An intelligent student psychological data collection and analysis system with multiple data sources

Abstract

The present invention discloses an intelligent student psychological data acquisition and analysis system with multiple data sources, which relates to the field of electronic digital data processing technology. The intelligent student psychological data acquisition and analysis system with multiple data sources includes: a data acquisition delay analysis module, a data transmission delay analysis module and a signal processing delay analysis module. The present invention performs data acquisition delay analysis on the acquisition process of the local preprocessing layer through the acquired first interference data, and at the same time determines whether to optimize the filter parameters based on the data acquisition delay analysis result, and then determines whether to optimize the sampling frequency based on the acquired data transmission delay analysis result, and finally determines whether to perform dynamic window optimization based on the acquired signal processing delay analysis result, thereby improving the timeliness of acquiring the psychological signals corresponding to the student psychological data in the dynamic load area, and solving the problem in the prior art that the timeliness of acquiring the psychological signals corresponding to the student psychological data in the dynamic load area is not high.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to an intelligent student psychological data collection and analysis system with multiple data sources. Background Art

[0002] The existing intelligent student psychological data collection and analysis system uses smart wearable devices, mobile applications and clinical assessment tools to collect multimodal indicators such as heart rate variability, voice emotion characteristics, cognitive behavioral data in real time, and combines it with machine learning algorithms for dynamic analysis. However, existing technologies cannot obtain students' psychological data in the dynamic load area in real time.

[0003] Existing technologies use multi-source and multi-modal data fusion to combine physiological data and behavioral data, pre-process the data to reduce noise interference, reduce manual intervention, and improve the degree of process automation.

[0004] For example, the invention patent with announcement number: CN117633329B announces a data collection method and system for multiple data sources, including: responsible for generating and managing data collection and configuring collection templates according to data types, executing specific collection tasks, using configured templates to obtain data through technology, equipped with a monitoring module to monitor task progress and abnormal scenarios, as well as a data cleaning module and a data persistence module, using multiple data source adaptation, and supporting heterogeneous data collection through data type identification and template configuration.

[0005] For example, the patent application with publication number CN116303699A discloses a method and system for data extraction and analysis based on multiple data sources, including: building a database and designing a three-level analysis model of U layer, C layer, and S layer, assigning a unified identification ID to multi-source heterogeneous data and completing data mapping, and generating structured and effective integrated data through standardized preprocessing, rule engine configuration, and redundant information deduplication to solve the problem of multi-source data dispersion and different formats.

[0006] However, in the process of implementing the technical solutions 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, data collection needs to be complete or transmitted in batches, and then uploaded to the cloud for unified processing, which results in high latency in obtaining data sources. The batch processing architecture relies on traditional database storage and then analysis, and is unable to stream and fuse multi-source data. The network round-trip delay accumulates, and there is a problem of low timeliness in obtaining psychological signals corresponding to students' psychological data in dynamic load areas. Summary of the Invention

[0008] The embodiment of the present application solves the problem in the prior art that the psychological signals corresponding to the student psychological data are not acquired in a timely manner in the dynamic load area by providing an intelligent student psychological data collection and analysis system with multiple data sources, thereby improving the timeliness of acquiring the psychological signals corresponding to the student psychological data in the dynamic load area.

[0009] An embodiment of the present application provides an intelligent student psychological data collection and analysis system with multiple data sources, including: a data acquisition delay analysis module, a data transmission delay analysis module, and a signal processing delay analysis module; wherein the data acquisition delay analysis module is used to perform data acquisition delay analysis on the acquisition process of the local preprocessing layer according to the acquired first interference data, and obtain a data acquisition delay analysis result, and the data acquisition delay analysis is used to quantify the degree of data response delay of the local preprocessing layer in the process of processing student psychological data; the data transmission delay analysis module is used to determine whether to optimize the filtering parameters according to the data acquisition delay analysis result, and at the same time perform data transmission delay analysis on the collaborative transmission process of the acquired student psychological data in the cloud and the terminal, and obtain a data transmission delay analysis result, and the filtering parameter optimization means adjusting the filtering strength and buffer capacity to improve the student psychological data in the cloud. The data acquisition efficiency of the preprocessing layer, the data transmission delay analysis is used to quantify the collaborative transmission efficiency of student psychological data during transmission between the cloud and the terminal; the signal processing delay analysis module is used to determine whether to perform sampling frequency optimization based on the obtained data transmission delay analysis results, and at the same time, based on the obtained second interference data, the signal processing delay analysis is performed on the psychological signal processing process in the dynamic load area to obtain the signal processing delay analysis results, and based on the obtained signal processing delay analysis results, it is determined whether to perform dynamic window optimization. The sampling frequency optimization means adjusting the sampling frequency amplitude and data compression activation to reduce the delay in the transmission of student psychological data between the cloud and the terminal. The signal processing delay analysis is used to quantify the load balance of student psychological data in the dynamic load area. The dynamic window optimization means adjusting the back pressure evaluation level to improve the efficiency and real-time performance of psychological signal processing.

[0010] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0011] 1. Perform data acquisition delay analysis on the acquisition process of the local preprocessing layer through the acquired first interference data, and then determine whether to optimize the sampling frequency based on the acquired data transmission delay analysis result. At the same time, perform signal processing delay analysis on the psychological signal processing process in the dynamic load area based on the acquired second interference data. Finally, determine whether to perform dynamic window optimization based on the acquired signal processing delay analysis result, thereby improving the optimization accuracy of filtering parameters and frequency sampling parameters, and further improving the real-time acquisition of student psychological data from multiple data sources in the dynamic load area, effectively solving the problem in the existing technology that the psychological signals corresponding to student psychological data are not acquired in a timely manner in the dynamic load area.

[0012] 2. The difference between the filter delay time and the reference filter delay time in the database is corrected by the filter delay time correction amount to obtain the filter delay time interference value. Similarly, the feature extraction delay time interference value and the ring buffer waiting time interference value are obtained through the same steps. The filter delay time interference value, the feature extraction delay time interference value and the ring buffer waiting time interference value are coupled to obtain the data acquisition delay analysis index, thereby achieving an improvement in the accuracy of the data acquisition delay analysis index, and then achieving a more accurate assessment of the delay degree of students' psychological data in the acquisition process.

