German education evaluation and selection system based on big data and data processing method thereof

Abstract

The invention provides a big data-based German education selection system and a data processing method thereof, and relates to the technical field of data synchronization, and the method comprises the steps: setting a selection feature sliding window during German education selection, screening selection interaction information according to the selection feature sliding window, and obtaining a selection behavior track during German education selection; according to the classroom performance information, determining comment and reward characteristics in the teenager education interaction, and according to the comment and reward characteristics and the selection behavior track, determining a selection marginal value of the education selection; performing data stream classification on the living habit data to obtain evaluation attributes in multiple types of teenager education evaluation dimensions, and determining an evaluation contribution degree of education evaluation according to the evaluation attributes; according to the method, the evaluation marginal value of the German education evaluation and the evaluation contribution degree of the German education evaluation are dynamically integrated, and the dynamic evaluation indexes are subjected to multi-terminal synchronization through the big data model, so that the dynamic synchronization of large-scale German education evaluation data can be pre-optimized, and the consistency of multi-terminal instant updating of the dynamic evaluation indexes is improved.

Description

Technical Field

[0001] The present application relates to the field of data synchronization technology, and more specifically, to a moral education evaluation system based on big data and a data processing method thereof. Background Art

[0002] Data synchronization refers to a series of technologies and methods for maintaining data consistency and real-time updates between different systems, devices or platforms. It ensures that data can be synchronized instantly between multiple ports or locations to avoid information errors caused by data inconsistency or delays. Common technologies include: using real-time data stream processing frameworks (such as Apache Kafka, Apache Flink) to ensure instant data synchronization; transferring and integrating data between systems through API interfaces (such as RESTful API, GraphQL); using WebSocket, Server-Sent Events and other technologies to achieve real-time data push from the server to the client; using data replication technology to synchronize data copies between multiple databases or storage systems; using distributed caching systems (such as Redis) to improve data access speed. At the same time, data synchronization technology also includes mechanisms to resolve data conflicts and merging problems to ensure data consistency and integrity during multi-source data synchronization.

[0003] The existing moral education selection data processing based on big data refers to obtaining students' multi-source data, including classroom performance, extracurricular activities and family living habits, through data collection technology (such as sensors, online learning management systems), and then using big data processing platforms (such as Hadoop, Apache Spark) to perform distributed computing and analysis on these large-scale data sets, extract valuable features and indicators, and use machine learning and statistical models (such as regression analysis, cluster analysis) to calculate and predict moral education selection indicators, and then synchronize the moral education selection indicators to each application end. However, in the processing of moral education selection data, due to the diverse data sources involved in moral education selection, there are different data formats and update frequencies, which makes it difficult to maintain data consistency and timeliness during real-time synchronization, which leads to delays in the synchronization of moral education selection data when users access it concurrently. Therefore, how to pre-optimize the dynamic synchronization of large-scale moral education selection data to improve the consistency of dynamic selection indicators in real-time updates on multiple ends is a problem faced by the industry. Summary of the invention

[0004] The present application provides a moral education evaluation system based on big data and a data processing method thereof, which can pre-optimize the dynamic synchronization of large-scale moral education evaluation data to improve the consistency of dynamic evaluation indicators in real-time updates on multiple terminals.

[0005] In the first aspect, the present application provides a method for processing moral education evaluation data based on big data, and the data processing method comprises the following steps: Receive interactive information from the youth moral education selection big data platform; Setting a sliding window of selection characteristics during moral education selection, filtering the selection interaction information according to the sliding window of selection characteristics, and obtaining a selection behavior track during moral education selection; Acquire the classroom performance information of the teenagers from the electronic student ID card, determine the comment and reward characteristics in the moral education interaction of the teenagers according to the classroom performance information, and determine the selection marginal value of the moral education selection according to the comment and reward characteristics and the selection behavior trajectory; Acquire the living habit data of teenagers in home-school collaborative education, classify the living habit data into data streams, obtain the evaluation attributes in multiple categories of youth moral education evaluation dimensions, and determine the evaluation contribution of the moral education evaluation according to the evaluation attributes; The marginal value of the moral education selection and the contribution of the moral education selection are dynamically integrated to obtain dynamic selection indicators for comprehensive moral education selection, and the dynamic selection indicators are synchronized on multiple terminals through a big data model.

[0006] In this embodiment, the selection interaction information of the youth moral education selection big data platform is regularly received in the form of a scheduled task.

[0007] In this embodiment, setting the evaluation feature sliding window during moral education evaluation specifically includes: Obtain the selection index information during moral education selection; Determining the selection priority in the moral education selection according to the selection index information; The selection feature sliding window during moral education selection is set by the selection priority.

