula, i is the number of the student to be monitored, , N represents the total number of students to be monitored, represents the first data completeness coefficient of the i-th student to be monitored, represents the number of first psychological data of the i-th student to be monitored, represents the number of first learning data of the i-th student to be monitored, represents the number of first social data of the i-th student to be monitored, Indicates the number of preset psychological data, Indicates the preset number of learning data. Represents the preset amount of social data; the specific method of obtaining the first data timeliness coefficient is as follows: the acquisition time of the first student data is recorded in real time to obtain the first updated data amount, and the first data timeliness coefficient is obtained according to the ratio of the first updated data amount to the total amount of the first data set. The first data timeliness coefficient is used to quantify the timeliness of data acquisition.

[0014] Furthermore, the second data quality includes a second data integrity coefficient and a second data timeliness coefficient, and the specific method for obtaining the second data integrity coefficient is as follows: F1, obtaining preset student data from a preset database, and when the second classification result meets the data serious missing condition, recording the second data integrity coefficient as 0, otherwise executing F2; F2, when the second classification result meets the first data serious missing condition, obtaining the second data integrity coefficient according to the ratio of the second learning data quantity to the preset learning data quantity and the ratio of the second psychological data quantity to the preset psychological data quantity, otherwise executing F3; F3, when the second classification result meets the second data serious missing condition, obtaining the second data integrity coefficient according to the ratio of the second learning data quantity to the preset learning data quantity and the ratio of the second psychological data quantity to the preset psychological data quantity The ratio of the number of social data to the preset number of social data is used to obtain the second data integrity coefficient, otherwise F4 is executed; F4, when the second classification result meets the third data serious missing condition, the second data integrity coefficient is obtained according to the ratio of the number of second psychological data to the preset number of psychological data and the ratio of the number of second social data to the preset number of social data, otherwise F5 is executed, and the second data integrity coefficient is used to quantitatively evaluate the integrity of data acquisition; F5, the second data integrity coefficient is obtained according to the ratio of the number of second learning data to the preset number of learning data, the ratio of the number of second psychological data to the preset number of psychological data, and the ratio of the number of second social data to the preset number of social data; the second data integrity coefficient is calculated by the following formula:

[0015] ;

[0016] In the formula, represents the second data completeness coefficient of the i-th student to be monitored, represents the number of second psychological data of the i-th student to be monitored, represents the number of second learning data of the i-th student to be monitored, represents the number of the second social data of the i-th student to be monitored;

[0017] The specific method for obtaining the second data timeliness coefficient is as follows: the second updated data volume is obtained by recording the acquisition time of the second student data in real time, and the second data timeliness coefficient is obtained according to the ratio of the second updated data volume to the total number of second data sets. The second data timeliness coefficient is used to quantify the timeliness of data acquisition.

[0018] Furthermore, when the first data quality does not meet the preset data standard, the first data quality is compared with the historical data to obtain a first data quantity evaluation value, specifically: B1, the first classification result is evaluated to obtain the first data quality, and whether the first data timeliness coefficient obtained meets the preset data timeliness standard. If the first data timeliness coefficient obtained meets the preset data timeliness standard, B2 is executed, otherwise the second student data is obtained through the auxiliary data source; B2, whether the first data integrity coefficient obtained meets the preset data integrity standard. If the first data integrity coefficient obtained meets the preset data integrity standard, it indicates that the data has diversity, otherwise the first data quality is compared with the historical data to obtain a first data quantity evaluation value.

[0019] Furthermore, the specific method for obtaining the first data volume evaluation value is as follows: historical data is obtained from a historical database, and a first data volume evaluation value is obtained according to the difference between the amount of learning data, the amount of psychological data and the amount of social data in the first student data and the amount of historical learning data, the amount of historical psychological data and the amount of historical social data in the historical data. The first data volume evaluation value is used to analyze the change trend in the quantity of student data and historical data of the monitored student; the first data volume evaluation value is calculated by the following formula:

[0020] ;

[0021] In the formula, represents the first data volume evaluation value of the i-th student to be monitored, represents the number of first psychological data of the i-th student to be monitored, represents the number of first learning data of the i-th student to be monitored, represents the number of first social data of the i-th student to be monitored, XL represents the number of historical psychological data of the i-th student to be monitored, XS represents the number of historical learning data of the i-th student to be monitored, and SJ represents the number of historical social data of the i-th student to be monitored.

[0022] Furthermore, the specific method for obtaining the second data volume evaluation value is as follows: the second data volume evaluation value is obtained according to the corresponding difference between the amount of learning data, the amount of psychological data and the amount of social data in the second student data and the amount of historical learning data, the amount of historical psychological data and the amount of historical social data in the historical data, and the second data volume evaluation value is used to analyze the quantitative change trend of the student data and the historical data of the monitored student; the second data volume evaluation value is calculated by the following formula:

[0023] ;

[0024] In the formula, represents the second data volume evaluation value of the i-th student to be monitored, represents the number of second psychological data of the i-th student to be monitored, represents the number of second learning data of the i-th student to be monitored, represents the amount of second social data of the i-th student to be monitored, XL represents the amount of historical psychological data of the i-th student to be monitored, XS represents the amount of historical learning data of the i-th student to be monitored, and SJ represents the amount of historical social data of the i-th student to be monitored.

[0025] Furthermore, the specific method of obtaining the third student data is as follows: C1, obtaining the second student data from an auxiliary data source, and the auxiliary data source includes monitoring, questionnaires, and records of activities outside the classroom; C2, aligning the first student data and the second student data, and the alignment means matching the first student data and the second student data according to key fields; C3, retaining all records of the first student data, and merging and preprocessing the second student data with the first student data to obtain the third student data.

[0026] Furthermore, the specific process of comparing the second data quality that does not meet the preset data standard with the historical data to obtain a second data quantity evaluation value is as follows: D1, evaluating the second classification result to obtain the second data quality, and judging whether the obtained second data timeliness coefficient meets the preset data timeliness standard. If the obtained second data timeliness coefficient does not meet the preset data timeliness standard, triggering a warning signal, otherwise executing D2; D2, judging whether the second data integrity coefficient meets the preset data integrity standard. If the second data integrity coefficient meets the preset data integrity standard, it indicates that the data has diversity. Otherwise, comparing the second data quality that does not meet the preset data standard with the historical data to obtain a second data quantity evaluation value.

[0027] Furthermore, it also includes: comparing the third student data of the student to be monitored with the historical student data to obtain the psychological change data of the student to be monitored; when the psychological change data of the student to be monitored is not less than a preset change amount, continuously monitoring the mental health of the student to be monitored until the psychological change data of the student to be monitored is less than the preset change amount, the psychological change data including mood fluctuations, changes in learning performance and changes in social interaction.

