Student psychological health data assessment and early warning system and method based on data analysis

Abstract

The invention discloses a student psychological health data evaluation and early warning system and method based on data analysis, and belongs to the technical field of big data processing, and the method comprises the following steps: collecting psychological evaluation data of student psychological health evaluation, obtaining the structure availability characteristics of the psychological evaluation data, obtaining the evaluation state label of the psychological evaluation data through analysis, and obtaining the structure availability characteristics of the psychological evaluation data; when the evaluation state label is an evaluable state, an evaluation task parameter set is generated, when the evaluation state label is a condition-limited evaluation state, data correction processing is executed, otherwise, evaluation is paused, a hierarchical scheduling result is obtained based on the evaluation task parameter set, and therefore psychological evaluation data is scheduled, and an evaluation result is output. According to the psychological health assessment method and device, the technical problems that in the prior art, assessment and early warning results are output when data conditions are insufficient or abnormal, the credibility of the psychological health assessment results of the psychological assessment data is not high, and misjudgment exists are solved.

Description

Technical Field

[0001] This invention relates to the field of big data processing technology, and in particular to a student mental health data assessment and early warning system and method based on data analysis. Background Technology

[0002] With the widespread application of information technology in education, the assessment and early warning of students' mental health involves collecting psychological assessment data through student-facing applications and online systems. This data is then centrally processed and analyzed to assess mental health status and provide risk warnings. Current technologies typically employ a unified data processing workflow, directly aggregating data from different data sources for analysis. However, in practice, due to diverse data sources, significant differences in collection methods, and inconsistent participation in psychological assessments, student mental health assessment data generally exhibits structural inconsistencies and insufficient continuity during the collection, transmission, and processing stages. This affects the stability and reliability of the student mental health assessment and early warning results.

[0003] Existing technologies perform quality verification and automatic correction on student-published data, and perform cluster analysis on evaluation data to form data sequence clusters. Based on the similarity confidence of the sequence clusters, the analysis frequency, sampling rate, and intra-cluster resource scheduling strategy are dynamically adjusted. The task allocation plan is calculated and issued according to the scheduling exposure index and resource ratio of each sequence cluster.

[0004] For example, Chinese invention patent CN120762923B discloses an intelligent psychological state assessment system based on psychological assessment data. This system includes: first, quality verification and automatic correction of student-submitted data to ensure reliable input for subsequent processing; second, data sequence clustering through cluster analysis, and dynamic adjustment of resource scheduling strategies based on the similarity confidence of each cluster to optimize the analysis frequency and sampling rate of different clusters; third, dynamic adjustment of resource scheduling strategies within clusters; fourth, intelligent calculation and distribution of optimal task allocation plans based on the scheduling exposure index and resource ratio of each sequence cluster to achieve precise matching of computing power and manpower; and finally, real-time monitoring of key performance indicators.

[0005] For example, the Chinese invention patent with announcement number CN120179422B discloses an AI-based psychological assessment data analysis and early warning system, which includes: a dataset complexity determination module, a data slice determination module, a GPU compatibility matching module, and a psychological data analysis and early warning module. The mental health monitoring platform collects multi-source psychological datasets of psychological assessment data, evaluates their overall complexity, and determines the number of psychological data slices and their respective complexities accordingly. The platform monitors the execution data of each GPU in real time, evaluates its initial execution quality indicators and compatibility complexity, and then, through data processing, matches the overall complexity of the psychological data slices with the compatibility complexity of each GPU, completing the allocation of psychological data slices to GPUs. Finally, the platform uses this allocation relationship to analyze the psychological data of the psychological assessment data, ultimately achieving the analysis and early warning of the psychological data of the psychological assessment data.

[0006] The above-mentioned technology has at least the following technical problems:

[0007] Existing technologies primarily focus on the data processing stage, generally lacking effective assessment of the structural consistency and usability of mental health assessment data in multi-source collection environments. Due to factors such as non-standard responses to mental health assessment data, failed data uploads, and network delays, data is often processed directly even when there are missing data, structural conflicts, or discontinuous collection. This results in assessment and warning results being output when data conditions are insufficient or abnormal, leading to technical problems such as low reliability of mental health assessment results and misjudgments. Summary of the Invention

[0008] To address the technical problem in existing technologies where assessment and early warning results are output when data conditions are insufficient or abnormal, leading to low reliability and misjudgments in psychological health assessments, this invention provides a student psychological health data assessment and early warning system and method based on data analysis. The technical solution is as follows:

[0009] On the one hand, a data-driven student mental health data assessment and early warning system is provided. This system includes: a data preprocessing module, an assessment status determination module, a data classification and processing module, a resource scheduling and control module, and a credibility determination module. The data preprocessing module collects psychological assessment data from students within a preset assessment window, generates data behavior identifiers, and processes the data based on these identifiers to obtain the structural usability characteristics of the psychological assessment data. The assessment status determination module analyzes the structural usability characteristics of the psychological assessment data to obtain assessment status labels, which include assessable status, conditionally limited assessment status, and unassessable status. The data classification and processing module... The first module generates an assessment task parameter set based on the structural availability characteristics of the psychological assessment data when the assessment status label is "assessable." When the assessment status label is "conditionally limited," it performs data correction processing; otherwise, it pauses the assessment and issues a reminder. The second module, the resource scheduling control module, obtains a data completeness index based on the assessment task parameter set and analyzes the hierarchical scheduling results to schedule the psychological assessment data. The third module, the credibility determination module, inputs the psychological assessment data into the mental health assessment model for evaluation, outputs the evaluation results, obtains the processing efficiency index and processing coverage index of the psychological assessment data, and thus obtains the credibility identifier of the evaluation results, completing the psychological assessment data evaluation task.