[0013] 3. The difference between the low-frequency signal ratio and the reference low-frequency signal ratio in the database is corrected by the low-frequency signal ratio correction value to obtain the low-frequency signal ratio interference value. Similarly, the noise signal ratio interference value and the inter-node communication delay time interference value are obtained through the same steps. The low-frequency signal ratio interference value, the noise signal ratio interference value and the inter-node communication delay time interference value are coupled to obtain the signal processing analysis index, thereby achieving an improvement in the accuracy of obtaining the signal processing analysis index, and further achieving a more accurate assessment of the delay degree of cloud-based processing of student psychological data. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic diagram of the structure of a multi-data source intelligent student psychological data collection and analysis system provided in an embodiment of the present application;

[0015] Figure 2 This is a flowchart of the filtering parameter optimization workflow corresponding to the data acquisition delay analysis module provided in an embodiment of the present application;

[0016] Figure 3 A specific workflow diagram for optimizing the buffer capacity corresponding to the data acquisition delay analysis module provided in an embodiment of the present application;

[0017] Figure 4 A flowchart of the sampling frequency optimization workflow corresponding to the data transmission delay analysis module provided in an embodiment of the present application;

[0018] Figure 5 A flowchart of the data compression activation optimization workflow corresponding to the data transmission delay analysis module provided in an embodiment of the present application;

[0019] Figure 6 This is a workflow diagram corresponding to the signal processing delay analysis module provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] An embodiment of the present application solves the problem in the prior art that the timeliness of acquisition of psychological signals corresponding to student psychological data in dynamic load areas is low by providing an intelligent student psychological data collection and analysis system with multiple data sources. A data acquisition delay analysis module performs data acquisition delay analysis on the acquisition process of the local preprocessing layer according to the acquired first interference data to obtain a data acquisition delay analysis result. Then, a data transmission delay analysis module determines whether to perform filtering parameter optimization according to the data acquisition delay analysis result. At the same time, a data transmission delay analysis is performed on the collaborative transmission process of the acquired student psychological data between the cloud and the terminal to obtain a data transmission delay analysis result. Finally, a signal processing delay analysis is performed based on the acquired data transmission delay analysis result to determine whether to perform sampling frequency optimization. At the same time, a signal processing delay analysis is performed on the psychological signal processing process in the dynamic load area based on the acquired second interference data to obtain a signal processing delay analysis result. Based on the acquired signal processing delay analysis result, it is determined whether to perform dynamic window optimization, thereby achieving improved timeliness of acquisition of psychological signals corresponding to student psychological data in the dynamic load area.

[0021] The technical solution in the embodiment of the present application is to solve the problem that the psychological signals corresponding to the above-mentioned student psychological data are not obtained in a timely manner in the dynamic load area. The overall idea is as follows:

[0022] The data acquisition delay analysis results are used to determine whether to optimize the filtering parameters, and then the sampling frequency optimization is determined based on the obtained data transmission delay analysis results. At the same time, the signal processing delay analysis is performed on the psychological signal processing process in the dynamic load area based on the obtained second interference data. Finally, based on the obtained signal processing delay analysis results, it is determined whether to perform dynamic window optimization, thereby achieving the effect of improving the timeliness of obtaining the psychological signals corresponding to the students' psychological data in the dynamic load area.

[0023] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0024] like Figure 1As shown, it is a structural diagram of a multi-data source intelligent student psychological data collection and analysis system provided by an embodiment of the present application. The multi-data source intelligent student psychological data collection and analysis system provided by an embodiment of the present application includes: a data acquisition delay analysis module, a data transmission delay analysis module, and a signal processing delay analysis module; the data acquisition delay analysis module is used to perform data acquisition delay analysis on the acquisition process of the local preprocessing layer according to the acquired first interference data, and obtain a data acquisition delay analysis result. The data acquisition delay analysis is used to quantify the degree of data response delay of the local preprocessing layer in the process of processing student psychological data; the data transmission delay analysis module is used to determine whether to optimize the filtering parameters according to the data acquisition delay analysis result, and at the same time perform data transmission delay analysis on the collaborative transmission process of the acquired student psychological data in the cloud and the terminal to obtain a data transmission delay analysis result. The filtering parameter optimization is expressed by adjusting The filtering strength and buffer capacity are used to improve the data acquisition efficiency of student psychological data in the preprocessing layer. The data transmission delay analysis module is used to quantify the collaborative transmission efficiency of student psychological data in the cloud and terminal transmission process; the signal processing delay analysis is used to determine whether to optimize the sampling frequency based on the obtained data transmission delay analysis results. At the same time, based on the obtained second interference data, the signal processing delay analysis is performed on the psychological signal processing process in the dynamic load area to obtain the signal processing delay analysis results. Based on the obtained signal processing delay analysis results, it is determined whether to perform dynamic window optimization. The sampling frequency optimization means adjusting the sampling frequency amplitude and data compression activation to reduce the delay of student psychological data in the cloud and terminal transmission process. The signal processing delay analysis is used to quantify the load balance of student psychological data in the dynamic load area. The dynamic window optimization means adjusting the back pressure evaluation level to improve the efficiency and real-time performance of psychological signal processing.

[0025] In this embodiment, if Figure 2 As shown in FIG, the filter parameter optimization workflow diagram corresponding to the data acquisition delay analysis module provided in the embodiment of the present application is as follows Figure 3 As shown, this is a specific workflow diagram for buffer capacity optimization corresponding to the data acquisition delay analysis module provided in an embodiment of the present application, wherein the connection points are described as follows: 1 indicates that when the filter strength optimization does not meet the improvement threshold, the buffer capacity optimization is started; 2 indicates that after the buffer capacity optimization is completed, the main process is returned to end.

[0026] Figure 2 Data delay > threshold? means comparing the acquired data delay index with the data acquisition delay analysis index set in the database. If the data acquisition delay analysis index is greater than the data acquisition delay analysis index set in the database, it is necessary to start the filter parameter optimization. Figure 2"Improvement > Threshold?" indicates whether the reduction in the deviation of the data acquisition delay analysis indicator obtained after the reduction in the filter intensity is greater than the reduction set in the database. The parallel processing duration deviation and CPU utilization are input into the ring buffer adjustment area to output the increase in the ring buffer capacity. If the data acquisition delay analysis indicator re-obtained within the set number of adjustments is not greater than the data acquisition delay analysis indicator set in the database, it means that the buffer capacity optimization is complete. Otherwise, a buffer warning instruction is sent.