[0028] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0029] 1. The first student data obtained through the main data source obtains the first data quality. If the first data quality and the first data quantity evaluation value do not meet the standard, the second student data obtained from the auxiliary data source obtains the second data quality. If the second data quality and the second data quantity evaluation value do not meet the standard, a warning signal is triggered. If it meets the standard, the data is diverse, thereby realizing multi-source data acquisition and merging, and then realizing the improvement of data collection diversity, effectively solving the problem of single data in the student psychological data collection system in the prior art.

[0030] 2. By obtaining the preset student data from the preset database, the first data completeness coefficient is obtained according to the first classification result and the preset student data quantity, and then the first updated data volume is obtained by real-time recording the acquisition time of the first student data, and finally the first data timeliness coefficient is obtained according to the first updated data volume and the total number of the first data set, thereby realizing the evaluation of data integrity and timeliness, and then realizing the dual guarantee of data comprehensiveness and timeliness.

[0031] 3. The first data quality is obtained by evaluating the first classification result, and then judging whether the first data timeliness coefficient meets the standard. If the first data timeliness coefficient does not meet the standard, the second student data is obtained through the auxiliary data source. Otherwise, judging whether the first data integrity coefficient meets the standard. If the first data integrity coefficient meets the standard, the data has diversity. Otherwise, the first data quality is compared with the historical data to obtain the data quantity evaluation value, thereby ensuring that the data timeliness and integrity meet the standard, thereby achieving the improvement of data quality and diversity. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the structure of a student mental health monitoring and early warning system based on big data and artificial intelligence provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of the structure of the first data acquisition module in the student mental health monitoring and early warning system based on big data and artificial intelligence provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of changes in the first data volume evaluation value provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The embodiment of the present application solves the problem of single data in the student psychological data collection system in the prior art by providing a student mental health monitoring and early warning system based on big data and artificial intelligence. The first student data is obtained through a main data source, and the obtained first student data is classified according to a preset classification standard to obtain a first classification result, and then evaluated to obtain a first data quality. The first data quality is compared with historical data to obtain a first data quantity evaluation value. If the first data quality and the first data quantity evaluation value do not meet the standards, the second data quality is obtained from the second student data obtained from the auxiliary data source. If the second data quality and the second data quantity evaluation value do not meet the standards, a warning signal is triggered. If they meet the standards, the data has diversity, thereby achieving an improvement in the diversity of data collection.

[0036] The technical solution in the embodiment of the present application is to solve the problem of single data in the above-mentioned student psychological data collection system. The overall idea is as follows:

[0037] The first student data obtained through the main data source obtains the first data quality. If the first data quality and the first data quantity evaluation values ​​do not meet the standards, the second student data obtained from the auxiliary data source obtains the second data quality. Secondly, if the second data quality and the second data quantity evaluation values ​​do not meet the standards, feedback is performed, thereby achieving the effect of improving the diversity of data collection.

[0038] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0039] like Figure 1As shown, it is a structural schematic diagram of a student mental health monitoring and early warning system based on big data and artificial intelligence provided by an embodiment of the present application. The student mental health monitoring and early warning system based on big data and artificial intelligence provided by an embodiment of the present application includes: a first data acquisition module, a first judgment module, a second judgment module, a third judgment module and a fourth judgment module; the first data acquisition module is used to obtain first student data of a student to be monitored within a preset time period through a main data source, classify the obtained first student data according to a preset classification standard to obtain a first classification result, and then evaluate to obtain a first data quality, the first student data represents data related to the student obtained from the main data source, the preset classification standard represents classification according to data type, the main data source represents a mental education platform constructed according to the platform used by students at school, and the main data source includes learning platform data, psychological platform data, and social platform data; the first judgment module is used to compare the first data quality with the historical data to obtain a first data quantity evaluation value when the first data quality does not meet the preset data standard, Historical data represents a data set related to students within a preset past time period; the second judgment module is used to obtain the second student data of the student to be monitored within the preset time period through the auxiliary data source and merge it with the first student data to obtain the third student data when the first data quantity evaluation value does not meet the preset evaluation value, classify the third student data according to the preset classification standard to obtain the second classification result, and then evaluate to obtain the second data quality. The auxiliary data source represents an external data source used to supplement the main data source. The auxiliary data source includes monitoring data, questionnaire data and classroom external activity data; the third judgment module is used to compare the second data quality that does not meet the preset data standard with the historical data to obtain the second data quantity evaluation value when the second data quality does not meet the preset data standard; the fourth judgment module is used to feedback that the data has diversity when the first data quality meets the preset data standard and the second data quality meets the preset data standard, and at the same time, when the second data quantity evaluation value does not meet the preset evaluation value, mark the student's data as "unqualified" and trigger an early warning signal.

[0040] In this embodiment, the main data source represents the main source for obtaining student data, which is usually an established psychological education platform constructed according to the platform used by students in school (such as a learning management system, a mental health platform, etc.); the psychological education platform contains various types of data such as students' basic information, learning data, and mental health assessments; the preset time period is obtained from a preset database, which is generally set to one week; the first student data is various types of student-related data obtained from the main data source, including learning data, psychological data, social data, etc.; the preset classification standard represents the rules for data classification, which is usually classified according to the type of data (such as learning, psychology, and social); the first data quality includes a first data timeliness coefficient and a first data integrity coefficient; the preset data standard includes a preset data timeliness standard and a preset data integrity standard; when the first data timeliness coefficient is less than the preset data timeliness standard or the first data integrity coefficient is less than the preset data integrity standard, it indicates that the first data quality does not meet the preset data standard; when the first data volume evaluation value is less than the preset evaluation value, it indicates that the first data volume evaluation value does not meet the preset evaluation value; the auxiliary data source table Indicates other data sources besides the main data source, such as monitoring, etc., which are used to supplement the first student data; the second data quality includes the second data timeliness coefficient and the second data integrity coefficient; when the second data timeliness coefficient is less than the preset data timeliness standard or the second data integrity coefficient is less than the preset data integrity standard, it indicates that the second data quality does not meet the preset data standard; when the second data volume evaluation value is less than the preset evaluation value, it indicates that the second data volume evaluation value does not meet the preset evaluation value; the mark indicates the action taken by the system when identifying potential problems, which is used to remind the system or staff that a student's data is missing; the system integrates a large amount of data from multiple data sources and uses big data analysis technology to identify the changing trend of students' behavior patterns. For example, the system can detect a decrease in the amount of learning data, a decrease in the amount of social data, and a decrease in the amount of psychological data; the application of artificial intelligence in this system is mainly reflected in data evaluation, anomaly detection and automated early warning. The system can continuously optimize data evaluation standards, identify whether the data is diverse, and improve the accuracy and timeliness of early warnings; it achieves an improvement in the diversity of data collection.

[0041] Specifically, the preset data timeliness standard represents the ideal standard for data timeliness set before using the data. The preset data timeliness standard is obtained from the preset database and is expressed by the average amount of updated data in the past time period; the preset data integrity standard represents the preset ideal standard for data integrity. The preset data integrity standard is obtained from the preset database and is expressed by the amount of various types of data obtained in the past time period; the preset evaluation value represents a key indicator for evaluating whether the amount of data is diverse. The preset evaluation value is obtained from the preset database and is expressed by the average data amount evaluation value in the past month.