[0010] On the other hand, a data analysis-based method for student mental health data assessment and early warning is provided. This method includes: collecting psychological assessment data of students within a preset assessment window, generating data behavior identifiers, and processing the data based on these identifiers to obtain the structural usability characteristics of the psychological assessment data; analyzing the structural usability characteristics of the psychological assessment data to obtain assessment status labels, including assessable status, conditionally limited assessment status, and unassessable status; when the assessment status label is assessable, generating an assessment task parameter set based on the structural usability characteristics of the psychological assessment data; when the assessment status label is conditionally limited, performing data correction processing; otherwise, pausing the assessment and issuing a reminder; obtaining a data completeness index based on the assessment task parameter set and analyzing the hierarchical scheduling results, thereby scheduling the psychological assessment data; inputting the psychological assessment data into a mental health assessment model for assessment, outputting the assessment results, obtaining the processing efficiency index and processing coverage index of the psychological assessment data, thereby obtaining the credibility identifier of the assessment results, and completing the psychological assessment data assessment task.

[0011] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0012] 1. The student mental health data assessment and early warning system based on data analysis provided by this invention collects psychological assessment data of students' mental health within a preset assessment window, generates data behavior identifiers for the psychological assessment data, obtains the structural usability characteristics of the psychological assessment data based on the data behavior identifiers, and obtains the assessment data label of the psychological assessment data based on the structural usability characteristics of the psychological assessment data. This realizes the pre-quality screening of psychological assessment data and solves the problem of low-quality data being directly used for assessment in the prior art, which leads to the distortion and instability of mental health assessment results.

[0013] 2. This invention obtains the data completeness index of psychological assessment data through the assessment task parameter set of psychological assessment data. Based on the data completeness index, a hierarchical scheduling result is obtained. According to the hierarchical scheduling result, the psychological assessment data is marked as hierarchical psychological assessment data, and then the psychological assessment data is included in the corresponding assessment task queue. The hierarchical processing bandwidth of all psychological assessment data at this level is obtained, and the allocated processing bandwidth of the psychological assessment data is obtained. This realizes the dynamic and fine allocation of system processing bandwidth under different assessment tasks, and improves the overall processing capability of the system in multi-data concurrent scenarios.

[0014] 3. This invention inputs psychological assessment data into a mental health assessment model for evaluation, outputs the evaluation results of the psychological assessment data, and obtains the processing efficiency index and processing coverage index of the psychological assessment data based on the processing evaluation of the mental health assessment model. The reliability of the evaluation results is determined, and the reliability identifier of the evaluation results is obtained, thus completing the evaluation task of the psychological assessment data and realizing the process verification of the reliability of the mental health assessment results. This effectively avoids the problem of directly outputting the evaluation results when the data processing is insufficient or the model execution is abnormal. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A schematic diagram of the structure of a student mental health data assessment and early warning system based on data analysis provided in this application embodiment;

[0017] Figure 2 A flowchart illustrating the student mental health assessment process for a data-driven student mental health data assessment and early warning system provided in this application embodiment;

[0018] Figure 3A flowchart illustrating the reliability determination of the evaluation results of the data-based student mental health data assessment and early warning system provided in this application embodiment;

[0019] Figure 4 The overall flowchart of the student mental health data assessment and early warning method based on data analysis provided in the embodiments of this application is shown. Detailed Implementation

[0020] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0021] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0022] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0023] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0024] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0025] like Figure 1The diagram shown is a structural schematic of a student mental health data assessment and early warning system based on data analysis provided in this application embodiment. The system includes: a data preprocessing module, an assessment status determination module, a data classification and processing module, a resource scheduling and control module, and a credibility determination module. The data preprocessing module collects psychological assessment data for student mental health assessment within a preset assessment window, generates data behavior identifiers, and processes the data based on these identifiers to obtain the structural usability characteristics of the psychological assessment data. The assessment status determination module analyzes the structural usability characteristics of the psychological assessment data to obtain assessment status labels for the data. These labels include assessable status and conditionally limited status. The system comprises four modules: an assessment status module and an unassessable status module; a data classification and processing module, which generates an assessment task parameter set based on the structural availability characteristics of the psychological assessment data when the assessment status label is "assessable"; a data correction processing module, which performs data correction processing when the assessment status label is "conditionally limited"; otherwise, it suspends the assessment and issues a reminder; a resource scheduling and control module, which obtains a data completeness index based on the assessment task parameter set and analyzes the hierarchical scheduling results to schedule the psychological assessment data; and a credibility determination module, which inputs the psychological assessment data into the mental health assessment model for evaluation, outputs the evaluation results, obtains the processing efficiency index and processing coverage index of the psychological assessment data, and thus obtains the credibility identifier of the evaluation results, completing the psychological assessment data evaluation task.

[0026] In this embodiment, as Figure 2 As shown, Figure 2 The flowchart of the student mental health assessment process for the data analysis-based student mental health data assessment and early warning system provided in this application embodiment is as follows: Within a preset assessment window, psychological assessment data for student mental health assessment is collected to obtain corresponding structure availability characteristics. Based on the structure availability characteristics, assessment status labels for the psychological assessment data are obtained. When the assessment status label is an assessable state, an assessment task parameter set is generated based on the psychological assessment data. When the assessment status label is a conditionally limited assessment state, data correction processing is performed, and a secondary assessment status label is obtained based on the corrected psychological assessment data. When the secondary assessment status label is an assessable state, a corresponding assessment task parameter set is generated; otherwise, the assessment task for the psychological assessment data is paused and a reminder is issued. The psychological assessment data is scheduled and processed based on the assessment task parameter set to obtain a credibility identifier for the assessment result. When the credibility identifier indicates a credible result, the assessment result is output as a mental health assessment result. When the credibility identifier indicates a dishonest result, the assessment result is marked as an invalid assessment result, and a review process is triggered.