[0008] In this embodiment, the selection interaction information is screened according to the selection feature sliding window, and the selection behavior track during the moral education selection is obtained, which specifically includes: Determining data access parameters during moral education selection according to the selection interaction information; Determine the behavioral characteristics of moral education behavior in moral education selection; The data access parameters are mapped onto the behavior characteristics to obtain the evaluation behavior track during the moral education evaluation.

[0009] In this embodiment, the classroom performance information of teenagers is obtained through the moral education evaluation model.

[0010] In this embodiment, determining the comment reward features in the youth moral education interaction according to the classroom performance information specifically includes: Determining the support degree corresponding to the classroom performance according to the classroom performance information; Determine the initial comment value in the interaction of youth moral education; The comment reward characteristics in the youth moral education interaction are determined according to the support degree corresponding to the classroom performance and the initial comment value.

[0011] In this embodiment, life habit data are obtained through feedback provided by parents, students' performance in school, and various smart devices (such as smart watches and health monitoring devices).

[0012] In this embodiment, the living habit data is classified into data streams to obtain multiple types of evaluation attributes in the youth moral education evaluation dimension, specifically including: Determining the selection logic information during the moral education selection according to the living habit data; Extracting data stream samples during selection through the selection logic information; Determine the trend data of participation in each dimension of youth moral education selection; The evaluation trend data is divided through the data stream samples to obtain the evaluation attributes in multiple categories of youth moral education evaluation dimensions.

[0013] In this embodiment, determining the evaluation contribution of the moral education evaluation according to the evaluation attribute specifically includes: Determining the selection quantile of the moral education selection according to the selection attributes; Determine the contribution factors of moral education selection; The evaluation contribution degree of the moral education evaluation is determined according to the evaluation percentile and the evaluation contribution factor.

[0014] In a second aspect, the present application provides a moral education selection system based on big data, which is used to execute a moral education selection data processing method based on big data, and the selection system includes: An information receiving module is used to receive the selection and interaction information of the youth moral education selection big data platform; A data screening module, used to set a sliding window of selection characteristics during moral education selection, and to screen the selection interaction information according to the sliding window of selection characteristics to obtain a selection behavior track during moral education selection; A feature extraction module is used to obtain the classroom performance information of the teenagers from the electronic student card, determine the comment and reward features in the moral education interaction of the teenagers according to the classroom performance information, and determine the selection marginal value of the moral education selection according to the comment and reward features and the selection behavior trajectory; A data classification module is used to obtain the living habit data of teenagers in home-school collaborative education, classify the living habit data into data streams, obtain the evaluation attributes in multiple categories of youth moral education evaluation dimensions, and determine the evaluation contribution of moral education evaluation according to the evaluation attributes; The data synchronization module is used to dynamically integrate the selection marginal value of the moral education selection and the selection contribution degree of the moral education selection, obtain the dynamic selection index during the comprehensive moral education selection, and synchronize the dynamic selection index on multiple terminals through the big data model.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: By receiving the evaluation interaction information from the big data platform for moral education evaluation of young people; setting the evaluation feature sliding window during moral education evaluation, filtering the evaluation interaction information according to the evaluation feature sliding window, and obtaining the evaluation behavior trajectory during moral education evaluation; obtaining the classroom performance information of young people from the electronic student card, determining the comment and reward features in the moral education interaction of young people according to the classroom performance information, and determining the evaluation marginal value of moral education evaluation according to the comment and reward features and the evaluation behavior trajectory; obtaining the living habit data of young people in home-school collaborative education, classifying the living habit data into data streams, obtaining the evaluation attributes in multiple dimensions of moral education evaluation of young people, and determining the evaluation contribution of moral education evaluation according to the evaluation attributes; dynamically integrating the evaluation marginal value and the evaluation contribution of moral education evaluation, obtaining the dynamic evaluation index during the comprehensive moral education evaluation, and synchronizing the dynamic evaluation index on multiple terminals through the big data model.