[0042] Furthermore, the first data acquisition module includes a first data acquisition unit, a first data classification unit and a first data evaluation unit; the first data acquisition unit is used to acquire first student data through a main data source, and transmit the acquired first student data to the first data classification unit, the main data source represents a platform used by the monitored students at school; the first data classification unit is used to classify and preprocess the received first student data according to a preset classification standard to obtain a first classification result, and transmit the obtained first classification result to the first data evaluation unit, the first classification result includes first learning data, first social data and first psychological data, the first learning data represents data related to the student's academic performance, the first social data represents data related to the student's social behavior, and the first psychological data represents data related to the student's psychological state; the first data evaluation unit is used to evaluate the received first classification result to obtain first data quality, and the first data quality is used to quantify the diversity of evaluation data.

[0043] In this embodiment, the first data acquisition unit needs to perform three steps of data extraction and data storage, and the specific process is as follows: data extraction means extracting the first student data from the main data source regularly according to the preset time, and data storage means storing the extracted data in the temporary data storage area of ​​the system for subsequent processing; the first data classification unit needs to perform three steps of data loading, data classification and data preprocessing, and the specific process is as follows; data loading means extracting the acquired original data from the acquisition unit; data classification means dividing the data into learning data, social data and psychological data according to the preset classification standards, for example, classifying students' test scores and homework submission records as learning data, classifying social activity participation records as social data, and classifying mental health assessment results as psychological data; data preprocessing means formatting the classified data; the first data evaluation unit needs to perform three steps of data loading, generating evaluation results and outputting evaluation results, and the specific process is as follows; data loading means obtaining the classification results from the classification unit; generating evaluation results means performing quality assessment on the classified data; and a quantitative assessment of data quality is achieved.

[0044] Furthermore, the first data quality includes a first data integrity coefficient and a first data timeliness coefficient. The specific method for obtaining the first data integrity coefficient is as follows: E1, obtaining preset student data from a preset database. When the first classification result meets the data missing condition, the first data integrity coefficient is recorded as 0, otherwise E2 is executed. The data missing condition indicates that the number of at least two types of data in the first learning data, the first psychological data and the first social data in the first classification result is less than the corresponding preset number; E2, when the first classification result meets the first data missing condition, the first data integrity coefficient is obtained according to the ratio of the number of first learning data to the preset number of learning data and the ratio of the number of first psychological data to the preset number of psychological data, otherwise E3 is executed. The first data missing condition indicates that the number of first social data in the first classification result is less than the preset number of social data and the number of first learning data is not less than the preset number of learning data and the number of first psychological data is not less than the preset number of psychological data. The preset student data includes the preset number of learning data, the preset number of psychological data and the preset number of social data; E3, when the first classification result meets the first data missing condition, When the second data missing condition is met, the first data completeness coefficient is obtained according to the ratio of the first learning data quantity to the preset learning data quantity and the ratio of the first social data quantity to the preset social data quantity, otherwise E4 is executed, and the second data missing condition indicates that the first psychological data quantity in the first classification result is less than the preset psychological data quantity and the first learning data quantity is not less than the preset learning data quantity; E4, when the first classification result meets the third data missing condition, the first data completeness coefficient is obtained according to the ratio of the first psychological data quantity to the preset psychological data quantity and the ratio of the first social data quantity to the preset social data quantity, otherwise E5 is executed, the third data missing condition indicates that the first learning data quantity in the first classification result is less than the preset learning data quantity, and the first data completeness coefficient is used to quantitatively evaluate the completeness of data acquisition; E5, the first data completeness coefficient is obtained according to the ratio of the first learning data quantity to the preset learning data quantity, the ratio of the first psychological data quantity to the preset psychological data quantity and the ratio of the first social data quantity to the preset social data quantity; the first data completeness coefficient is calculated by the following formula:

[0045] ;

[0046] In the formula, i is the number of the student to be monitored, , N represents the total number of students to be monitored, represents the first data completeness coefficient of the i-th student to be monitored, represents the number of first psychological data of the i-th student to be monitored, represents the number of first learning data of the i-th student to be monitored, represents the number of first social data of the i-th student to be monitored, Indicates the number of preset psychological data, Indicates the preset number of learning data. Indicates the preset social data quantity.

[0047] The specific method for obtaining the first data timeliness coefficient is as follows: the acquisition time of the first student data is recorded in real time to obtain the first updated data volume, and the first data timeliness coefficient is obtained according to the ratio of the first updated data volume to the total amount of the first data set. The first data timeliness coefficient is used to quantify the timeliness of data acquisition; the first data timeliness coefficient is calculated by the following formula:

[0048] ;

[0049] In the formula, represents the first data timeliness coefficient of the i-th student to be monitored, represents the first updated data volume of the i-th student to be monitored, Represents the total number of the first data set of the i-th student to be monitored.

[0050] In this embodiment, the preset student data includes a preset number of psychological data, a preset number of learning data, and a preset number of social data; the preset number of psychological data represents the ideal number of psychological-related data of students within a preset time period, usually including psychological assessment results, psychological counseling records, and emotional state monitoring data, etc.; the preset number of psychological data is obtained from a preset database, and the setting of the preset number of psychological data is based on the frequency of mental health services provided by the school; the preset number of learning data represents the ideal number of learning-related data of students within a preset time period, usually including classroom performance, test scores, homework submission status, and classroom interaction data, etc.; the preset number of learning data is obtained from a preset database, and the setting of the preset number of learning data is based on the frequency of students' learning activities; the preset number of social data represents the ideal number of social-related data of students within a preset time period, usually including students' interaction records with peers and their activity on campus social platforms, etc.; the preset number of social data is obtained from a preset database, and the preset social The setting of the data quantity is based on the frequency of students' social activities; the first updated data volume represents the updated data volume obtained by the system from student data within a specific period of time; the total number of the first data set represents the total amount of all data related to the student, including historical data and current data; the situation where the first student data obtained is wrong is not ruled out. When the learning data in the first classification result is insufficient, the system will evaluate the data integrity by calculating the ratio of psychological data to social data. If the psychological data and social data are sufficient, the system may believe that the data as a whole is still complete, but will mark the problem of insufficient learning data; when the psychological data is insufficient and the learning data is sufficient, the system will calculate the ratio of learning data to social data to determine whether the overall data is still complete, and mark the problem of insufficient psychological data; when the social data is insufficient and both the learning data and psychological data are sufficient, the system will evaluate the data integrity by the ratio of learning data to psychological data, and mark the problem of insufficient social data; the evaluation of the comprehensiveness and timeliness of the data is realized.