[0027] Within the current assessment window, psychological assessment data includes various psychological assessment sub-data. Candidate psychological assessment sub-data refers to the smallest data unit within the assessment window that reflects a student's mental health status, collected by different data collection platforms such as student-side applications, environmental sensors, and online systems. Candidate psychological assessment sub-data includes data related to psychological scale responses, data related to psychological risk scoring dimensions, and information on the collection behavior. Specifically, data related to psychological scale responses includes at least the items the student has answered on the mental health scale and the corresponding answer for each item; data related to psychological risk scoring dimensions includes at least psychological risk dimensions such as anxiety, depression, stress, and mood swings, and their corresponding scores; and information on the collection behavior includes at least the time of data collection and the type of data source. Data source types include student-side applications, environmental sensors, and online systems. Student-side applications include at least psychological testing applications, campus applications, and student online psychological testing terminals; environmental sensors include at least wearable devices and campus environmental monitoring equipment; and online systems include at least school management systems, online behavior recording systems, and learning platforms or interactive systems.

[0028] The system acquires each candidate psychological assessment sub-data and generates a corresponding data behavior identifier. The data behavior identifier includes the data source type, collection timestamp, number of completed items, and number of risk scoring dimensions. Candidate psychological assessment sub-data with zero completed items and zero risk scoring dimensions are recorded as invalid psychological assessment sub-data and will not enter the subsequent data processing flow. Otherwise, they are recorded as psychological assessment sub-data. When all candidate psychological assessment sub-data of a psychological assessment data are invalid psychological assessment sub-data, the system stops processing the assessment task of that psychological assessment data.

[0029] The system identifies the psychological scale response data contained in the candidate psychological assessment sub-data, counts the total number of answered items, and records it as the number of completed items; the system also identifies the psychological risk scoring dimension data contained in the candidate psychological assessment sub-data, counts the total number of psychological risk dimensions, and records it as the number of risk scoring dimensions.

[0030] The structural usability features include key field completeness and key data continuity. The key field completeness is obtained by the following method: For each psychological assessment sub-data, the system overlays the number of completed items and the number of risk scoring dimensions based on its data behavior identifier to obtain the number of key fields for that psychological assessment sub-data. Within the current assessment window, the system overlays the number of key fields for all psychological assessment sub-data to obtain the total number of key fields for the psychological assessment data. The system then calculates the ratio of this total number of key fields to the preset key field reference number to obtain the key field completeness of the psychological assessment data.

[0031] The key data continuity is obtained by the following method: The system sorts the collection timestamps of all psychological assessment sub-data within the assessment window according to the time order to obtain the collection time series. Based on the collection time series, the system calculates the collection time interval between adjacent psychological assessment sub-data, obtains the preset maximum collection interval threshold, divides the collection time interval by the maximum collection interval threshold to obtain the ratio result, and takes the average of all ratio results within the current assessment window to obtain the key data continuity.

[0032] It should be noted that the various threshold parameters involved are not arbitrarily set, but are pre-set by the system based on statistical analysis of historical operating data. For example, the specific method for obtaining the preset reference number of key fields is as follows: During historical operation, a certain number of historical evaluation windows are selected, and psychological evaluation data samples with the evaluation status label of "evaluable" and the evaluation result credibility label of "credible result" are filtered out as a reference sample set. For a certain psychological evaluation data in the reference sample set, the system counts the number of key fields of each psychological evaluation sub-data in the corresponding evaluation window, and then sums up the number of key fields of each psychological evaluation sub-data to obtain the total number of historical key fields of the psychological evaluation data. The system takes the average of the total number of historical key fields of all psychological evaluation data in the reference sample set, and uses the average as the preset reference number of key fields.

[0033] The mental health assessment model is a composite rule-driven model. It performs scaled scoring on data related to mental health scale responses based on mental health scale scoring rules, and assesses the risk level of data related to the psychological risk scoring dimension based on psychological risk assessment rules. The output is an assessment result of the student's mental health status, which is a level (e.g., good mental health, mental health requiring attention). When the credibility indicator of the assessment result is "credible," the system considers the model's output reliable and can be used as the final mental health assessment result. When the credibility indicator is "unreliable," the system marks the assessment result as invalid and triggers a review process. The specific method for triggering the review process is as follows: the mental health assessment model re-evaluates the mental health assessment data and outputs a secondary assessment result. If the credibility indicator of this secondary assessment result is still "unreliable," the assessor is reminded to review the student's mental health assessment data; otherwise, the secondary assessment result is used as the final mental health assessment result for this data.

[0034] Mental health scale scoring rules refer to a set of rules for rating students' completed questions and their answers according to the predefined item structure, scoring method, and dimension affiliation of the mental health scale. Mental health risk assessment rules refer to a set of rules for judging and classifying students' mental health risk status based on the psychological risk scoring dimensions and their corresponding scores.

[0035] Furthermore, structural usability features include key field completeness and key data continuity. Preset thresholds for field completeness and data continuity are obtained. The key field completeness and key data continuity of the psychological assessment data are compared with these thresholds, respectively. When both the key field completeness and key data continuity are greater than the thresholds, the psychological assessment data is labeled as assessable. When both the key field completeness and key data continuity are below the thresholds, the psychological assessment data is labeled as unassessable. Otherwise, it is labeled as conditionally restricted assessment. The specific method is as follows:

[0036] In this embodiment, the assessment status label indicates whether the psychological assessment data within the current assessment window can be used to carry out the assessment task. The key field completeness reflects the degree to which the psychological assessment data meets the content requirements for carrying out the assessment task, indicating whether the number of completed items and the number of risk scoring dimensions in the psychological assessment sub-data obtained within the assessment window meet the minimum content requirements for carrying out the assessment task. The key data continuity reflects the stability of the collection of psychological assessment data over time, indicating whether the psychological assessment data is collected continuously and stably within the assessment window, thereby avoiding the distortion of psychological state judgment caused by excessively large collection intervals.