[0016] It can be seen that in this application, the dynamic synchronization of large-scale moral education selection data can be optimized in advance; among them, by setting the sliding window of the selection feature of moral education selection, the relevant data can be systematically screened and integrated, and the sliding window technology can normalize the data according to the preset features to reduce data noise and inconsistency; the distributed data synchronization technology is applied to perform real-time data stream processing and push to ensure the consistency and accuracy of the data during the multi-terminal synchronization process, and combine the data caching technology and load balancing strategy to improve the system performance and reduce the synchronization delay; by comprehensively considering the classroom performance information and the characteristics of the comment reward, and combining the selection behavior trajectory, the selection marginal value is accurately determined to ensure the accuracy of the selection marginal value, and then affect the rationality of the selection results; through the data stream classification technology and the determination of multi-dimensional selection attributes, the accurate classification and evaluation of life habit data is ensured, and the calculation accuracy of the selection contribution of moral education selection is improved; through the big data model for dynamic integration and multi-terminal synchronization, the dynamic selection indicators are ensured to be updated in real time and consistent, and the response speed of the system and the real-time nature of the data are improved. Finally, the dynamic selection indicators are synchronized on multiple terminals through the big data model.

[0017] To sum up, the technical solution adopted in this application can pre-optimize the dynamic synchronization of large-scale moral education evaluation data to improve the consistency of dynamic evaluation indicators in real-time updates on multiple terminals. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 It is a flow chart of the data processing method of moral education selection based on big data provided by this application; Figure 2 It is a module structure diagram of the moral education evaluation system based on big data provided by this application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The embodiment of the present application provides a moral education selection system based on big data and a data processing method thereof, the core of which is to receive selection interaction information from a big data platform for moral education selection for young people; set a sliding window for selection characteristics during moral education selection, filter the selection interaction information according to the sliding window for selection characteristics, and obtain the selection behavior trajectory during moral education selection; obtain the classroom performance information of young people from an electronic student card, determine the comment and reward characteristics in the moral education interaction of young people according to the classroom performance information, and determine the selection marginal value of moral education selection according to the comment and reward characteristics and the selection behavior trajectory; obtain the living habit data of young people in home-school collaborative education, classify the living habit data into data streams, obtain the selection attributes in multiple categories of moral education selection dimensions for young people, and determine the selection contribution of moral education selection according to the selection attributes; dynamically integrate the selection marginal value of the moral education selection and the selection contribution of the moral education selection to obtain the dynamic selection index during the comprehensive moral education selection, and synchronize the dynamic selection index on multiple terminals through a big data model. The above scheme can be adopted to optimize the dynamic synchronization of large-scale moral education evaluation data in advance, so as to improve the consistency of dynamic evaluation indicators in real-time updates on multiple terminals. Embodiment 1

[0022] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1As shown in FIG. 1 , this figure is an exemplary flow chart of a method for processing moral education evaluation data based on big data according to this embodiment of the present application, and the data processing method includes the following steps: In step S1, the selection interaction information of the youth moral education selection big data platform is received.

[0023] In the specific implementation, first of all, we must ensure the reliability and integrity of the data source. The data source mainly comes from the Youth Moral Education Selection Big Data Platform, which contains the following interactive data: voting information: the voting records of young people for candidates (such as classmates or themselves) in the selection activities, like information: the behavior of expressing approval of the behavior or performance of others, evaluation information: text or rating evaluation of candidates or behaviors, which may come from the young people themselves or the person in charge of the selection (such as teachers) and participation records: records of whether young people have participated in specific selection activities, the frequency and duration of participation, and these data exist in the form of digital records, timestamps, selection content, etc.; then, when young people have any interaction during the selection process (such as voting, liking, etc.), this information should be immediately transmitted to the system, such as real-time update of the selection status; finally, regularly send data requests to the selection platform to obtain all the selection interaction information in the past period of time. This can be regularly executed through scheduled tasks. For example, every morning the system will automatically request all the data of the previous day from the selection platform, that is, the selection interaction information of the Youth Moral Education Selection Big Data Platform can be regularly received through scheduled tasks, which will not be repeated here.

[0024] It should be noted that in this application, selection interaction information refers to all interactive behavior data generated by young people during the moral education selection process, including voting, liking, evaluation, etc. This information reflects the participation and specific performance of young people in the selection.

[0025] In step S2, a sliding window of evaluation characteristics during moral education evaluation is set, and the evaluation interaction information is screened according to the sliding window of evaluation characteristics to obtain the evaluation behavior track during moral education evaluation.

[0026] In this embodiment, setting the evaluation feature sliding window during moral education evaluation can be achieved by using the following steps: Obtain the selection index information during moral education selection; Determining the selection priority in the moral education selection according to the selection index information; The selection feature sliding window during moral education selection is set by the selection priority.