[0051] Taking the preset number of learning data as 10, the preset number of psychological data as 10, and the preset number of social data as 10 as an example, the statistical table of changes in the first data integrity coefficient is shown in the following table:

[0052]

[0053] From the table, it can be seen that when the number of first psychological data , the first learning data quantity and the number of first social data When both are not less than the corresponding preset value, the first psychological data quantity , the first learning data quantity and the number of first social data The larger the first data integrity coefficient is, The larger the number of first psychological data , the first learning data quantity and the number of first social data With the first data complete coefficient Proportional; when the number of first psychological data , the first learning data quantity and the number of first social data When both are less than the corresponding preset values, the first data complete coefficient Recorded as 0; when there is only the first psychological data number When the number of first learning data is less than the preset value and the number of first social data The larger the first data integrity coefficient is, The larger the number of first learning data and the number of first social data With the first data complete coefficient Proportional; Similarly, when there is only the first learning data When the number of first psychological data is less than the preset value and the number of first social data With the first data complete coefficient Proportional; when only the number of first social data When the number of first psychological data is less than the preset value and the number of first learning data With the first data complete coefficient Directly proportional.

[0054] The algorithm of this embodiment combines the "number of first psychological data of the i-th student to be monitored ","The number of first learning data of the i-th student to be monitored ” and “the number of first social data of the i-th student to be monitored ", comprehensive analysis to obtain the "first data completeness coefficient of the i-th student to be monitored ", and the various parameters are related to each other, not independent, it is a whole, and it is not possible to obtain the "first data completeness coefficient of the i-th student to be monitored" by simply combining and adding them together. ”, for example, in this formula, “the number of first psychological data of the i-th student to be monitored " may lead to the increase of "the first data completeness coefficient of the i-th student to be monitored "Increase does not necessarily mean that the first data completeness coefficient of the i-th student to be monitored " is large, and at this time, we also need to consider "the number of first learning data of the i-th student to be monitored ” and “the number of first social data of the i-th student to be monitored " can also determine the data integrity of the i-th student to be monitored at the next moment. It takes into account the "number of first psychological data of the i-th student to be monitored" in a quantitative way. ","The number of first learning data of the i-th student to be monitored ","The number of first social data of the i-th student to be monitored ” and “the first data completeness coefficient of the i-th student to be monitored "The correlation and mutual influence between them, the number of first psychological data of the i-th student to be monitored , the first learning data quantity and the number of first social data Any increase in the first data integrity coefficient The increase of , comprehensive analysis results in the algorithm itself, which can accurately and quantitatively analyze the data integrity of the i-th student to be monitored, indicating the effect of accurately evaluating the first data integrity coefficient, and therefore accurately analyzes it by establishing a mathematical form.

[0055] Furthermore, the second data quality includes a second data integrity coefficient and a second data timeliness coefficient. The specific method for obtaining the second data integrity coefficient is as follows: F1, obtaining the preset student data from the preset database. When the second classification result meets the data serious missing condition, the second data integrity coefficient is recorded as 0, otherwise execute F2. The data serious missing condition indicates that there are at least two types of data in the second learning data, second psychological data and second social data in the second classification result that are less than the corresponding preset quantity; F2, when the second classification result meets the first data serious missing condition, the second data integrity coefficient is obtained according to the ratio of the second learning data quantity to the preset learning data quantity and the second psychological data quantity to the preset psychological data quantity, otherwise execute F3. The first data serious missing condition indicates that the second social data quantity in the second classification result is less than the preset social data quantity and the second learning data quantity is not less than the preset learning data quantity and the second psychological data quantity is not less than the preset psychological data quantity. The preset student data includes the preset learning data quantity, the preset psychological data quantity and the preset social data quantity; F3, when the second classification result meets the second data When the condition of serious missing data is met, the second data completeness coefficient is obtained according to the ratio of the second learning data quantity to the preset learning data quantity and the ratio of the second social data quantity to the preset social data quantity. Otherwise, F4 is executed. The condition of serious missing data means that the second psychological data quantity in the second classification result is less than the preset psychological data quantity and the second learning data quantity is not less than the preset learning data quantity and the second social data quantity is a complete set. F4, when the second classification result meets the condition of serious missing data, the second data completeness coefficient is obtained according to the ratio of the second psychological data quantity to the preset psychological data quantity and the ratio of the second social data quantity to the preset social data quantity. Otherwise, F5 is executed. The condition of serious missing data means that the second learning data quantity in the second classification result is less than the preset learning data quantity. The second data completeness coefficient is used to quantitatively evaluate the completeness of data acquisition. F5, the second data completeness coefficient is obtained according to the ratio of the second learning data quantity to the preset learning data quantity, the ratio of the second psychological data quantity to the preset psychological data quantity and the ratio of the second social data quantity to the preset social data quantity. The second data completeness coefficient is calculated by the following formula:

[0056] ;

[0057] In the formula, represents the second data completeness coefficient of the i-th student to be monitored, represents the number of second psychological data of the i-th student to be monitored, represents the number of second learning data of the i-th student to be monitored, Represents the amount of second social data of the i-th student to be monitored; the specific method of obtaining the second data timeliness coefficient is as follows: the second updated data amount is obtained by real-time recording the acquisition time of the second student data, and the second data timeliness coefficient is obtained according to the ratio of the second updated data amount to the total amount of the second data set. The second data timeliness coefficient is used to quantify the timeliness of data acquisition.

[0058] The second data timeliness coefficient is calculated by the following formula:

[0059] ;

[0060] In the formula, represents the second data timeliness coefficient of the i-th student to be monitored, represents the second updated data volume of the i-th student to be monitored, Represents the total number of second data sets for the i-th student to be monitored.

[0061] In this embodiment, the possibility of errors in the acquired third student data is not excluded. The severe data missing condition indicates that the quantity of at least two categories (learning data, psychological data, and social data) in the data is less than the preset standard; the first severe data missing condition indicates that the social data in the data is less than the preset standard, but the learning data and the psychological data are not less than the preset standard; the second severe data missing condition indicates that the psychological data in the data is less than the preset standard, but the learning data is not less than the preset standard and the social data is a complete set; the third severe data missing condition indicates that the learning data in the data is less than the preset standard; the second updated data volume indicates the amount of new data added in a preset time period, which is used to evaluate the frequency and timeliness of data updates; the second total data set quantity indicates the total data volume of a student, including the sum of learning data, psychological data, and social data; this process achieves the rigor and reliability of data quality assessment.