[0037] When the completeness of key fields in psychological assessment data is greater than the preset field completeness threshold and the continuity of key data is greater than the preset data continuity threshold, it means that the psychological assessment data obtained in the current assessment window meets the basic requirements for carrying out the assessment task in both the dimensions of content completeness and time continuity. Therefore, when the system determines the assessment status label of the psychological assessment data to be in an assessable state, it allows the psychological assessment data to directly enter the subsequent mental health assessment process and carry out the assessment task.

[0038] When only one of the key fields of psychological assessment data, namely completeness and continuity, exceeds the corresponding threshold, it indicates that the psychological assessment data has assessment value in some dimensions, but the overall data conditions are not yet fully sufficient. For this psychological assessment data, the system will determine the assessment status label as a condition-limited assessment status and attempt to supplement or repair the data conditions through subsequent data correction processing mechanisms, thereby improving the usability of psychological assessment data while ensuring the reliability of the assessment.

[0039] When the completeness of key fields in psychological assessment data is below the field completeness threshold and the continuity of key data is below the data continuity threshold, it indicates that the psychological assessment data obtained in the current assessment window has both serious content missingness and discontinuous collection problems. Such psychological assessment data is difficult to support effective mental health assessment, and direct assessment is prone to misjudgment or unstable assessment results. Therefore, the system determines the assessment status label of the psychological assessment data as unassessable and suspends the psychological assessment data from entering the subsequent mental health assessment process to avoid outputting unreliable assessment results when the data conditions are obviously insufficient.

[0040] Furthermore, the evaluation task parameter set includes field completeness score, data continuity score, and timeliness weight. Based on the structural availability characteristics of the psychological evaluation data, the corresponding field completeness score and data continuity score are obtained. Within the current evaluation window, the number of psychological evaluation sub-data points is counted, and a preset timeliness attention interval is obtained within the current evaluation window. The number of psychological evaluation sub-data points whose collection timestamps fall within the timeliness attention interval is counted and recorded as the evaluation attention count. Based on this evaluation attention count, the timeliness weight is obtained. The specific method is as follows:

[0041] In this embodiment, a preset completeness score reference set is obtained, and the completeness of key fields of the psychological assessment data is matched and mapped with the completeness score reference set. When the completeness of a key field of the psychological assessment data falls into a certain key field completeness interval of the completeness score reference set, it is matched and mapped to that interval, and the field completeness score corresponding to the interval is obtained. The completeness score reference set includes each key field completeness interval and its corresponding field completeness score. A preset continuity score reference set is also obtained, and the continuity of key data of the psychological assessment data is matched and mapped with the continuity score reference set. When the continuity of key data of the psychological assessment data falls into a certain key data continuity interval of the continuity score reference set, it is matched and mapped to that interval, and the data continuity score corresponding to the interval is obtained. The continuity score reference set includes each key data continuity interval and its corresponding data continuity score.

[0042] A higher field completeness score indicates that the psychological assessment data is more complete and stable, and that relatively reliable assessment results can be obtained after entering the mental health assessment process. A higher data continuity score indicates that the psychological assessment data is more concentrated within the assessment window.

[0043] Within the current assessment window, the number of assessment concerns for psychological assessment data is divided by the corresponding number of psychological assessment sub-data to obtain the timeliness weight. When the number of assessment concerns for psychological assessment data is zero, a preset minimum baseline timeliness weight is obtained as the timeliness weight for that psychological assessment data. The timeliness weight indicates the urgency of processing the psychological assessment data within the current assessment window, reflecting whether the psychological assessment data is approaching the end point of the assessment window in terms of time dimension. Within the current assessment window, the system counts the total number of psychological assessment sub-data contained in the psychological assessment data, denoted as the number of psychological assessment sub-data. The system obtains a preset timeliness concern interval, set at the end of the current assessment window, indicating the collection time range of psychological assessment sub-data that is about to exceed the assessment window. The total number of psychological assessment sub-data whose collection timestamps fall within the timeliness concern interval is counted, denoted as the assessment concern count. The assessment concern count indicates the number of psychological assessment sub-data that need to be processed and assessed as soon as possible, generated near the end of the assessment window. The ratio of the assessment concern count to the number of psychological assessment sub-data is calculated to obtain the timeliness weight, which indicates the proportion of psychological assessment sub-data that urgently needs to be processed within the psychological assessment data.

[0044] By weighting psychological assessment data according to its timeliness, the system can accurately identify psychological assessment data with high time urgency. This allows the system to prioritize the timely processing and assessment of psychological assessment data with high time urgency when resources are limited, thus preventing assessment results from becoming invalid or being discarded due to the expiration of the assessment window.

[0045] Furthermore, the start time of the current assessment window is obtained, and a preset time compensation interval is extended forward to obtain an extended assessment window. Psychological assessment data is collected within this extended assessment window, and based on the data, the structural usability characteristics of the psychological assessment data are obtained. The secondary assessment status label of the psychological assessment data is then analyzed to obtain this label. When the secondary assessment status label of the psychological assessment data is assessable, the corresponding assessment task parameter set is generated; otherwise, the assessment task for that psychological assessment data is paused, and a reminder is issued. The specific method is as follows:

[0046] In this embodiment, the start time of the current evaluation window is obtained. Using the start time of the current evaluation window as a reference point, the start time is shifted historically by the length of a preset time compensation interval. The difference between the start time and the interval length is calculated to obtain the corrected start time, thus obtaining an extended evaluation window. The end time of the extended evaluation window is consistent with the end time of the original evaluation window. The time compensation interval can improve the situation of missing or discontinuous psychological evaluation data caused by response delays, data upload failures, and network latency. By obtaining the extended evaluation window, the system re-collects psychological evaluation data within this time period, making the data coverage more complete and the system obtains more data that can be used for evaluation. Within the current evaluation window, data correction processing is performed on psychological evaluation data with the evaluation status label of "conditionally limited evaluation state" to obtain the extended evaluation window. This extended evaluation window does not affect the length of the next evaluation window.