[0027] In the specific implementation, firstly, by setting the data reading program, the selection index data of the moral education selection is read from the storage unit of the big data moral education selection system, and the selection index data is used as the selection index information. It will not be repeated here. The selection index information of the moral education selection includes the number of participants and the interaction frequency, etc. For example, the system obtains the latest selection index data every hour or every day to ensure the timeliness of the data; then, the system can assign weights to different selection dimensions based on historical data or preset rules. For example, the weight of classroom performance may be higher than that of extracurricular activities, because classroom performance is considered to more directly reflect the students' moral education level. According to the index information obtained in real time or periodically, the system will dynamically adjust the priority of each dimension or feature. For example, if the number of students participating in the interaction increases significantly within a certain period of time, The priority of the "participation" dimension in the selection feature may be increased, that is, the selection priority in the moral education selection is obtained; finally, the selection feature sliding window is set according to the selection priority, and the size of the sliding window will be different. For the selection dimension with high weight, the sliding window is shorter, so as to monitor the changes of these important dimensions in real time. For example, if "class performance" is given a higher priority, the system will set a short time window (for example, the performance in the last 7 days) to monitor the real-time changes of students. For dimensions with lower weights, the window may be longer (such as 30 days or longer) to observe its long-term trend, and the sliding window is dynamically adjusted to cope with changes in the moral education selection. For example, after the selection activity started, the system initially set a sliding window of 30 days to evaluate the overall performance of students within one month. However, as the selection progressed, it was found that the importance of classroom performance increased significantly, so the system shortened the sliding window of classroom performance to 10 days to ensure that this dimension can reflect the changes in students' performance in a timely manner.

[0028] It should be noted that in this application, the evaluation index information refers to the key quantifiable data or indicators related to the moral education evaluation. These index information can reflect the importance or influence in the evaluation process, and they are usually used for screening or sorting in the evaluation process; the evaluation priority is an indicator used to determine the importance of different dimensions or characteristics in the evaluation process; the evaluation feature sliding window refers to a continuous time period set in the moral education evaluation process based on the timeliness and priority of the evaluation data, which is used to dynamically screen and analyze the evaluation characteristics and behaviors within a specific time range.

[0029] In this embodiment, the selection interaction information is screened according to the selection feature sliding window to obtain the selection behavior trajectory during the moral education selection, which can be achieved by the following steps: Determining data access parameters during moral education selection according to the selection interaction information; Determine the behavioral characteristics of moral education behavior in moral education selection; The data access parameters are mapped onto the behavior characteristics to obtain the evaluation behavior track during the moral education evaluation.

[0030] In the specific implementation, first, based on the sliding window, the time range of the selection data is set. For example, the system may need to obtain the selection interaction information within the past 7 days or 30 days to ensure the timeliness of the data, and then extract specific types of interaction data according to the nature of the selection activity, such as filtering out only voting data or only filtering out evaluation data, and use the interaction data as a data access parameter; then, the quantitative data on classroom performance, extracurricular activities, social responsibility, and personal moral performance collected in the moral education selection system are used as the behavioral characteristics of moral education behavior in the moral education selection. In other embodiments, other methods can also be used to determine the behavioral characteristics of moral education behavior in the moral education selection. There is no limitation on this; finally, the selection interaction information within the corresponding time period is filtered out according to the set time range (sliding window), for example, the student's voting and liking behavior data in the past 30 days, and then these interaction data are classified and categorized according to different behavioral characteristics (such as classroom performance, extracurricular activities, etc.). For example, a liking behavior is mapped to the behavioral characteristic of "cooperative spirit", and the voting behavior is mapped to the "classroom participation" characteristic; finally, all the mapped behavioral data are combined to form the selection behavior trajectory during the moral education selection, among which the combination process can use Bayesian data fusion, maximum likelihood estimation, etc., which are not limited here.

[0031] It should be noted that in this application, data access parameters refer to the parameters set by the system for screening, classifying and extracting data in the processing of interactive selection information, including time range, behavior type, individual identification, etc.; behavioral characteristics refer to the classification of specific behaviors exhibited by adolescents in the process of moral education selection, such as classroom performance, extracurricular activities performance, social responsibility, etc. This feature is used to measure the students' moral education level; the selection behavior trajectory refers to a dynamic behavior performance path generated by mapping the selection interaction information and behavioral characteristics, which reflects the students' behavioral changes and trends over a period of time.

[0032] In step S3, the classroom performance information of the teenagers is obtained from the electronic student card, and the comment and reward characteristics in the moral education interaction of the teenagers are determined according to the classroom performance information. The selection marginal value of the moral education selection is determined according to the comment and reward characteristics and the selection behavior trajectory.