[0062] The algorithm of this embodiment combines the "number of second psychological data of the i-th student to be monitored ”, “The number of second learning data of the i-th student to be monitored ” and “the number of the second social data of the i-th student to be monitored ", comprehensive analysis to obtain the "second data completeness coefficient of the i-th student to be monitored ", and the various parameters are related to each other, not independent, it is a whole, and it is not possible to obtain the "second data integrity coefficient of the i-th student to be monitored" by simply combining and adding them. ”, for example, in this formula, “the number of second psychological data of the i-th student to be monitored " may lead to the increase of "the second data completeness coefficient of the i-th student to be monitored "Increase does not necessarily mean that the second data completeness coefficient of the i-th student to be monitored " is large, and at this time, we also need to consider "the number of second learning data of the i-th student to be monitored ” and “the number of the second social data of the i-th student to be monitored " can also determine the data integrity of the i-th student to be monitored at the next moment. It takes into account the "number of second psychological data of the i-th student to be monitored" in a quantitative way. ”, “The number of second learning data of the i-th student to be monitored ","The number of the second social data of the i-th student to be monitored ” and “the second data completeness coefficient of the i-th student to be monitored "The correlation and mutual influence between them, when the number of second psychological data , the second learning data quantity and the number of second social data When both are not less than the corresponding preset value, the second psychological data quantity , the second learning data quantity and the number of second social data The larger the second data integrity coefficient The larger the number of second psychological data , the second learning data quantity and the number of second social data With the second data complete coefficient Proportional; when the number of second psychological data , the second learning data quantity and the number of second social data When both are less than the corresponding preset value, the second data complete coefficient Recorded as 0; when there is only the second psychological data number When the number of second learning data is less than the preset value, and the number of second social data The larger the second data integrity coefficient The larger the second learning data and the number of second social data With the second data complete coefficient Proportional; Similarly, when there is only the second learning data When the second psychological data is less than the preset value, and the number of second social data With the second data complete coefficient Proportional; when only the second social data When the second psychological data is less than the preset value, and the second learning data quantity With the second data complete coefficient The algorithm obtained through comprehensive analysis can accurately and quantitatively analyze the data integrity of the i-th student to be monitored, indicating the effect of accurately evaluating the second data integrity coefficient. Therefore, accurate analysis is carried out by establishing a mathematical form.

[0063] Furthermore, when the first data quality does not meet the preset data standard, the first data quality is compared with the historical data to obtain a first data quantity evaluation value, specifically: B1, the first classification result is evaluated to obtain the first data quality, and whether the obtained first data timeliness coefficient meets the preset data timeliness standard. If the obtained first data timeliness coefficient meets the preset data timeliness standard, execute B2, otherwise the second student data is obtained through the auxiliary data source; B2, whether the obtained first data integrity coefficient meets the preset data integrity standard. If the obtained first data integrity coefficient meets the preset data integrity standard, it indicates that the data has diversity, otherwise the first data quality is compared with the historical data to obtain a first data quantity evaluation value.

[0064] In this embodiment, the preset data timeliness standard represents an ideal standard for data timeliness set before using the data. The preset data timeliness standard is obtained from a preset database and is represented by the average amount of updated data in the past time period. If the first data timeliness coefficient is not less than the preset data timeliness standard, it means that the first data timeliness coefficient meets the preset data timeliness standard. The auxiliary data source represents a secondary data source used to supplement or replace the primary data source. When the data quality of the primary data source does not meet the standard, data is obtained from the auxiliary data source. The preset data integrity standard represents a preset ideal standard for data integrity. The preset data integrity standard is obtained from a preset database and is represented by the amount of data of various types obtained in the past time period. If the first data integrity coefficient is not less than the preset data integrity standard, it means that the first data integrity coefficient meets the preset data integrity standard. Data diversity represents the richness of categories or dimensions contained in the data, which usually means that the data can provide multi-faceted information. This series of steps realizes data diversity.

[0065] Furthermore, the specific method for obtaining the first data volume evaluation value is as follows: historical data is obtained from a historical database, and the first data volume evaluation value is obtained according to the corresponding difference between the amount of learning data, the amount of psychological data and the amount of social data in the first student data and the amount of historical learning data, the amount of historical psychological data and the amount of historical social data in the historical data. The historical data is used to determine whether the real-time status of the monitored student is normal. The historical data includes the amount of historical learning data, the amount of historical psychological data and the amount of historical social data. The first data volume evaluation value is used to analyze the quantitative change trend of the student data and the historical data of the monitored student. The historical database is used to store historical data related to the student in the past time period; the first data volume evaluation value is calculated by the following formula:

[0066] ;

[0067] In the formula, represents the first data volume evaluation value of the i-th student to be monitored, represents the number of first psychological data of the i-th student to be monitored, represents the number of first learning data of the i-th student to be monitored, represents the number of first social data of the i-th student to be monitored, XL represents the number of historical psychological data of the i-th student to be monitored, XS represents the number of historical learning data of the i-th student to be monitored, and SJ represents the number of historical social data of the i-th student to be monitored.

[0068] In this embodiment, the first data quantity evaluation value is used to quantify the degree of change of current student data relative to historical data, reflecting the differences between students' current learning, psychological and social data and historical data; the amount of historical learning data is obtained from the historical database, and is represented by the average amount of learning data in the past month; the amount of historical psychological data is obtained from the historical database, and is represented by the average amount of psychological data in the past month; the amount of historical social data is obtained from the historical database, and is represented by the average amount of social data in the past month; by calculating the first data quantity evaluation value, effective quantification of the change range between current student data and historical data is achieved.

[0069] The number of historical psychological data is 15, the number of historical learning data is 15, the number of historical social data is 15, and the number of first social data is Take 15 as an example, Figure 3 As shown, it is a schematic diagram of the change of the first data amount evaluation value provided in an embodiment of the present application. From the figure, it can be seen that when the amount of first learning data is constant, the larger the amount of first psychological data, the larger the first data amount evaluation value; when the amount of first psychological data is constant, the larger the amount of first learning data, the larger the first data amount evaluation value.

[0070] Furthermore, the specific method for obtaining the second data volume evaluation value is as follows: the second data volume evaluation value is obtained according to the corresponding difference between the amount of learning data, the amount of psychological data and the amount of social data in the second student data and the amount of historical learning data, the amount of historical psychological data and the amount of historical social data in the historical data. The second data volume evaluation value is used to analyze the change trend in the quantity of student data and historical data of the monitored student; the second data volume evaluation value is calculated by the following formula:

[0071] ;

[0072] In the formula, represents the second data volume evaluation value of the i-th student to be monitored, represents the number of second psychological data of the i-th student to be monitored, represents the number of second learning data of the i-th student to be monitored, represents the amount of second social data of the i-th student to be monitored, XL represents the amount of historical psychological data of the i-th student to be monitored, XS represents the amount of historical learning data of the i-th student to be monitored, and SJ represents the amount of historical social data of the i-th student to be monitored.

[0073] In this embodiment, the amount of learning data in the second student data represents the amount of data related to the student's learning activities obtained from the auxiliary data source; the amount of psychological data in the second student data represents the amount of data related to the student's psychological state or behavior obtained from the auxiliary data source; the amount of social data in the second student data represents the amount of data related to the student's social activities or behaviors obtained from the auxiliary data source; by calculating the second data amount evaluation value, the evaluation of students' data changes in learning, psychology and social aspects is achieved.

[0074] Furthermore, the specific method of obtaining the third student data is as follows: C1, obtaining the second student data from an auxiliary data source, where the auxiliary data source represents an external data source, and the auxiliary data source includes monitoring, questionnaires, and records of activities outside the classroom; C2, aligning the first student data and the second student data, where alignment represents matching the first student data and the second student data according to key fields, and the key fields represent the basic information of the students to be monitored; C3, retaining all records of the first student data, and merging and preprocessing the second student data with the first student data to obtain the third student data.