[0047] Within the extended evaluation window, the system recalculates the structural usability characteristics of the re-collected psychological evaluation data and analyzes it to obtain secondary evaluation status labels. These labels include evaluable, conditionally limited, and unevaluable states. When the secondary evaluation status label of the psychological evaluation data is evaluable, it indicates that the data integrity and continuity meet the system's evaluation requirements. Therefore, the system generates the corresponding evaluation task parameter set, adds the psychological evaluation data to the evaluation task queue, and executes the evaluation task normally. Otherwise, it indicates that the data quality or continuity of the psychological evaluation data is still insufficient. The system will suspend the evaluation task for that psychological evaluation data and issue a reminder to prevent the generation of unreliable evaluation results.

[0048] By performing data correction processing, a time compensation interval and an expanded assessment window are obtained, which effectively compensates for assessment blind spots caused by data delays or missing data, and improves the completeness and usability of psychological assessment data.

[0049] Furthermore, the assessment task parameter set of the psychological assessment data is obtained, and the average of the field completeness score and the data continuity score is taken as the data completeness index of the psychological assessment data. This data completeness index is then multiplied by the timeliness weight to obtain the data completeness index of the psychological assessment data. The specific method is as follows:

[0050] In this embodiment, the average of the field completeness score and the data continuity score is taken as the data completeness index of the psychological assessment data. The values ​​of the field completeness score, data continuity score, and data completeness index are all within the range [0, 100]. The data completeness index reflects the overall usability of the psychological assessment data. The data completeness index is then multiplied by a timeliness weight to obtain the data integrity index. By multiplying the data completeness index by the timeliness weight, the data integrity index can simultaneously reflect the data's completeness and processing urgency. Therefore, under limited resource conditions, the system prioritizes processing psychological assessment data that is both complete and urgent, optimizing the execution of the assessment task queue and improving the system's resource utilization efficiency and the reliability of the assessment results.

[0051] Furthermore, based on the data completeness index of the psychological assessment data, this data completeness index is compared with the preset first completeness index and second completeness index. When the data completeness index is greater than the second completeness index, the hierarchical scheduling result is first-level scheduling; when the data completeness index is less than the second completeness index but greater than the first completeness index, the hierarchical scheduling result is second-level scheduling; otherwise, the hierarchical scheduling result is third-level scheduling. The specific method is as follows:

[0052] In this embodiment, the system acquires a preset first completeness index and a second completeness index, wherein the first completeness index is less than the second completeness index. The first completeness index represents the medium priority processing threshold, and the second completeness index represents the high priority processing threshold, which can distinguish psychological assessment data with different urgency levels and data completeness.

[0053] When the data completeness index of psychological assessment data is greater than the second completeness index, it indicates that the psychological assessment data is both complete and urgent. The system allocates it to the first-level scheduling to ensure that its assessment task can be processed with priority. When the data completeness index of psychological assessment data is lower than the second completeness index but higher than the first completeness index, it indicates that the psychological assessment data is of moderate urgency and not very complete. The system allocates it to the second-level scheduling for medium-priority processing. When the data completeness index is lower than the first completeness index, it indicates that the psychological assessment data is relatively not urgent and has low data completeness. The system allocates it to the third-level scheduling to postpone the processing order and avoid excessive consumption of the system's valuable processing resources.

[0054] By employing the hierarchical scheduling method described above, the system can scientifically divide the processing levels of psychological assessment data into corresponding assessment tasks based on data completeness indicators. This enables the rational allocation of limited resources, ensuring that high-priority psychological assessment data is processed promptly, medium-priority data is queued efficiently, and low-priority data is processed later. This improves the overall assessment efficiency and resource utilization of the system, guarantees the timeliness and reliability of mental health assessment results, reduces the risk of misjudgment due to task conflicts or unreasonable resource allocation, and achieves refined management of assessment tasks.

[0055] Furthermore, based on the hierarchical scheduling results of psychological assessment data, the psychological assessment data is marked as hierarchical psychological assessment data. Within the current assessment window, the data completeness index of all psychological assessment data at the current level is superimposed to obtain the priority index of that level. The priority indices of each level are superimposed to obtain the total priority index, thereby obtaining the bandwidth weight of the level. Hierarchical psychological assessment data includes first-level, second-level, and third-level psychological assessment data. The levels include first, second, and third levels. First-level psychological assessment data is included in the high-priority assessment task queue, second-level psychological assessment data is included in the medium-priority assessment task queue, and third-level psychological assessment data is included in the low-priority assessment task queue. The system processing bandwidth is obtained, and the system processing bandwidth is multiplied by the bandwidth weight of the level to obtain the hierarchical processing bandwidth of all psychological assessment data at that level. For psychological assessment data at the same level, a secondary allocation of hierarchical processing bandwidth is performed. The specific method is as follows:

[0056] In this embodiment, psychological assessment data is labeled as psychological assessment data at each level. Specifically, psychological assessment data with a first-level scheduling result is labeled as first-level psychological assessment data, psychological assessment data with a second-level scheduling result is labeled as second-level psychological assessment data, and psychological assessment data with a third-level scheduling result is labeled as third-level psychological assessment data.