[0033] In specific implementation, obtaining teenagers' classroom performance information from electronic student cards can be achieved in the following ways, namely: electronic student cards usually have built-in sensing or positioning devices that can record students' attendance, classroom participation and other behaviors. First, the data interface of the electronic student card can be used to collect students' behavioral data on campus in real time, such as the time of entering and leaving the classroom, the number of times they answered questions, the frequency of participating in discussions, etc.; then, the collected data is uploaded to the school's moral education evaluation big data platform. The platform classifies and processes the data according to preset rules, and extracts information related to classroom performance, such as attendance rate, participation rate, etc. Then, by cross-comparing with other subject grades, teacher evaluations and other data, the student's classroom performance record is improved. Finally, the improved student classroom performance record is integrated into the moral education evaluation model, and the classroom performance information of teenagers can be obtained through the moral education evaluation model, which is not limited here.

[0034] It should be noted that in this application, classroom performance information refers to various data and information related to learning and behavior demonstrated by students in the classroom environment. This information usually includes students' attendance rate, classroom participation (such as answering questions, frequency of participating in discussions), concentration, cooperation ability, discipline compliance, etc.

[0035] In this embodiment, determining the comment reward feature in the youth moral education interaction according to the classroom performance information can be achieved by using the following steps: Determining the support degree corresponding to the classroom performance according to the classroom performance information; Determine the initial comment value in the interaction of youth moral education; The comment reward characteristics in the youth moral education interaction are determined according to the support degree corresponding to the classroom performance and the initial comment value.

[0036] In the specific implementation, first, a scoring system is set up, and students with high attendance rates and active participation in discussions receive higher support. A weighting algorithm can be used to weight different classroom performance data (such as the number of answers, participation in discussions), and then each student's classroom performance data is converted into support according to the set standards. For example, if a student has frequently participated in classroom discussions in the past month, his or her support will be higher; conversely, students with lower participation will have lower support, that is, the support corresponding to the classroom performance will be obtained; then, according to the selection criteria of the school or organization, a range of initial comment values ​​is set. For example, a basic score (such as 10 points) can be set, and then adjusted according to the student's performance, wherein the initial comment value can come from the teacher's score, the previous moral education selection record, or the system preset benchmark value, and then, according to the set criteria, an initial comment value is assigned to each student's moral education interaction, that is, the initial comment value in the youth moral education interaction is obtained. In other embodiments , other methods can also be used to determine the initial comment value in the moral education interaction of young people, which is not limited here; finally, the support of each student is integrated with its initial comment value. For example, if a student has a high support (indicating that his or her classroom performance is excellent), then his or her comment reward feature will be higher than the initial comment value. Then, the algorithm is used to combine the support with the initial comment value. The final comment reward value can be adjusted by weighted average, multiplication, etc. For example, the following formula is used: Final comment reward = initial comment value * (1 + support / maximum support). The value of the final comment reward is used as the comment reward feature in the moral education interaction of young people. For example, if a student's initial comment value is 10 points and his or her classroom performance support is 80% (out of 100%), then the final comment reward feature is 1.8 times the initial comment value, that is, 18 points. That is, students with high support can get higher comment rewards, thereby encouraging them to be more active in moral education activities. I will not go into details here.

[0037] It should be noted that in this application, support is an indicator to measure students' performance in class, reflecting their participation and enthusiasm; the initial comment value represents the basic comment score given to a certain behavior or performance in moral education interaction; the comment reward feature refers to the indicator for rewarding students in moral education selection, which is used to characterize students' overall moral education performance.

[0038] In this embodiment, the following steps can be used to determine the selection margin value of the moral education selection according to the comment reward characteristics and the selection behavior trajectory: Determine the first selection marginal label of the moral education selection according to the review reward characteristics; Determine the second marginal label of the moral education selection according to the selection behavior trajectory; The selection marginal value of the moral education selection is determined according to the first selection marginal label and the second selection marginal label.

[0039] In the specific implementation, first, the first selection marginal label is set according to the scoring criteria. For example, the comment reward feature can be divided into multiple levels, such as "excellent", "good", "medium", "to be improved", etc., and each level corresponds to a marginal label, and then the student's comment reward feature value is classified into the corresponding marginal label. For example, if a student's comment reward feature value is higher than 90 points, it is marked as "excellent"; if it is between 60 and 80 points, it is marked as "good", that is, the first selection marginal label of moral education selection is obtained; then, the standard of the second selection marginal label of the behavior trajectory is set. For example, the behavior trajectory can be divided into categories such as "stable", "rising", and "declining", and each category corresponds to a marginal label, and then according to the analysis results of the selection behavior trajectory, it is classified into the second selection marginal label. For example For example, if a student's behavior trajectory shows continuous positive behavior, it may be labeled as "rising"; if the performance remains stable, it is labeled as "stable", that is, the second selection marginal label is obtained; finally, the first selection marginal label and the second selection marginal label are comprehensively analyzed. For example, if the first label is "excellent" and the second label is "rising", it may indicate that the student has outstanding performance in the moral education selection. Then, based on the integrated labels, the final selection marginal value is calculated using preset rules or algorithms. For example, different scores can be assigned to different marginal labels, and then weighted averaged to obtain the final selection marginal value. For example: the first selection marginal label: "excellent" (score value 90), the second selection marginal label: "rising" (score value 80), then the selection marginal value = (90+80) / 2=85, which will not be repeated here.