[0027] like Figure 4 As shown in FIG, the sampling frequency optimization workflow diagram corresponding to the data transmission delay analysis module provided in the embodiment of the present application is as follows Figure 5 As shown, it is a data compression activation optimization workflow diagram corresponding to the data transmission delay analysis module provided in the embodiment of the present application, wherein the connection point description is as follows: 3 indicates that when the frequency sampling optimization is judged to be unqualified, the connection point is used to jump to the data compression activation process, and 4 indicates that when the data compression activation is completed, the connection point is used to return to the end node of the main process; the obtained data transmission delay analysis result is used to determine whether to perform sampling frequency optimization. When the obtained data transmission delay analysis is less than the data transmission delay time set in the database, signal processing delay analysis is performed. If it is greater, sampling frequency optimization is performed. The data transmission delay time deviation and the data sampling frequency deviation are input together into the linear regression algorithm to output the reduction amplitude of the pressure sampling frequency. It is determined whether the reduction amplitude of the data transmission delay time deviation obtained after the reduction is greater than the reduction amplitude set in the database. If it is greater, the sampling frequency is continued to be reduced. If it is less, a data compression activation instruction is sent. Figure 4 Meet the standard within the number of times? It means that when it is determined that the data transmission delay time re-obtained within the sampling frequency adjustment times preset in the database is not greater than the data transmission delay time set in the database, the sampling frequency optimization is completed, otherwise a sampler warning instruction is sent; the obtained data transmission delay time deviation is input into the symmetric decompression to calculate the data compression activation parameter, and it is determined whether the compressed data transmission delay time obtained within the preset sampling frequency adjustment times is greater than the compressed data transmission delay time set in the database, if it is less, the data compression activation is completed, if it is greater, a data compression warning instruction is sent.

[0028] like Figure 6As shown, this is a workflow diagram corresponding to the signal processing delay analysis module provided in an embodiment of the present application. If the acquired signal processing delay analysis index is less than the signal processing delay analysis index set in the database, a cloud storage instruction is sent; if it is greater, dynamic window parameter adjustment is performed; the signal processing delay analysis index deviation and the back pressure assessment level deviation are input into the dynamic window adjustment mechanism to output the back pressure assessment level adjustment amplitude, and it is judged whether the reduction amplitude of the signal processing delay analysis index acquired again after adjustment is greater than the reduction amplitude set in the database; if not, it is uploaded to the cloud for data storage; if so, dynamic window parameter adjustment is performed, and the dynamic window adjustment amplitude is used to judge whether the signal processing delay analysis index acquired again within the preset dynamic window adjustment times is not greater than the set signal processing delay analysis index; if so, the dynamic window adjustment is completed; if not, a dynamic window warning instruction is sent.

[0029] Through the data acquisition delay index, the system can accurately quantify the degree of interference of the first interference data on the local preprocessing layer in obtaining student psychological data. Similarly, through the obtained signal processing delay index, the degree of interference of the second interference data on the cloud data processing process can be accurately quantified. This quantification provides objective and accurate data support for the collection and analysis process, which helps to understand the degree of interference in this process. Secondly, the obtained indicators can dynamically evaluate the optimization effect and determine whether the dynamic window needs to be readjusted based on the optimization effect. This dynamic adjustment mechanism ensures the continuous optimization and improvement of student psychological data collection and analysis, thereby achieving improved timeliness in the acquisition of psychological signals corresponding to student psychological data in the dynamic load area.

[0030] Furthermore, the first interference data includes a filtering delay time, a feature extraction delay time, and a ring buffer waiting time; and performing data acquisition delay analysis at a local preprocessing layer based on the acquired first interference data, specifically comprising the following steps:

[0031] First, the difference between the filter delay time and the reference filter delay time in the database is obtained, and the filter delay time correction value is used to correct it to obtain the filter delay time interference value. The specific expression is: , where It represents the filtering delay duration interference value of the student psychological data in the local preprocessing layer at the end of the current acquisition period, Indicates the filtering delay time of the student psychological data in the local preprocessing layer at the end of the current acquisition period, Indicates the reference filter delay time, Indicates the filter delay time correction amount.

[0032] Then, the difference between the feature extraction delay time and the reference feature extraction delay time in the database is obtained, and the feature extraction delay time correction value is used to correct it to obtain the feature extraction delay time interference value. The specific expression is: , where It represents the interference value of the feature extraction delay duration of the student psychological data in the local preprocessing layer at the end of the current acquisition period. Indicates the feature extraction delay of the student psychological data in the local preprocessing layer at the end of the current acquisition period, Indicates the reference feature extraction delay time, Indicates the correction amount for feature extraction delay time.

[0033] Then, the difference between the obtained ring buffer waiting time and the reference ring buffer waiting time in the database is corrected by the ring buffer waiting time correction amount to obtain the ring buffer waiting time interference value. The specific expression is: , where Indicates the ring buffer waiting time interference value of the student psychological data in the local preprocessing layer at the end of the current acquisition period, Indicates the waiting time of the ring buffer of student psychological data in the local preprocessing layer at the end of the current acquisition period. Indicates the waiting time of the reference ring buffer. Indicates the correction amount for the ring buffer waiting time.

[0034] Finally, the acquired wave delay time interference value, feature extraction delay time interference value and ring buffer waiting time interference value are coupled to obtain the data acquisition delay analysis index, which is used to quantify the degree of interference of the first interference data on the acquisition process of the local preprocessing layer. The specific expression is: , where Indicates the data acquisition latency analysis indicator of student psychological data in the local preprocessing layer at the end of the current acquisition period.

[0035] In this embodiment, the reference filtering delay time is represented by the sum and average of the historical filtering delay times of the student psychological data in the local preprocessing layer in the database at the end of the historical acquisition period, the reference feature extraction delay time is represented by the sum and average of the historical reference feature extraction delay times of the student psychological data in the local preprocessing layer in the database at the end of the historical acquisition period, and the reference ring buffer waiting time is represented by the sum and average of the historical reference ring buffer waiting times of the student psychological data in the local preprocessing layer in the database at the end of the historical acquisition period; the filtering delay time, feature extraction delay time and ring buffer waiting time are monitored by time sensors and are expressed in milliseconds (ms).