[0057] Within the current evaluation window, the system superimposes the data completeness indicators of all first-level psychological assessment data to obtain the first-level priority indicator. Similarly, it superimposes the data completeness indicators of all second-level psychological assessment data to obtain the second-level priority indicator. The system then superimposes the data completeness indicators of all third-level psychological assessment data to obtain the third-level priority indicator. Finally, it superimposes the priority indicators from each level to obtain the total priority indicator. Dividing the first-level priority indicator by the total priority indicator yields the first-level bandwidth weight; the second-level priority indicator by the total priority indicator yields the second-level bandwidth weight; and the third-level priority indicator by the total priority indicator yields the third-level bandwidth weight. The system processing bandwidth is then obtained. Multiplying this system processing bandwidth by the first-level bandwidth weight yields the first-level hierarchical processing bandwidth; multiplying this system processing bandwidth by the second-level bandwidth weight yields the second-level hierarchical processing bandwidth; and multiplying this system processing bandwidth by the third-level bandwidth weight yields the third-level hierarchical processing bandwidth.

[0058] The specific method for obtaining the system processing bandwidth is as follows: The system determines the assessment processing resources used for psychological assessment data processing. Within the current assessment window, the system performs status detection on the assessment processing resources, obtains the current available computing resource ratio, and performs unified conversion processing on the available computing resource ratio to obtain the system processing bandwidth.

[0059] Significant differences exist in the data completeness indicators for psychological assessment data at different levels. The high-priority assessment task queue is used to handle urgent tasks with high data completeness, ensuring that key data can be assessed in a timely manner. The medium-priority assessment task queue handles tasks with moderate urgency and low data completeness. The low-priority assessment task queue postpones the processing of relatively non-urgent tasks with low data completeness. This achieves a scientific division of assessment task processing priorities and a reasonable allocation of processing resources, enabling system resources to prioritize the most urgent and important data, improving the overall assessment efficiency of the system, and avoiding system delays caused by low-priority assessment tasks occupying key resources.

[0060] Bandwidth weights represent the proportion of the total assessment task volume at different levels relative to the total assessment task volume. The system processing bandwidth is obtained and multiplied by the bandwidth weight for each level to obtain the hierarchical processing bandwidth for the first, second, and third levels. The hierarchical processing bandwidth represents the total processing bandwidth allocated to all psychological assessment data at that level. Since the system's processing bandwidth is limited, allocating bandwidth to each level through bandwidth weights allows for the rational allocation of system resources to psychological assessment data at different levels, improving the processing efficiency and accuracy of the assessment tasks.

[0061] System processing bandwidth represents the total number of evaluation tasks that the system can complete per unit of time within the current evaluation window, reflecting the system's maximum processing capacity within the current evaluation window.

[0062] Furthermore, the evaluation attention count of the psychological assessment data is obtained, and the total evaluation attention count of all psychological assessment data at the same level is counted. The evaluation attention count of the psychological assessment data is divided by the total evaluation attention count to obtain the evaluation urgency of the psychological assessment data. The number of psychological assessment sub-data points of the psychological assessment data is obtained, and the total number of psychological assessment sub-data points of all psychological assessment data at the same level is counted. The number of psychological assessment sub-data points of the psychological assessment data is divided by the total number of psychological assessment sub-data points to obtain the task load of the psychological assessment data. The average of the evaluation urgency and task load of the psychological assessment data is taken as the secondary bandwidth weight of the psychological assessment data. Based on the hierarchical processing bandwidth of the level where the psychological assessment data is located, the secondary bandwidth weight of the psychological assessment data is multiplied by the corresponding hierarchical processing bandwidth to obtain the allocated processing bandwidth of the psychological assessment data. The specific method is as follows:

[0063] In this embodiment, the evaluation attention counts corresponding to all psychological evaluation data at the same level are summed to obtain the total evaluation attention count. The number of psychological evaluation sub-data corresponding to all psychological evaluation data at the same level is also summed to obtain the total number of psychological evaluation sub-data. Evaluation urgency indicates the time sensitivity of the psychological evaluation data within the current evaluation window; a higher evaluation urgency means the psychological evaluation data is closer to the end of the evaluation window, and the higher the timeliness requirement for evaluation processing. Task load indicates the data processing scale of the evaluation task corresponding to the psychological evaluation data; a higher task load means a larger amount of psychological evaluation data is processed, and a higher degree of resource consumption.

[0064] Within the same level, there may be multiple assessment tasks for psychological assessment data. Different psychological assessment data vary in terms of timeliness and processing load. The average of the assessment urgency and task load of the psychological assessment data is taken as the secondary bandwidth weight of the psychological assessment data. This integrates the urgency factor and the processing load factor to avoid a single factor dominating the allocation of processing bandwidth. This ensures that the allocation of processing bandwidth prioritizes assessment tasks with higher timeliness requirements, while also taking into account the processing complexity of the assessment tasks themselves, thus achieving a balance in resource allocation among psychological assessment data at the same level.

[0065] The allocated processing bandwidth represents the maximum processing bandwidth resources allocated to the psychological assessment data within the current assessment window. This ensures that each psychological assessment data task receives processing power commensurate with its urgency and data size under system resource constraints. It enables fine-grained scheduling of assessment resources within a hierarchy, avoiding processing delays or resource waste caused by differences in urgency and data size among psychological assessment data at the same level. This improves the overall efficiency and fairness of assessment data processing, thereby enhancing the timeliness and stability of mental health assessment results.

[0066] Furthermore, such as Figure 3 As shown, Figure 3 The flowchart for determining the credibility of the assessment results of the student mental health data assessment and early warning system based on data analysis provided in this application embodiment is as follows: The psychological assessment data is input into the mental health assessment model, which performs assessment processing and outputs the assessment results. During the model's assessment process, the processing efficiency index and processing coverage index of the psychological assessment data are obtained, thereby obtaining the credibility identifier of the assessment results. When the credibility identifier of the assessment results indicates that the results are credible, the assessment results are output as mental health assessment results; otherwise, if the results are unreliable, the assessment results are marked as invalid assessment results, and a review process is triggered to complete the assessment task of the psychological assessment data.