[0040] It should be noted that in this application, the first selection marginal label is an indicator used to evaluate the performance level of students in moral education interaction; the second selection marginal label is used to evaluate the behavioral performance trend of students in moral education selection, showing the behavioral changes of students over a certain period of time; the selection marginal value refers to the data used to determine the student's selection qualifications or grades in the moral education selection process.

[0041] In step S4, the living habit data of teenagers in home-school collaborative education are obtained, and the data stream of the living habit data is classified to obtain the selection attributes in multiple categories of teenagers' moral education selection dimensions, and the selection contribution of the moral education selection is determined according to the selection attributes.

[0042] In specific implementation, the following methods can be used to obtain the living habit data of adolescents in home-school collaborative education, namely: first, the living habit data can be obtained through the feedback provided by parents, the performance of students in school, and various smart devices (such as smart watches, health monitoring devices). Specifically, parents can submit data about students' daily routines, eating habits, homework completion, etc. through the home-school communication platform or special applications, and the school can obtain other behavioral data of students through classroom performance, extracurricular activities participation, etc. In addition, smart devices can provide physiological data about students' exercise volume, sleep quality, etc.; then, after the data is collected, the data from different sources need to be transmitted to the central database through the data interface or API. In this process, the data format may be different, so data conversion and cleaning are required to ensure the uniformity and consistency of the data. For example, the data filled in by parents may need to be matched and integrated with the behavior records in the school system; finally, the integrated living habit data is processed and analyzed using data analysis tools. For example, statistical analysis can be used to understand whether the students' sleep time is regular, whether the daily routine is stable, and whether there are bad living habits, that is, to obtain the living habit data of adolescents in home-school collaborative education.

[0043] It should be noted that in this application, lifestyle data refers to information that reflects an individual's daily life behaviors and patterns, including but not limited to work and rest time, eating habits, exercise, sleep quality, study habits, and homework completion status.

[0044] In this embodiment, the following steps can be used to classify the data stream of the living habit data and obtain the selection attributes in multiple categories of youth moral education selection dimensions: Determining the selection logic information during the moral education selection according to the living habit data; Extracting data stream samples during selection through the selection logic information; Determine the trend data of participation in each dimension of youth moral education selection; The evaluation trend data is divided through the data stream samples to obtain the evaluation attributes in multiple categories of youth moral education evaluation dimensions.

[0045] In specific implementation, first, based on the collected data, the system can set logical rules to identify and classify different living habit patterns, and use the identified and classified living habit patterns as selection logic information, such as regular work and rest, good diet, etc. For example, if the data shows that the student goes to bed on time every night and gets up on time in the morning, the selection logic information may mark this behavior as "regular work and rest"; then, use the selection logic information to extract data samples that meet specific rules from the overall living habit data. For example, extract all student data with good regular work and rest as a sample set, and use the sample set as the data stream sample for selection. In other embodiments, other methods can also be used to determine the data stream sample for selection, which is not limited here. Then, the extracted data samples are organized into structured data. For example, the data samples can be organized according to dimensions such as student ID, work and rest time, and amount of exercise. For example, all student information with regular work and rest is extracted from the living habit data to form a data set containing the work and rest time and related behaviors of these students; then, trend analysis is performed on the extracted data samples to determine the evaluation trend in each selection dimension, and the evaluation trend is used as the youth The trend data of the participants in the dimension of youth moral education selection, for example, analyze the impact of work and rest rules on academic performance, or the impact of exercise volume on social skills, and then define different dimensions of moral education selection based on the trend analysis results. For example, "work and rest rules" can be defined as one selection dimension, and "exercise volume" as another dimension. If the analysis finds that students with good work and rest rules perform well in learning, then "work and rest rules" can be established as an important dimension in moral education selection; finally, according to the data stream samples and trend analysis, students are classified into different selection attributes. For example, students with regular work and rest are marked as "good work and rest rules", and students with a large amount of exercise are marked as "active exercise". Then the standards and ranges of each selection attribute are set. For example, "good work and rest rules" include students who sleep no less than 8 hours a night, and "active exercise" includes students who exercise more than 3 hours a week. By analyzing the data stream samples, all students with good work and rest rules are marked as "good work and rest rules", and students with a large amount of exercise are marked as "active exercise". Finally, selection attributes in multiple selection dimensions are formed, such as "regular work and rest rules" and "active exercise", which are not limited here.