[0075] In this embodiment, the second judgment module includes a data quantity evaluation value judgment unit, a second student data collection unit, a second data classification unit and a second data evaluation unit; the data quantity evaluation value judgment unit: used to judge whether the data quantity evaluation value meets the preset evaluation value. If the data quantity evaluation value meets the preset evaluation value, it indicates that the data has diversity, otherwise the second student data collection unit is executed; the second student data collection unit: used to obtain the second student data through the auxiliary data source, merge the obtained second student data with the first student data to obtain the third student data, and transmit the third student data to the second data classification unit; the second data classification unit: used to classify the third student data according to the preset classification standard to obtain the second classification result, and transmit the second classification result data to the second data evaluation unit; the second data evaluation unit: used to evaluate the second classification result to obtain the second data quality.

[0076] If the data volume evaluation value is not less than the preset evaluation value data volume, it means that the evaluation value meets the preset evaluation value; the data volume evaluation value judgment unit is used to judge whether the "data volume evaluation value" meets the preset standard. If it does, it means that the data is diverse enough. If it does not, more data needs to be collected; the second student data collection unit indicates that when the data volume evaluation value is insufficient, more student data is obtained from additional data sources through this unit, and these new data are merged with the existing data to supplement the data volume; the second data classification unit indicates the classification of the third student data; the classification standard is pre-set, usually classified according to the type of data (such as learning, psychology, social), and is used to organize the data into different categories for subsequent evaluation; the second data evaluation unit: evaluates the classified data to determine whether the quality of these data meets the requirements; the preset evaluation value represents a key indicator for evaluating whether the amount of data is diverse; the preset evaluation value is obtained from the preset database and is represented by the average data volume evaluation value in the past month; when the existing data is insufficient, the second student data collection unit is used to supplement the data in a timely manner to ensure the comprehensiveness of the data, thereby reducing the analysis bias caused by insufficient data.

[0077] The primary data source is a direct way to obtain data. When the data obtained from the primary data source does not meet the preset standards, it can be supplemented by obtaining data from the secondary data source, which can avoid unnecessary use of the secondary data source. For example, the monitored students do not frequently use the campus consumption platform, which may result in missing data on the monitored students obtained by the primary data source, but the secondary data source can obtain data in this regard; or the monitored students may be unwilling to engage in social interactions on the platform, which may result in missing data on the monitored students obtained by the primary data source, but the secondary data source can obtain data in this regard; the secondary data source refers to an external data source, which is usually used to supplement the main data source within the system; the secondary data sources include monitoring, questionnaires, and records of activities outside the classroom; monitoring refers to student behavior and activity data recorded by video surveillance equipment; questionnaires refer to self-reported data on students' psychological, learning or social status collected through questionnaires; records of activities outside the classroom refer to student activity data outside the classroom, such as participation in extracurricular activities, social interactions, sports, etc.; the secondary data source is obtained through the school's authorized platform or other compliant channels to ensure the confidentiality of student information; During the data evaluation stage, the primary data source is used first, and the secondary data source is combined when necessary to ensure the accuracy and comprehensiveness of the analysis results; alignment refers to matching the data in two different data sources based on certain key fields (such as students' basic information) to ensure that the records in different data sources can accurately correspond to the same student, for example, aligning the first student data with the second student data based on the student's name, student number or other unique identifier; merging refers to integrating the first student data and the second student data to form a new data set; preprocessing is to clean, format or standardize the merged data to ensure data consistency and quality; data format unification means converting all numerical fields and units into a unified format, for example, converting date fields into a unified date format (such as YYYY-MM-DD), and unifying all length units into millimeters; data cleaning means that for multiple records with the same key fields, you can choose to keep the latest record; by collecting data from secondary data sources, aligning and merging these data, a more comprehensive and accurate student data set is constructed.

[0078] Furthermore, the specific process of comparing the second data quality that does not meet the preset data standard with the historical data to obtain the second data quantity evaluation value is as follows: D1, evaluating the second classification result to obtain the second data quality, judging whether the obtained second data timeliness coefficient meets the preset data timeliness standard, if the obtained second data timeliness coefficient does not meet the preset data timeliness standard, marking the student's data as "unqualified", and triggering an early warning signal to remind the preset personnel to intervene in the student, otherwise executing D2; D2, judging whether the second data integrity coefficient meets the preset data integrity standard, if the second data integrity coefficient meets the preset data integrity standard, it indicates that the data has diversity, otherwise the second data quality that does not meet the preset data standard is compared with the historical data to obtain the second data quantity evaluation value; the specific process of triggering the early warning signal when the second data quantity evaluation value does not meet the preset evaluation value is as follows: judging whether the second data quantity evaluation value meets the preset evaluation value, if the second data quantity evaluation value meets the preset evaluation value, it indicates that the data has diversity, otherwise, marking the student's data as "unqualified", and triggering an early warning signal to remind the preset personnel to intervene in the student.

[0079] In this embodiment, if the timeliness coefficient does not meet the preset standard, it means that the data may be outdated or no longer have reference value; first, the timeliness of the second classification result is evaluated and its timeliness coefficient is calculated. If the timeliness coefficient does not meet the preset timeliness standard, for example, the data is too old, the student's data is marked as "unqualified" and a warning signal is triggered to remind relevant personnel to intervene, such as requiring data to be updated or contacting the student; if the timeliness coefficient meets the standard, D2 is executed; the integrity of the second classification result is evaluated and its completeness coefficient is calculated. If the completeness coefficient meets the preset completeness standard, it means that the data is complete and diverse, and the process ends. If the completeness coefficient does not meet the standard, it is necessary to compare these incomplete second data with historical data to calculate the data volume evaluation value; the calculated second data volume evaluation value is compared with the preset evaluation value. If the evaluation value meets the preset standard, it means that the data is diverse and the process ends. If the evaluation value does not meet the standard, it means that the data lacks diversity or representativeness, the student's data is marked as "unqualified", and a warning signal is triggered to remind relevant personnel to intervene; the accuracy and reliability of the data are improved.

[0080] Furthermore, it also includes: comparing the third student data of the student to be monitored with the historical student data to obtain the psychological change data of the student to be monitored; when the psychological change data of the student to be monitored is not less than a preset change amount, continuously monitoring the mental health of the student to be monitored until the psychological change data of the student to be monitored is less than the preset change amount, the psychological change data including mood fluctuations, changes in learning performance and changes in social interaction.