[0036] The filter delay time correction amount, feature extraction delay time correction amount and ring buffer waiting time correction amount are respectively the influence of the filter delay time, feature extraction delay time and ring buffer waiting time preset in the database on the process of obtaining the data acquisition delay analysis index. Specifically, the database stores the preset correction amounts corresponding to the filter delay time, feature extraction delay time and ring buffer waiting time. There is a pre-set mapping relationship between these correction amounts and the filter delay time, feature extraction delay time and ring buffer waiting time. This mapping relationship can be one-to-one or many-to-one. For example, in actual applications, the real-time filter delay time, feature extraction delay time and ring buffer waiting time can be input into this mapping relationship to quickly obtain the corresponding correction amount, which provides an important quantitative indicator for evaluating the timeliness of the acquisition of psychological signals corresponding to student psychological data in the dynamic load area, and thus more accurately calculates the data acquisition delay analysis index.

[0037] In this example, the value ranges of the filtering delay correction value, the feature extraction delay correction value, and the ring buffer waiting time correction value are all limited to between 0 and 1, and the sum of the three is 1.

[0038] It should be noted that there is a correlation between the three factors of filtering delay, feature extraction delay, and ring buffer waiting time. An increase in filtering delay means that the data has to wait and process for a longer time before entering the feature extraction link, resulting in a decrease in the amount of data received by the feature extraction module per unit time, which makes the feature extraction process take longer to complete, thereby increasing the feature extraction delay.

[0039] Similarly, changes in the filtering delay will affect the pace of data entering the ring buffer. When the filtering delay increases, the speed at which data reaches the ring buffer slows down, resulting in a decrease in the amount of data in the ring buffer, thereby affecting the buffer's scheduling and waiting mechanism; the increase in the feature extraction delay will be fed back to the filtering link, resulting in a large amount of resources being occupied, which in turn affects the processing efficiency of the filtering link and increases the filtering delay. Therefore, changes in the feature extraction delay will directly affect the speed at which data enters the ring buffer from the feature extraction link.

[0040] The increase in the waiting time of the ring buffer means that the backlog of data in the buffer will be fed back to the upstream, affecting the processing rhythm of the filtering link. The ring buffer is in a high occupancy state for a long time, resulting in the data output by the filtering module unable to enter the buffer in time, thereby forcing the filtering module to adjust the processing speed, which in turn affects the filtering delay time; when the waiting time of the ring buffer increases, the time for data to reach the feature extraction module is delayed, which may cause the feature extraction module to be idle and waiting.

[0041] By considering the above-mentioned mutual influence mechanism, we can have a more comprehensive understanding of the relationship between the data acquisition delay analysis indicators and each variable. These relationships are crucial for the timeliness evaluation of the acquisition of psychological signals corresponding to students' psychological data in the dynamic load area. By optimizing the filtering delay time, feature extraction delay time and ring buffer waiting time, the real-time performance of the student psychological data acquisition process is improved, and then the timeliness of the acquisition of psychological signals corresponding to students' psychological data in the dynamic load area is improved, effectively solving the problem of low timeliness of the acquisition of psychological signals corresponding to students' psychological data in the dynamic load area.

[0042] Furthermore, whether to perform filtering parameter optimization is determined based on the data acquisition delay analysis results. The specific steps include: comparing the acquired data acquisition delay analysis index with the data acquisition delay analysis index set in the database: if the acquired data acquisition delay analysis index is greater than the data acquisition delay analysis index set in the database, the data acquisition delay analysis result is recorded as unqualified and filtering parameter optimization is performed; if the acquired data acquisition delay analysis index is not greater than the data acquisition delay analysis index set in the database, the data acquisition delay analysis result is recorded as qualified and psychological signal delay analysis is performed; the filtering parameters include filtering strength and ring buffer capacity.

[0043] Specifically, the specific steps of filtering parameter optimization are as follows: the obtained data acquisition delay analysis index deviation and feature extraction delay time deviation are inputted into the real-time filtering algorithm of the adaptive filter to output the actual reduction amplitude of the filtering strength, the data acquisition delay analysis index deviation is used to quantify the difference between the obtained data acquisition delay analysis index and the data acquisition delay index set in the database, and the feature extraction delay time deviation is used to quantify the difference between the obtained feature extraction delay time and the feature extraction delay time set in the database; after the filtering strength is reduced once, it is judged whether the reduction amplitude of the obtained data acquisition delay analysis index deviation is greater than the reduction amplitude set in the database. If so, the filtering strength of the adaptive filter is continued to be reduced, otherwise a buffer capacity optimization instruction is sent and the buffer capacity is optimized; if the data acquisition delay analysis index re-acquired within the preset number of filtering strength adjustments is not greater than the data acquisition delay analysis index set in the database, the filtering strength optimization is completed, otherwise a filter warning instruction is sent and the preset personnel are prompted to intervene, and the set data acquisition delay analysis index is represented by the result of summing and averaging the historical data acquisition delay indicators of the student psychological data in the local preprocessing layer in the database at the end of the historical acquisition period.

[0044] Among them, the specific steps of buffer capacity optimization are: inputting the obtained parallel processing time deviation and CPU resource utilization into the ring buffer adjustment area to output the actual increase in the ring buffer capacity; if the data acquisition delay analysis index re-acquired within the preset filter intensity adjustment times is not greater than the data acquisition delay analysis index set in the database, then the buffer capacity optimization is completed and the data delay analysis is performed, otherwise a buffer warning instruction is sent and the preset personnel are prompted to intervene. The parallel processing time deviation is used to quantify the degree of difference between the obtained parallel processing time and the parallel processing time set in the database.

[0045] In this embodiment, the parallel processing duration deviation represents the difference between the parallel processing duration and the parallel processing duration set in the database, the feature extraction delay duration represents the difference between the feature extraction delay duration and the feature extraction delay duration set in the database, and the data acquisition delay analysis index deviation reduction amplitude represents the difference between the acquired data delay analysis index deviation and the re-acquired data acquisition delay analysis index deviation.

[0046] By integrating the data acquisition delay analysis indicator deviation and the feature extraction delay time deviation, they are imported as input into the real-time algorithm of the adaptive filter to dynamically generate the adjustment range of the filter strength, which helps to achieve dynamic adjustment of the filter strength. After executing a single intensity attenuation, the actual attenuation of the delay indicator deviation is compared with the reduction range preset in the database. If it exceeds, the filter strength is reduced, otherwise the buffer capacity adjustment mechanism is triggered. By setting early warning instructions, the preset personnel can take measures in advance to avoid efficiency decline, thereby reducing the probability of timeliness of data acquisition due to changes in filter parameters.