[0046] It should be noted that in this application, the evaluation logic information is the rules and standards formulated based on life habit data, which are used to guide data classification and analysis; data stream sample refers to a representative data subset extracted from a continuous data stream, which is used for specific analysis, processing or testing; evaluation trend data refers to the changing trend of student behavior or performance obtained through time series analysis, pattern recognition, etc. of student behavior or performance data during the moral education selection process. These data reflect the dynamic changes of students in different evaluation dimensions (such as work and rest habits, learning attitudes, social interactions, etc.); evaluation attributes refer to the specific characteristics or indicators extracted from the data stream samples according to specific selection dimensions or standards during the moral education selection process, which are used to describe and evaluate students' performance.

[0047] In this embodiment, determining the evaluation contribution of the moral education evaluation according to the evaluation attributes can be achieved by using the following steps: Determining the selection quantile of the moral education selection according to the selection attributes; Determine the contribution factors of moral education selection; The evaluation contribution degree of the moral education evaluation is determined according to the evaluation percentile and the evaluation contribution factor.

[0048] In the specific implementation, first, organize the student data according to the selection attributes (such as "regular work and rest", "active participation", etc.), summarize and sort the selection attribute values ​​of all students, and then calculate the quantiles according to the distribution of the selection attribute values. For example, divide all students' work and rest attribute values ​​into four equal parts, calculate each quantile (such as 25%, 50%, 75% quantiles) to determine the relative position of the students on the attribute. Specifically, statistical methods (such as the quartile method) can be used to determine these quantiles. For example, the students' work and rest attribute values ​​range from 50 to 100, and the 25th quantile is calculated to be 65, the 50th quantile is 75, and the 75th quantile is 85. These quantiles are used to identify the performance range of students in the work and rest attribute; then, according to different selection attributes and their impact on moral education selection, set the corresponding selection contribution factors. For example, work and rest may have a greater impact, so the contribution factor is higher; while the contribution factor of activity participation may be lower, and assign a value to each selection attribute. A contribution factor. These factors can be determined based on historical data, expert opinions or statistical analysis. The contribution factor can be a fixed value or dynamically adjusted through an algorithm. For example, for "work and rest rules", the contribution factor is set to 1.5; for "activity participation", the contribution factor is set to 1.0, which is not limited here; finally, the student's selection contribution in each selection attribute is calculated. Generally, this process includes multiplying the selection attribute value with the corresponding contribution factor to obtain a weighted score, and calculating the final selection contribution through an algorithm (such as weighted average). For example, the work and rest rule attribute value of student A is at the 50th percentile (75), and the contribution factor is 1.5. Therefore, the student's contribution to work and rest rules is 75*1.5=112.5, and the activity participation attribute value of student A is at the 25th percentile (60), and the contribution factor is 1.0. Therefore, the student's contribution to activity participation is 60*1.0=60, and the selection contribution is = (112.5+60) / 2=86.25, which will not be repeated here.

[0049] It should be noted that in this application, the evaluation percentile refers to the relative position or percentage point used to divide the data set during the moral education evaluation process, describing the performance level of a certain percentage of students in the data set in the evaluation attribute; the evaluation contribution factor refers to the weight coefficient set in the moral education evaluation process to quantify and adjust the influence of different evaluation attributes on the overall contribution of students. This factor is used to adjust the score of each evaluation attribute to ensure that the contribution of each attribute to the overall evaluation result reflects its actual influence; the evaluation contribution degree refers to an indicator to measure the comprehensive performance level of students in each evaluation dimension during the moral education selection process.

[0050] In step S5, the marginal value of the moral education selection and the contribution of the moral education selection are dynamically integrated to obtain dynamic selection indicators for comprehensive moral education selection, and the dynamic selection indicators are synchronized on multiple terminals through a big data model.

[0051] In this embodiment, the selection marginal value of the moral education selection and the selection contribution degree of the moral education selection are dynamically integrated to obtain the dynamic selection index for the comprehensive moral education selection, which can be achieved by the following steps: Determining the loss index during the selection according to the selection margin value of the moral education selection; Determine the integration weight during the selection process according to the selection contribution of the moral education selection process; By combining the loss index and the fusion weight, a dynamic selection index for comprehensive moral education selection is obtained.