[0067] Within the current assessment window, based on the mental health assessment model, the processing efficiency index and processing coverage index of the mental health assessment data are obtained. These indices are then compared with preset processing efficiency thresholds and processing coverage thresholds, respectively. If both the processing efficiency index and the processing coverage index are greater than the processing efficiency threshold and the processing coverage threshold, the assessment result output by the mental health assessment model is deemed reliable and is used as the mental health assessment result. Otherwise, the result is deemed unreliable, marked as an invalid assessment result, and a review process is triggered. The specific method is as follows:

[0068] In this embodiment, the processing efficiency index of psychological assessment data is obtained by the following method: within the current assessment window, each psychological assessment sub-data is acquired, the actual processing time of each psychological assessment sub-data is recorded, a preset reference standard processing time is obtained, the reference standard processing time is divided by the actual processing time to obtain the time ratio of each psychological assessment sub-data, the time ratio is compared with the preset standard ratio, and when the time ratio of the psychological assessment sub-data is greater than the standard ratio, the standard ratio is used as the time ratio of the psychological assessment sub-data, all time ratios of the psychological assessment data are statistically analyzed, and the average value is taken as the processing efficiency index of the psychological assessment data.

[0069] The processing coverage index of psychological assessment data is obtained by the following method: within the current assessment window, each psychological assessment sub-data that has been processed by the psychological health assessment model is obtained and recorded as the processed effective sub-data. The total number of all processed effective sub-data is counted to obtain the total number of processed effective sub-data. The total number of processed effective sub-data is divided by the number of psychological assessment sub-data to obtain the processing coverage index of the psychological assessment data.

[0070] The reliability of the assessment results is independently determined by the processing efficiency index and processing coverage index of psychological assessment data, which improves the credibility of the psychological health assessment results at the assessment process level.

[0071] like Figure 4 As shown, Figure 4 The overall flowchart of the student mental health data assessment and early warning method based on data analysis provided in this application embodiment includes the following steps: Within a preset assessment window, collect psychological assessment data for student mental health assessment, generate data behavior identifiers, and based on the data behavior identifiers, process to obtain the structural usability characteristics of the psychological assessment data; based on the structural usability characteristics of the psychological assessment data, analyze to obtain assessment status labels for the psychological assessment data, including assessable status, conditionally limited assessment status, and unassessable status; when the assessment status label is assessable, generate an assessment task parameter set based on the structural usability characteristics of the psychological assessment data; when the assessment status label is conditionally limited, perform data correction processing; otherwise, pause the assessment and issue a reminder; based on the assessment task parameter set, obtain a data completeness index and analyze to obtain hierarchical scheduling results, thereby scheduling the psychological assessment data; input the psychological assessment data into a mental health assessment model for assessment, output the assessment results, obtain the processing efficiency index and processing coverage index of the psychological assessment data, thereby obtaining the credibility identifier of the assessment results, and completing the psychological assessment data assessment task.

[0072] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0073] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0074] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0075] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0076] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0077] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A student mental health data assessment and early warning system based on data analysis, characterized in that: include: The module includes a data preprocessing module, an evaluation status determination module, a data classification and processing module, a resource scheduling and control module, and a credibility determination module. The data preprocessing module is used to collect psychological assessment data of students' mental health assessment within a preset assessment window, generate data behavior identifiers, and process the data based on the data behavior identifiers to obtain the structural usability characteristics of the psychological assessment data. The assessment status determination module is used to analyze and obtain assessment status labels of psychological assessment data based on the structural availability characteristics of psychological assessment data. The assessment status labels include assessable status, conditionally limited assessment status, and unassessable status. The data classification and processing module is used to generate an assessment task parameter set based on the structural availability characteristics of the psychological assessment data when the assessment status label is an assessable state; to perform data correction processing when the assessment status label is a conditionally limited assessment state; otherwise, to pause the assessment and issue a reminder. The resource scheduling and control module is used to obtain data completeness indicators based on the evaluation task parameter set, and analyze the hierarchical scheduling results to perform scheduling processing on the psychological evaluation data. The credibility determination module is used to input psychological assessment data into a mental health assessment model for evaluation, output the evaluation results, obtain the processing efficiency index and processing coverage index of the psychological assessment data, thereby obtaining the credibility identifier of the evaluation results and completing the evaluation task of the psychological assessment data.

2. The student mental health data assessment and early warning system based on data analysis as described in claim 1, characterized in that, The specific method for obtaining the assessment status labels of the psychological assessment data is as follows: Structural usability features include the completeness of key fields and the continuity of key data; Obtain preset field completeness thresholds and data continuity thresholds. Compare the key field completeness and key data continuity of the psychological assessment data with the field completeness thresholds and data continuity thresholds, respectively. When both the key field completeness and key data continuity are greater than the field completeness threshold and the data continuity threshold, the assessment status label of the psychological assessment data is "evaluable". When both the key field completeness and key data continuity are below the field completeness threshold and the data continuity threshold, the assessment status label of the psychological assessment data is "unevaluable". Otherwise, it is "conditionally limited assessment".

3. The student mental health data assessment and early warning system based on data analysis as described in claim 1, characterized in that, The specific method for generating the evaluation task parameter set is as follows: The evaluation task parameter set includes field completeness score, data continuity score, and timeliness weight; Based on the structural availability characteristics of psychological assessment data, corresponding field completeness scores and data continuity scores are obtained. Within the current assessment window, the number of psychological assessment sub-data is counted, the preset timeliness attention interval within the current assessment window is obtained, and the number of psychological assessment sub-data whose collection timestamp falls within the timeliness attention interval is counted and recorded as the assessment attention number. Based on this assessment attention number, the timeliness weight is obtained.