[0047] Secondly, by comparing the numerical relationship between the actual number of filter strength adjustments and the preset number of filter strength adjustments, it is helpful to determine the actual increase in the ring buffer capacity, optimize the buffer capacity and perform data delay analysis. At the same time, by sending early warning instructions, preset personnel can intervene in advance to avoid efficiency decline, thereby reducing the risk of system performance loss caused by filter parameter adjustment problems and ensuring the high real-time performance of the data processing process.

[0048] Furthermore, whether to perform sampling frequency optimization is determined based on the obtained data transmission delay analysis results. The specific steps include: if the obtained data transmission delay duration is greater than the data transmission delay duration set in the database, the data transmission delay analysis result is recorded as unqualified and the sampling frequency optimization is performed; if the obtained data transmission delay duration is less than the data transmission delay duration set in the database, the data transmission delay analysis result is recorded as qualified and a signal processing delay analysis is performed; the data transmission delay duration is used to quantify the degree of time delay experienced by the student psychological data from the sending end to the receiving end during the transmission process.

[0049] Specifically, the specific steps of sampling frequency optimization are as follows: Y1, the obtained data transmission delay time deviation and data sampling frequency deviation are inputted into the linear regression algorithm to output the actual reduction amplitude of the pressure sampling frequency; Y2, after a sampling frequency reduction, it is determined whether the obtained data transmission delay time deviation reduction amplitude is greater than the reduction amplitude set in the database. If so, the sampling frequency is further reduced, otherwise a data compression activation instruction is sent and Y4 is executed; Y3, if the data transmission delay time re-obtained within the preset sampling frequency adjustment times is not greater than the data transmission delay time set in the database, the sampling frequency optimization is completed, otherwise a sampler warning instruction is sent and a preset personnel is prompted to intervene; Y4, the specific steps of data compression activation are as follows: the obtained data transmission delay time deviation is inputted into the symmetric decompression algorithm to output the data compression activation parameter; if the compressed data transmission delay time re-obtained within the preset sampling frequency adjustment times is not greater than the compressed data transmission delay time set in the database, the data compression activation is completed, otherwise a data compression warning instruction is sent and a preset personnel is prompted to intervene; the data transmission delay time deviation is used to quantify the degree of difference between the obtained data transmission delay time and the preset data transmission delay time in the database.

[0050] In this embodiment, the set data transmission delay time is represented by the sum and average of the historical data transmission delay times at the end of the historical transmission period of student psychological data in the dynamic load area in the database. By comparing the dynamic change relationship between the data transmission delay time deviation and the sampling frequency deviation, the linear regression algorithm is used to accurately deduce the dynamic adjustment range of the pressure sampling frequency to achieve data collection and control. When the delay deviation decreases beyond the limit, the sampling frequency is optimized. Otherwise, the data compression mechanism is activated to compress redundant information. If the delay index returns to the standard threshold within the limited number of adjustments, the optimization process is determined to be completed; if it continues to exceed the limit, the early warning mechanism is triggered, prompting the preset personnel to intervene and investigate, thereby reducing the imbalance between data collection and transmission efficiency, and ensuring the high timeliness of student psychological data collection and analysis. The data transmission delay time deviation represents the difference between the data transmission delay time and the data transmission delay time set in the database. The data sampling frequency deviation represents the difference between the data sampling frequency and the data sampling frequency set in the database. The data transmission delay time deviation reduction range represents the difference between the data transmission delay time deviation obtained this time and the data transmission delay time deviation obtained last time.

[0051] Furthermore, the second interference data includes a low-frequency signal ratio, a noise signal ratio, and an inter-node communication delay duration; and a signal processing delay analysis is performed on the psychological signal processing process in the dynamic load area based on the acquired second interference data. The specific steps include:

[0052] First, the difference between the low-frequency signal ratio and the reference low-frequency signal ratio in the database is corrected by the low-frequency signal ratio correction amount to obtain the low-frequency signal ratio interference value. The specific expression is: , where Indicates the low-frequency signal ratio interference value of the psychological signal in the dynamic load area at the end of the current signal processing period, The proportion of low-frequency signals in the psychological signal representing the dynamic load area at the end of the current signal processing period, Indicates the proportion of reference low-frequency signal, Indicates the correction amount of low-frequency signal ratio.

[0053] Then, the difference between the noise signal ratio and the reference noise signal ratio in the database is corrected by the noise signal ratio correction amount to obtain the noise signal ratio interference value. The specific expression is: , where Indicates the noise signal ratio interference value of the psychological signal in the dynamic load area at the end of the current signal processing period, The ratio of the psychological signal representing the dynamic load region to the noise signal at the end of the current signal processing period, represents the reference noise signal ratio, Indicates the correction amount of the noise signal ratio.

[0054] Then, the difference between the inter-node communication delay time and the reference inter-node communication delay time in the database is corrected by the inter-node communication delay time correction amount to obtain the inter-node communication delay time interference value. The specific expression is: , where The interference value of the inter-node communication delay duration of the psychological signal in the dynamic load area at the end of the current signal processing period, The inter-node communication delay duration of the psychological signal representing the dynamic load area at the end of the current signal processing period, Indicates the communication delay between reference nodes, Indicates the correction amount of the communication delay between nodes.

[0055] Finally, the obtained low-frequency signal ratio interference value, noise signal ratio interference value and inter-node communication delay duration interference value are coupled to obtain the signal processing delay analysis index. The signal processing delay analysis index is used to quantify the degree of interference of the second interference data on the cloud data processing process. The signal processing delay analysis index The specific expression is: , where A signal processing delay analysis indicator that indicates the psychological signal in the dynamic load area at the end of the current signal processing period.