[0081] In this embodiment, big data technology is used to compare the third-party student data and historical student data of the student to be monitored to obtain the psychological change data of the student to be monitored; natural language processing technology is used to analyze the text and voice data of the student to be monitored to identify emotional fluctuations; emotional fluctuations indicate the magnitude of changes in the emotional state of the student to be monitored, such as from positive to negative or emotional instability; changes in learning performance indicate changes in the performance of the student to be monitored in the learning process, including academic performance, homework completion, class participation, etc.; changes in social interaction indicate changes in social behavior between the student to be monitored and his peers, teachers or family members, such as reduced social activities, isolation or a sudden increase in social activity; historical student data indicate various types of behavioral data of the student to be monitored in the past, including academic performance, psychological assessment results, social activity records, etc.; historical student data provides students' baseline behavior patterns, which are convenient for comparison with current data for comparison; when the system detects that one or more indicators in the psychological change data are not less than the preset change amount, for example, increased mood fluctuations, a sharp decline in learning performance, or an abnormal increase or decrease in social interactions, it indicates that the student may be experiencing mental health problems; the system will conduct continuous monitoring based on the degree of abnormality of these data. Continuous monitoring means closely tracking students' behavioral changes and increasing the frequency of data collection to capture potential risk signals more promptly; during the continuous monitoring process, the system will continuously evaluate the students' mental health status. If the monitoring shows that the students' psychological change data is less than the preset change amount, for example, emotions tend to stabilize and learning performance returns to normal, the system will determine that the students' mental health status has recovered; once the students' mental health returns to normal, the system will end continuous monitoring and switch to regular periodic monitoring; real-time monitoring of the mental health status of the monitored students is realized.

[0082] To summarize, the embodiment of the present application obtains a first data quality from the first student data obtained through the main data source, and then if the first data quality and the first data quantity evaluation value do not meet the standard, the second student data obtained from the auxiliary data source obtains a second data quality, and secondly, if the second data quality and the second data quantity evaluation value do not meet the standard, an early warning signal is triggered, and if it meets the standard, the data is diverse, thereby realizing multi-source data acquisition and merging, and further realizing the improvement of data collection diversity, effectively solving the problem of single data in the student psychological data collection system in the prior art.

[0083] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0088] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A student mental health monitoring and early warning system based on big data and artificial intelligence, characterized by: It includes a first data acquisition module, a first judgment module, a second judgment module, a third judgment module and a fourth judgment module; The first data acquisition module is used to obtain first student data of the students to be monitored within a preset time period through a main data source, classify the obtained first student data according to a preset classification standard to obtain a first classification result, and then evaluate to obtain first data quality, wherein the main data source is a psychological education platform constructed according to the platform used by the students at school, and the main data source includes learning platform data, psychological platform data, and social platform data; The first judgment module is used to compare the first data quality with the historical data to obtain a first data quantity evaluation value when the first data quality does not meet the preset data standard; The second judgment module is used for merging the second student data of the student to be monitored within a preset time period obtained through the auxiliary data source with the first student data to obtain third student data when the first data volume evaluation value does not meet the preset evaluation value, classifying the third student data according to the preset classification standard to obtain the second classification result and then evaluating to obtain the second data quality, wherein the auxiliary data source represents an external data source used to supplement the main data source, and the auxiliary data source includes monitoring data, questionnaire survey data and classroom external activity data; The third judgment module is used for comparing the second data quality that does not meet the preset data standard with the historical data to obtain a second data quantity evaluation value when the second data quality does not meet the preset data standard; The fourth judgment module is used to feedback that the data has diversity when the first data quality meets the preset data standard and the second data quality meets the preset data standard, and trigger an early warning signal when the second data volume evaluation value does not meet the preset evaluation value; The specific method of obtaining the first data volume evaluation value is as follows: Acquire historical data from a historical database, and obtain a first data quantity evaluation value according to the difference between the amount of learning data, the amount of psychological data, and the amount of social data in the first student data and the amount of historical learning data, the amount of historical psychological data, and the amount of historical social data in the historical data, wherein the first data quantity evaluation value is used to analyze the change trend in the quantity of student data and historical data of the student to be monitored; The first data volume evaluation value is calculated by the following formula: ； In the formula, represents the first data volume evaluation value of the i-th student to be monitored, represents the number of first psychological data of the i-th student to be monitored, represents the number of first learning data of the i-th student to be monitored, represents the number of first social data of the i-th student to be monitored, XL represents the number of historical psychological data of the i-th student to be monitored, XS represents the number of historical learning data of the i-th student to be monitored, and SJ represents the number of historical social data of the i-th student to be monitored; The specific method of obtaining the second data volume evaluation value is as follows: Obtaining a second data volume evaluation value according to the corresponding differences between the amount of learning data, the amount of psychological data and the amount of social data in the second student data and the amount of historical learning data, the amount of historical psychological data and the amount of historical social data in the historical data, wherein the second data volume evaluation value is used to analyze the change trend in the quantity of the student data and the historical data of the student to be monitored; The second data volume evaluation value is calculated by the following formula: ； In the formula, represents the second data volume evaluation value of the i-th student to be monitored, represents the number of second psychological data of the i-th student to be monitored, represents the number of second learning data of the i-th student to be monitored, represents the amount of second social data of the i-th student to be monitored, XL represents the amount of historical psychological data of the i-th student to be monitored, XS represents the amount of historical learning data of the i-th student to be monitored, and SJ represents the amount of historical social data of the i-th student to be monitored.

2. The student mental health monitoring and early warning system based on big data and artificial intelligence as claimed in claim 1 is characterized in that: The first data acquisition module includes a first data acquisition unit, a first data classification unit and a first data evaluation unit; The first data acquisition unit is used to acquire the first student data through the main data source, and transmit the acquired first student data to the first data classification unit; The first data classification unit is used to classify and preprocess the received first student data according to a preset classification standard to obtain a first classification result, and transmit the obtained first classification result to the first data evaluation unit, wherein the first classification result includes first learning data, first social data and first psychological data; The first data evaluation unit is used to evaluate the received first classification result to obtain a first data quality, where the first data quality is used to quantitatively evaluate the diversity of data.