4. The student mental health data assessment and early warning system based on data analysis as described in claim 1, characterized in that, The specific method for the execution data correction process is as follows: Obtain the start time of the current assessment window, extend it forward by a preset time compensation interval to obtain an extended assessment window, collect psychological assessment data within the extended assessment window, and obtain the structural usability characteristics of the psychological assessment data based on the psychological assessment data. Analyze the data to obtain the secondary assessment status label of the psychological assessment data. When the secondary assessment status label of the psychological assessment data is assessable, generate the corresponding assessment task parameter set; otherwise, pause the assessment task of the psychological assessment data and issue a reminder.

5. The student mental health data assessment and early warning system based on data analysis as described in claim 1, characterized in that, The specific method for obtaining the data completeness index is as follows: Obtain the assessment task parameter set of the psychological assessment data, take the average of the field completeness score and the data continuity score as the data completeness index of the psychological assessment data, and multiply the data completeness index by the timeliness weight to obtain the data completeness index of the psychological assessment data.

6. The student mental health data assessment and early warning system based on data analysis as described in claim 1, characterized in that, The specific method for obtaining the hierarchical scheduling result is as follows: Based on the data completeness index of psychological assessment data, the data completeness index is compared with the preset first completeness index and second completeness index. When the data completeness index is greater than the second completeness index, the hierarchical scheduling result is the first level scheduling. When the data completeness index is less than the second completeness index but greater than the first completeness index, the hierarchical scheduling result is the second level scheduling. Otherwise, the hierarchical scheduling result is the third level scheduling.

7. The student mental health data assessment and early warning system based on data analysis as described in claim 1, characterized in that, The specific method for performing the scheduling process is as follows: Based on the hierarchical scheduling results of psychological assessment data, psychological assessment data is marked as hierarchical psychological assessment data. Within the current assessment window, the data completeness index of all psychological assessment data at the current level is superimposed to obtain the priority index of that level. The priority index of each level is superimposed to obtain the total priority index, thereby obtaining the bandwidth weight of the level. The hierarchical psychological assessment data includes first-level psychological assessment data, second-level psychological assessment data, and third-level psychological assessment data. The hierarchy includes first-level, second-level, and third-level psychological assessment data. First-level psychological assessment data is placed in the high-priority assessment task queue, second-level psychological assessment data is placed in the medium-priority assessment task queue, and third-level psychological assessment data is placed in the low-priority assessment task queue. The system processing bandwidth is obtained, and the system processing bandwidth is multiplied by the bandwidth weight of the level to obtain the hierarchical processing bandwidth of all psychological assessment data in that level. For psychological assessment data in the same level, the hierarchical processing bandwidth is re-allocated.

8. The student mental health data assessment and early warning system based on data analysis as described in claim 7, characterized in that, The specific method for the secondary allocation of bandwidth for hierarchical processing is as follows: Obtain the number of assessment attentions for psychological assessment data, count the total number of assessment attentions for all psychological assessment data at the same level, divide the number of assessment attentions for psychological assessment data by the total number of assessment attentions to obtain the assessment urgency of psychological assessment data, obtain the number of psychological assessment sub-data for psychological assessment data, count the total number of psychological assessment sub-data for all psychological assessment data at the same level, divide the number of psychological assessment sub-data for psychological assessment data by the total number of psychological assessment sub-data to obtain the task load of psychological assessment data; The average of the urgency and task load of the psychological assessment data is taken as the secondary bandwidth weight of the psychological assessment data. Based on the hierarchical processing bandwidth of the level where the psychological assessment data is located, the secondary bandwidth weight of the psychological assessment data is multiplied by the corresponding hierarchical processing bandwidth to obtain the allocated processing bandwidth of the psychological assessment data.

9. The student mental health data assessment and early warning system based on data analysis as described in claim 1, characterized in that, The specific method for obtaining the credibility indicator of the evaluation result is as follows: Within the current assessment window, based on the mental health assessment model, the processing efficiency index and processing coverage index of the mental health assessment data are obtained. The processing efficiency index and processing coverage index of the mental health assessment data are compared with the preset processing efficiency threshold and processing coverage threshold, respectively. When the processing efficiency index of the mental health assessment data is greater than the processing efficiency threshold and the processing coverage index is greater than the processing coverage threshold, the credibility of the assessment result output by the mental health assessment model is marked as credible, and the assessment result is used as the mental health assessment result. Otherwise, the result is unreliable, the assessment result is marked as invalid, and the review process is triggered.

10. A method for student mental health data assessment and early warning based on data analysis, applied to the student mental health data assessment and early warning system based on data analysis as described in any one of claims 1-9, characterized in that, Includes the following steps: Within a preset assessment window, psychological assessment data of students' mental health is collected, data behavior identifiers are generated, and based on the data behavior identifiers, the structural usability characteristics of the psychological assessment data are obtained. Based on the structural availability characteristics of psychological assessment data, the assessment status labels of the psychological assessment data are analyzed and obtained. The assessment status labels include assessable status, conditionally limited assessment status, and unassessable status. When the evaluation status label is "evaluable", an evaluation task parameter set is generated based on the structural availability characteristics of the psychological evaluation data. When the evaluation status label is "conditionally limited", data correction processing is performed. Otherwise, the evaluation is paused and a reminder is issued. Based on the evaluation task parameter set, a data completeness index is obtained, and the hierarchical scheduling result is analyzed to schedule and process the psychological evaluation data. The psychological assessment data is input into the mental health assessment model for evaluation, and the assessment results are output. The processing efficiency index and processing coverage index of the psychological assessment data are obtained, thereby obtaining the credibility indicator of the assessment results, thus completing the assessment task of the psychological assessment data.

Images