[0056] In this embodiment, the reference low-frequency signal ratio is represented by the sum and average of the historical low-frequency signal ratios at the end of the historical signal processing period of the student psychological data in the dynamic load area of ​​the database, and the low-frequency signal ratio is detected by a voltage acceleration sensor; the reference noise signal ratio is represented by the sum and average of the historical noise signal ratios at the end of the historical signal processing period of the student psychological data in the dynamic load area of ​​the database, and the noise signal ratio is measured by a spectrum analyzer and a threshold integral, and the units of the low-frequency signal ratio and the noise signal ratio are both percentages (%); the reference inter-node communication delay time is represented by the sum and average of the historical inter-node communication delay time at the end of the historical signal processing period of the student psychological data in the dynamic load area of ​​the database, and the inter-node communication delay time is obtained by network probe and differential calculation, and the unit is milliseconds (ms);

[0057] The correction amount for the proportion of low-frequency signals, the correction amount for the proportion of noise signals, and the correction amount for the delay time of communication between nodes are respectively the degrees of influence of the low-frequency signal proportion, the noise signal proportion, and the delay time of communication between nodes preset in the database on the process of obtaining signal processing analysis indicators. Specifically, the database stores preset correction amounts corresponding to the proportion of low-frequency signals, the proportion of noise signals, and the delay time of communication between nodes. There is a pre-set mapping relationship between these correction amounts and the proportion of low-frequency signals, the proportion of noise signals, and the delay time of communication between nodes. This mapping relationship can be one-to-one or many-to-one. For example, in actual applications, the real-time proportion of low-frequency signals, the proportion of noise signals, and the delay time of communication between nodes can be input into this mapping relationship to quickly obtain the corresponding correction amount, which provides an important quantitative indicator for evaluating the timeliness of signal processing of psychological signals corresponding to student psychological data in the dynamic load area, thereby more accurately calculating the signal processing analysis indicators.

[0058] In this example, the value ranges of the low-frequency signal ratio correction value, the noise signal ratio correction value, and the inter-node communication delay correction value are all limited to between 0 and 1, and the sum of the three is 1.

[0059] It should be noted that the three factors of low-frequency signal proportion, noise signal proportion and inter-node communication delay affect each other. When the proportion of noise signals increases, the purity of the data decreases, which will cause problems in data analysis and interpretation; the increase in inter-node communication delay means that data takes more time to transmit between nodes, resulting in a slower pace of data reaching the processing module; changes in the proportion of low-frequency signals may affect the recognition and processing of noise signals, and will also affect the data characteristics of inter-node communication.

[0060] Changes in the delay in communication between nodes will affect the real-time processing of low-frequency and noise signals. When the delay increases, the timeliness of the data decreases, which in turn affects the accurate analysis of low-frequency and noise signals. Changes in the proportion of low-frequency signals and noise signals will be fed back to the communication link between nodes, affecting the efficiency of data transmission and processing. Changes in the delay in communication between nodes will also be fed back upstream, affecting the collection and analysis process of low-frequency and noise signals.

[0061] Students' psychological signals are essentially a comprehensive reflection of bioelectric signals (such as EEG, ECG, etc.) or characteristic signals (such as voice intonation, body movement frequency, etc.), and usually contain multiple frequency band components. The proportion of low-frequency signals reflects the degree of expression of specific characteristics in the students' psychological state. When the proportion of low-frequency signals increases, it indicates that there are more invalid signals in the psychological signals. At this time, extra time is required to process these invalid signals, resulting in an increase in calculation amount, thereby increasing the length of signal processing delay.

[0062] By considering the above-mentioned mutual influence mechanism, we can have a more comprehensive understanding of the relationship between the signal processing delay analysis indicators and various variables, which helps to improve the efficiency of processing students' psychological signals in the cloud, and provides a reliable basis for accurately capturing changes in students' psychological states and timely adjusting intervention strategies, ensuring that the cloud-based psychological signal processing system can still maintain efficient and stable operation under complex interactive influences, thereby achieving an improvement in the timeliness of obtaining psychological signals corresponding to students' psychological data in the dynamic load area, and effectively solving the problem of low timeliness of obtaining psychological signals corresponding to students' psychological data in the dynamic load area.

[0063] Furthermore, whether to perform dynamic window optimization is determined based on the obtained signal processing delay analysis results. The specific steps include: comparing the obtained signal processing delay analysis index with the signal processing delay analysis index set in the database: if the obtained signal processing delay analysis index is greater than the signal processing delay analysis index set in the database, the data processing delay analysis result is recorded as unqualified and dynamic window parameter adjustment is performed; if the obtained signal processing delay analysis index is not greater than the signal processing delay analysis index set in the database, the data processing delay analysis result is recorded as qualified and a cloud storage instruction is sent; dynamic window parameter adjustment includes dynamic window adjustment and back pressure assessment level; the back pressure assessment level is used to quantify the degree of obstruction of the obtained student psychological data during the processing process.

[0064] In this embodiment, the dynamic window strategy flexibly adjusts the window size based on the back-pressure assessment level. When the back-pressure assessment level increases, it means that the processing of student psychological data is severely hindered. In this case, the dynamic window will be appropriately narrowed to reduce the amount of data entering the processing flow per unit time, alleviate processing pressure, and avoid further delays caused by data backlogs. When the back-pressure assessment level decreases, indicating that data processing is relatively smooth, the dynamic window will be appropriately expanded to improve data processing efficiency and fully utilize system resources. During the dynamic window parameter adjustment process, the system monitors the changes in various indicators in real time and dynamically adjusts them according to actual conditions. In addition, the qualified data processing delay analysis results are sent to the cloud for storage. This not only facilitates the subsequent review and analysis of signal processing performance, but also improves the real-time performance of cloud-based signal processing, thereby improving the real-time performance of the entire system.

[0065] The specific steps of dynamic window parameter optimization are as follows: inputting the obtained signal processing delay analysis indicator deviation and back pressure assessment level deviation into the dynamic window adjustment mechanism to output the adjustment range of the back pressure assessment level; after a back pressure assessment level adjustment, determining whether the reduction range of the re-acquired signal processing delay analysis indicator deviation is greater than the reduction range set in the database; if so, dynamic window parameter adjustment is performed; otherwise, the data is uploaded to the cloud for cloud data storage; inputting the obtained signal processing delay analysis indicator deviation and back pressure assessment level deviation into the dynamic window adjustment mechanism to output the adjustment range of the back pressure assessment level; dynamic window adjustment means automatically switching the window strategy based on the fluctuation type of the re-acquired signal processing delay analysis indicator to output the window adjustment range; if the re-acquired signal processing delay analysis indicator within the preset dynamic window adjustment times is not greater than the signal processing delay analysis indicator set in the database, the dynamic window adjustment is completed; otherwise, a dynamic window area warning instruction is sent to remind the preset personnel to intervene; the signal processing delay analysis indicator deviation is used to quantify the degree of difference between the obtained signal processing delay analysis indicator and the signal processing delay analysis indicator set in the database; the back pressure assessment level deviation is used to quantify the degree of difference between the obtained back pressure assessment level and the back pressure assessment level set in the database.