3. The student mental health monitoring and early warning system based on big data and artificial intelligence as claimed in claim 1 is characterized in that: The first data quality includes a first data integrity coefficient and a first data timeliness coefficient. The first data integrity coefficient is specifically obtained in the following manner: E1, obtaining preset student data from a preset database, and when the first classification result meets the data missing condition, recording the first data completeness coefficient as 0, otherwise executing E2, the preset student data includes a preset psychological data quantity, a preset learning data quantity, and a preset social data quantity, and the data missing condition indicates that the quantity of at least two types of data in the first learning data, the first psychological data, and the first social data in the first classification result is less than the corresponding preset quantity; E2, when the first classification result meets the first data missing condition, obtain the first data completeness coefficient according to the ratio of the first learning data quantity to the preset learning data quantity and the ratio of the first psychological data quantity to the preset psychological data quantity, otherwise execute E3, the first data missing condition indicates that the first social data quantity in the first classification result is less than the preset social data quantity and the first learning data quantity is not less than the preset learning data quantity and the first psychological data quantity is not less than the preset psychological data quantity; E3, when the first classification result meets the second data missing condition, obtain the first data completeness coefficient according to the ratio of the first learning data quantity to the preset learning data quantity and the ratio of the first social data quantity to the preset social data quantity, otherwise execute E4, the second data missing condition indicates that the first psychological data quantity in the first classification result is less than the preset psychological data quantity and the first learning data quantity is not less than the preset learning data quantity; E4, when the first classification result meets the third data missing condition, obtain the first data completeness coefficient according to the ratio of the first psychological data quantity to the preset psychological data quantity and the ratio of the first social data quantity to the preset social data quantity, otherwise execute E5, the third data missing condition indicates that the first learning data quantity in the first classification result is less than the preset learning data quantity, and the first data completeness coefficient is used to quantitatively evaluate the completeness of data acquisition; E5, obtaining a first data completeness coefficient according to a ratio of the first learning data quantity to the preset learning data quantity, a ratio of the first psychological data quantity to the preset psychological data quantity, and a ratio of the first social data quantity to the preset social data quantity; The first data integrity coefficient is calculated by the following formula: ； In the formula, i is the number of the student to be monitored, , N represents the total number of students to be monitored, represents the first data completeness coefficient of the i-th student to be monitored, represents the number of first psychological data of the i-th student to be monitored, represents the number of first learning data of the i-th student to be monitored, represents the number of first social data of the i-th student to be monitored, Indicates the number of preset psychological data, Indicates the preset number of learning data. Indicates the preset number of social data; The specific method of obtaining the first data timeliness coefficient is as follows: The acquisition time of the first student data is recorded in real time to obtain the first updated data volume, and the first data timeliness coefficient is obtained according to the ratio of the first updated data volume to the total number of the first data set. The first data timeliness coefficient is used to quantify the timeliness of data acquisition.

4. The student mental health monitoring and early warning system based on big data and artificial intelligence as claimed in claim 3 is characterized in that: The second data quality includes a second data integrity coefficient and a second data timeliness coefficient. The specific method for obtaining the second data integrity coefficient is as follows: F1, obtaining preset student data from a preset database, and when the second classification result meets the data serious missing condition, recording the second data completeness coefficient as 0, otherwise executing F2, the preset student data includes the preset psychological data quantity, the preset learning data quantity and the preset social data quantity, and the data serious missing condition indicates that the quantity of at least two types of data in the second learning data, the second psychological data and the second social data in the second classification result is less than the corresponding preset quantity; F2, when the second classification result meets the first data serious missing condition, obtain the second data completeness coefficient according to the ratio of the second learning data quantity to the preset learning data quantity and the ratio of the second psychological data quantity to the preset psychological data quantity, otherwise execute F3, the first data serious missing condition indicates that the second social data quantity in the second classification result is less than the preset social data quantity and the second learning data quantity is not less than the preset learning data quantity and the second psychological data quantity is not less than the preset psychological data quantity; F3, when the second classification result meets the second data serious missing condition, the second data completeness coefficient is obtained according to the ratio of the second learning data quantity to the preset learning data quantity and the ratio of the second social data quantity to the preset social data quantity, otherwise, F4 is executed, and the second data serious missing condition indicates that the second psychological data quantity in the second classification result is less than the preset psychological data quantity and the second learning data quantity is not less than the preset learning data quantity and the second social data quantity is a complete set; F4, when the second classification result meets the third data serious missing condition, the second data completeness coefficient is obtained according to the ratio of the second psychological data quantity to the preset psychological data quantity and the ratio of the second social data quantity to the preset social data quantity, otherwise, F5 is executed, the second data completeness coefficient is used to quantitatively evaluate the completeness of data acquisition, and the third data serious missing condition indicates that the second learning data quantity in the second classification result is less than the preset learning data quantity; F5, obtaining a second data completeness coefficient according to a ratio of the second learning data quantity to the preset learning data quantity, a ratio of the second psychological data quantity to the preset psychological data quantity, and a ratio of the second social data quantity to the preset social data quantity; The second data integrity coefficient is calculated by the following formula: ； In the formula, represents the second data completeness coefficient of the i-th student to be monitored, represents the number of second psychological data of the i-th student to be monitored, represents the number of second learning data of the i-th student to be monitored, represents the number of the second social data of the i-th student to be monitored; The specific method of obtaining the second data timeliness coefficient is as follows: The second updated data volume is obtained by recording the acquisition time of the second student data in real time, and the second data timeliness coefficient is obtained according to the ratio of the second updated data volume to the total number of the second data sets. The second data timeliness coefficient is used to quantify the timeliness of data acquisition.

5. The student mental health monitoring and early warning system based on big data and artificial intelligence as claimed in claim 1, characterized in that: When the first data quality does not meet the preset data standard, the first data quality is compared with the historical data to obtain a first data quantity evaluation value, specifically: B1, evaluate the first classification result to obtain the first data quality, and determine whether the obtained first data timeliness coefficient meets the preset data timeliness standard. If the obtained first data timeliness coefficient meets the preset data timeliness standard, execute B2, otherwise obtain the second student data through the auxiliary data source; B2, judging whether the obtained first data integrity coefficient meets the preset data integrity standard. If the obtained first data integrity coefficient meets the preset data integrity standard, it means that the data has diversity. Otherwise, the first data quality is compared with the historical data to obtain a first data quantity evaluation value.

6. The student mental health monitoring and early warning system based on big data and artificial intelligence as claimed in claim 1, characterized in that: The specific method of obtaining the third student data is as follows: C1, obtaining second student data from an auxiliary data source, wherein the auxiliary data source includes monitoring, questionnaires, and records of activities outside the classroom; C2, aligning the first student data and the second student data, wherein the alignment means matching the first student data and the second student data according to key fields; C3, retaining all records of the first student data, and merging and preprocessing the second student data with the first student data to obtain the third student data.

7. The student mental health monitoring and early warning system based on big data and artificial intelligence as claimed in claim 6, characterized in that: The specific process of comparing the second data quality that does not meet the preset data standard with the historical data to obtain the second data quantity evaluation value is as follows: D1, evaluating the second classification result to obtain the second data quality, judging whether the obtained second data timeliness coefficient meets the preset data timeliness standard, if the obtained second data timeliness coefficient does not meet the preset data timeliness standard, triggering an early warning signal, otherwise executing D2; D2, judging whether the second data integrity coefficient meets the preset data integrity standard. If the second data integrity coefficient meets the preset data integrity standard, it indicates that the data has diversity. Otherwise, the second data quality that does not meet the preset data standard is compared with the historical data to obtain a second data quantity evaluation value.

8. The student mental health monitoring and early warning system based on big data and artificial intelligence as claimed in claim 1, characterized in that: Also includes: The third student data of the student to be monitored and the historical student data are compared to obtain the psychological change data of the student to be monitored. When the psychological change data of the student to be monitored is not less than the preset change amount, the mental health of the student to be monitored is continuously monitored until the psychological change data of the student to be monitored is less than the preset change amount. The psychological change data includes mood fluctuations, changes in learning performance and changes in social interaction.

Images