[0066] In this embodiment, the signal processing delay analysis indicator deviation represents the difference between the signal processing delay analysis indicator and the signal processing delay analysis indicator set in the database, and the back pressure assessment level deviation represents the difference between the back pressure assessment level and the back pressure assessment level set in the database; the back pressure assessment level is quantified by real-time monitoring of system resources (such as memory usage) and task queue length. The original back pressure assessment level is set by a preset person, usually to save resource utilization, and is therefore too conservative (triggering back pressure too early). However, the load fluctuation of the psychological signal in the actual processing process may show nonlinear characteristics (such as periodic peaks). If the back pressure assessment level is not optimized at this time, it may cause data backlog or packet loss, because the system may over-limit throughput under low load or fail to trigger the protection mechanism in time under high load.

[0067] The signal processing delay analysis index deviation and the back pressure assessment level deviation are input into the dynamic window adjustment mechanism to output the adjustment range of the back pressure assessment level. The signal processing delay and back pressure conditions are comprehensively considered. After a back pressure assessment level adjustment, the relationship between the reduction range of the regained signal processing delay analysis index deviation and the reduction range set in the database is judged. If it is greater than, the dynamic window parameter adjustment is continued, which helps to continuously optimize the signal processing effect until a more ideal state is reached; if it is not greater than, the data is uploaded to the cloud for storage, which is convenient for subsequent analysis and tracing of the adjustment process and results, and helps to ensure the stability and accuracy of the student psychological data signal processing, thereby improving the high real-time performance of the entire system in processing the student's psychological state.

[0068] To sum up, the embodiment of the present application performs data acquisition delay analysis on the acquisition process of the local preprocessing layer through the acquired first interference data, and then determines whether to perform sampling frequency optimization based on the acquired data transmission delay analysis result. At the same time, based on the acquired second interference data, a signal processing delay analysis is performed on the psychological signal processing process in the dynamic load area. Finally, based on the acquired signal processing delay analysis result, it is determined whether to perform dynamic window optimization, thereby achieving an improvement in the optimization accuracy of filtering parameters and frequency sampling parameters, and further achieving an improvement in the real-time acquisition of student psychological data from multiple data sources in the dynamic load area, effectively solving the problem in the prior art that the psychological signals corresponding to student psychological data are not acquired in a timely manner in the dynamic load area.

[0069] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, 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 flowcharts and / or block diagrams. 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.

[0071] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0073] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional 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.

[0074] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An intelligent student psychological data collection and analysis system with multiple data sources, characterized by: include: Data acquisition delay analysis module, data transmission delay analysis module, signal processing delay analysis module; The data acquisition delay analysis module is used to perform data acquisition delay analysis on the acquisition process of the local preprocessing layer according to the acquired first interference data to obtain a data acquisition delay analysis result, wherein the first interference data includes filtering delay duration, feature extraction delay duration and ring buffer waiting duration, and the data acquisition delay analysis is used to quantify the degree of data response delay of the local preprocessing layer in the process of processing student psychological data; The data transmission delay analysis module is used to determine whether to perform filter parameter optimization based on the data acquisition delay analysis results, and at the same time perform data transmission delay analysis on the collaborative transmission process of the acquired student psychological data in the cloud and the terminal to obtain the data transmission delay analysis results. The filter parameter optimization means adjusting the filter strength and buffer capacity to improve the data acquisition efficiency of the student psychological data in the preprocessing layer. The data transmission delay analysis is used to quantify the collaborative transmission efficiency of the student psychological data in the cloud and terminal transmission process; The signal processing delay analysis module is used to determine whether to perform sampling frequency optimization based on the obtained data transmission delay analysis results, and at the same time, perform signal processing delay analysis on the psychological signal processing process in the dynamic load area based on the obtained second interference data to obtain the signal processing delay analysis results, and determine whether to perform dynamic window optimization based on the obtained signal processing delay analysis results. The sampling frequency optimization means adjusting the sampling frequency amplitude and data compression activation to reduce the delay in the transmission process of student psychological data in the cloud and terminal. The signal processing delay analysis is used to quantify the load balancing of student psychological data in the dynamic load area. The dynamic window optimization means adjusting the back pressure evaluation level to improve the efficiency and real-time performance of psychological signal processing.

2. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 1, characterized in that: The data acquisition delay analysis is performed on the acquisition process of the local preprocessing layer according to the acquired first interference data, and the specific steps include: Obtaining the degree of difference between the filter delay time and the reference filter delay time in the database, and correcting it using the filter delay time correction amount to obtain a filter delay time interference value; Obtaining the degree of difference between the feature extraction delay time and the reference feature extraction delay time in the database, and correcting it using the feature extraction delay time correction amount to obtain a feature extraction delay time interference value; The difference between the obtained ring buffer waiting time and the reference ring buffer waiting time in the database is corrected by the ring buffer waiting time correction amount to obtain the ring buffer waiting time interference value; The obtained filtering delay time interference value, feature extraction delay time interference value and ring buffer waiting time interference value are coupled to obtain a data acquisition delay analysis index, which is used to quantify the degree of interference of the first interference data on the local preprocessing layer acquisition process.

3. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 2, characterized in that: The specific steps of determining whether to perform filter parameter optimization based on the data acquisition delay analysis result include: Compare the acquired data acquisition delay analysis indicators with the data acquisition delay analysis indicators set in the database: If the acquired data acquisition delay analysis index is greater than the data acquisition delay analysis index set in the database, the data acquisition delay analysis result is recorded as unqualified and the filter parameter optimization is performed; If the obtained data acquisition delay analysis index is not greater than the data acquisition delay analysis index set in the database, the data acquisition delay analysis result is recorded as qualified and the psychological signal delay analysis is performed; The filtering parameters include filtering strength and ring buffer capacity.

4. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 3, characterized in that: The specific steps of the filtering parameter optimization are: The obtained data acquisition delay analysis index deviation and feature extraction delay duration deviation are input into the real-time filtering algorithm of the adaptive filter to output the actual reduction of the filtering strength; After the filtering strength is reduced once, it is determined whether the obtained delay analysis indicator deviation reduction is greater than the reduction range set in the database. If so, the filtering strength of the adaptive filter is further reduced. Otherwise, a buffer capacity optimization instruction is sent and the buffer capacity is optimized. If the data acquisition delay analysis index reacquired within the preset filter strength adjustment times is not greater than the data acquisition delay analysis index set in the database, the filter strength optimization is completed, otherwise a filter warning instruction is sent and the preset personnel are prompted to intervene.

5. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 4, characterized in that: The data acquisition delay analysis indicator deviation is used to quantify the degree of difference between the acquired data acquisition delay analysis indicator and the data acquisition delay indicator set in the database; The feature extraction delay time deviation is used to quantify the difference between the acquired feature extraction delay time and the feature extraction delay time set in the database; The specific steps of the buffer capacity optimization are: The obtained parallel processing duration deviation and CPU resource utilization are input into the ring buffer adjustment area to output the actual increase in the ring buffer capacity; The parallel processing duration deviation is used to quantify the difference between the obtained parallel processing duration and the parallel processing duration set in the database; If the data acquisition delay analysis index reacquired within the preset filter strength adjustment times is not greater than the data acquisition delay analysis index set in the database, the buffer capacity optimization is completed and the data delay analysis is performed, otherwise a buffer warning instruction is sent and the preset personnel are prompted to intervene.

6. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 1, characterized in that: The specific steps of determining whether to optimize the sampling frequency based on the acquired data transmission delay analysis result include: If the acquired data transmission delay time is longer than the data transmission delay time set in the database, the data transmission delay analysis result is recorded as unqualified and the sampling frequency is optimized; If the acquired data transmission delay time is less than the data transmission delay time set in the database, the data transmission delay analysis result is recorded as qualified and the signal processing delay analysis is performed; The data transmission delay duration is used to quantify the degree of time delay experienced by student psychological data from the sending end to the receiving end during the transmission process.

7. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 6, characterized in that: The specific steps of the sampling frequency optimization are: Y1, inputs the obtained data transmission delay time deviation and data sampling frequency deviation into the linear regression algorithm to output the actual reduction amplitude of the pressure sampling frequency; Y2, after a sampling frequency reduction determines whether the obtained data transmission delay time deviation reduction is greater than the reduction rate set in the database, if so, continue to reduce the sampling frequency, otherwise send a data compression activation command and execute Y4; Y3, if the data transmission delay time reacquired within the preset sampling frequency adjustment times is not greater than the data transmission delay time set in the database, the sampling frequency optimization is completed, otherwise a sampler warning instruction is sent and a preset person is prompted to intervene; Y4, the specific steps for data compression activation are: Inputting the retrieved data transmission delay time deviation into the symmetric decompression algorithm output data compression activation parameter; If the data transmission delay time reacquired within the preset sampling frequency adjustment times is not greater than the data transmission delay time set in the database, the data compression activation is completed; otherwise, a data compression warning instruction is sent and the preset personnel are prompted to intervene; The data transmission delay duration deviation is used to quantify the degree of difference between the acquired data transmission delay duration and a preset data transmission delay duration in the database.

8. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 1, characterized in that: The second interference data includes the proportion of low-frequency signals, the proportion of noise signals, and the delay duration of communication between nodes; The signal processing delay analysis of the psychological signal processing process in the dynamic load area based on the acquired second interference data specifically includes the following steps: The difference between the low-frequency signal ratio and the reference low-frequency signal ratio in the database is corrected by the low-frequency signal ratio correction amount to obtain the low-frequency signal ratio interference value; The difference between the noise signal ratio and the reference noise signal ratio in the database is corrected by the noise signal ratio correction amount to obtain a noise signal ratio interference value; The difference between the inter-node communication delay time and the reference inter-node communication delay time in the database is corrected by the inter-node communication delay time correction amount to obtain the inter-node communication delay time interference value; The obtained low-frequency signal ratio interference value, noise signal ratio interference value and inter-node communication delay duration interference value are coupled and processed to obtain a signal processing delay analysis index, which is used to quantify the degree of interference of the second interference data on the cloud data processing process.

9. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 8, characterized in that: The specific steps of determining whether to perform dynamic window optimization based on the obtained signal processing delay analysis result include: Compare the obtained signal processing delay analysis indicators with the signal processing delay analysis indicators set in the database: If the obtained signal processing delay analysis index is greater than the signal processing delay analysis index set in the database, the data processing delay analysis result is recorded as unqualified and the dynamic window parameter is adjusted; If the obtained signal processing delay analysis index is not greater than the signal processing delay analysis index set in the database, the data processing delay analysis result is recorded as qualified and a cloud storage instruction is sent; The dynamic window parameter adjustment includes dynamic window adjustment and back pressure assessment level; The back pressure assessment level is used to quantify the degree of obstruction in the processing of the acquired student psychological data.

10. The intelligent student psychological data collection and analysis system with multiple data sources as claimed in claim 9, characterized in that: The specific steps of adjusting the dynamic window parameters are as follows: The obtained signal processing delay analysis index deviation and back pressure assessment level deviation are input into the dynamic window adjustment mechanism to output the adjustment range of the back pressure assessment level; After a back pressure assessment level adjustment, determine whether the reduction in the deviation of the newly acquired signal processing delay analysis indicator is greater than the reduction set in the database. If so, adjust the dynamic window parameters; otherwise, upload the data to the cloud for storage. The dynamic window adjustment means automatically switching the window strategy output window adjustment amplitude of the reacquired signal processing delay analysis indicator through the fluctuation type; If the signal processing delay analysis index re-acquired within the preset dynamic window adjustment times is not greater than the signal processing delay analysis index set in the database, the dynamic window adjustment is completed; otherwise, a dynamic window area warning instruction is sent to remind the preset personnel to intervene; The signal processing delay analysis indicator deviation is used to quantify the difference between the acquired signal processing delay analysis indicator and the signal processing delay analysis indicator preset in the database; The back pressure evaluation level deviation is used to quantify the difference between the acquired back pressure evaluation level and the back pressure evaluation level preset in the database.

Images