[0052] In specific implementation, first, the loss index during selection can be determined by comparing each student's selection score with the marginal value. The loss index can be the difference between the marginal value and the actual score, or the loss can be quantified based on the ratio of reaching the standard to not reaching the standard. For example, the marginal value of moral education selection is 80, and a student's score is 75. The loss index can be calculated as 80-75=5, indicating that the student has a potential loss of 5 points in this dimension. There is no limitation here. Then, according to the distribution of selection contribution, the fusion weight of each selection dimension is set. These weights reflect the contribution of different attributes to the final selection results. Usually, the weight can be determined based on the contribution factor of each selection attribute, historical data analysis or expert evaluation. For example, the selection contribution of "work and rest rules" is relatively high, and the fusion weight of this dimension is set to 0.6. , and the weight of "activity participation" is 0.4, indicating that "work and rest rules" have a greater impact on the dynamic selection index, which will not be repeated here; finally, according to the loss index and the fusion weight, the dynamic selection index is calculated by weighted average or other merging methods. The specific process includes combining the loss index and the fusion weight to obtain the comprehensive score of each student in each dimension, and integrating the calculation results of all selection dimensions to form the student's dynamic selection index, which reflects the student's comprehensive performance in the moral education selection. For example, the student's loss index in the "work and rest rules" dimension is 5, the fusion weight is 0.6, and the loss index in the "activity participation" dimension is 3, and the fusion weight is 0.4. Then the dynamic selection index = (5*0.6) + (3*0.4) = 3.0 + 1.2 = 4.2, which will not be repeated here.

[0053] It should be noted that, in this application, the loss index is an indicator used to quantify the potential losses or adverse effects caused by failure to reach the marginal value of the selection, so as to reflect the degree of non-compliance; the fusion weight is a coefficient used to adjust the relative importance and influence of the contribution of the selection attribute in the final selection index, to ensure that the contribution of each attribute to the comprehensive selection result is accurately reflected; the dynamic selection index refers to the measurement of the overall performance of students in the moral education selection process, reflecting their comprehensive performance in multiple dimensions and the degree of compliance with the selection criteria.

[0054] In specific implementation, the dynamic selection indicators can be synchronized on multiple terminals through a big data model in the following manner: first, a comprehensive data model is constructed to process the dynamic selection indicators. The model needs to include data elements such as various selection dimensions, loss indicators, contribution, fusion weights, and algorithms and logic for calculating these elements. The data model should be able to support real-time data input, processing, and output to ensure the accuracy and timeliness of the dynamic selection indicators; then, various data sources (such as students' classroom performance, living habits data, etc.) are integrated into the data model, and the ETL (extraction, transformation, loading) process is used to process the original data into the format required by the model to ensure the consistency and accuracy of the data; then, big data technologies (such as stream processing frameworks Kafka, Apache Flink, etc.) to process real-time data streams. The calculation of dynamic selection indicators should be updated synchronously when the data is generated to ensure that the selection results displayed on all ports and devices are the latest; finally, use data synchronization technology (such as API interface, WebSocket, etc.) to push the dynamic selection indicators to various terminal devices in real time, including school systems, parent-side applications, student-side applications, etc., to ensure that all user ends can obtain the latest selection information in real time. For example, push the dynamic selection indicators to the school management system and parent applications through the API interface, and use WebSocket technology to achieve real-time updates, so that parents and school administrators can immediately see the latest selection results. The user interface designed for each user end (such as school management system, parent and student applications) can also display detailed information and trends of dynamic selection indicators. The interface should support charts, reports and notification functions to help better understand and analyze the selection results, which will not be repeated here.

[0055] It can be seen that in this application, the dynamic synchronization of large-scale moral education selection data can be optimized in advance; among them, by setting the sliding window of the selection feature of moral education selection, the relevant data can be systematically screened and integrated, and the sliding window technology can normalize the data according to the preset features to reduce data noise and inconsistency; the distributed data synchronization technology is applied to perform real-time data stream processing and push to ensure the consistency and accuracy of the data during the multi-terminal synchronization process, and combine the data caching technology and load balancing strategy to improve the system performance and reduce the synchronization delay; by comprehensively considering the classroom performance information and the characteristics of the comment reward, and combining the selection behavior trajectory, the selection marginal value is accurately determined to ensure the accuracy of the selection marginal value, and then affect the rationality of the selection results; through the data stream classification technology and the determination of multi-dimensional selection attributes, the accurate classification and evaluation of life habit data is ensured, and the calculation accuracy of the selection contribution of moral education selection is improved; through the big data model for dynamic integration and multi-terminal synchronization, the dynamic selection indicators are ensured to be updated in real time and consistent, and the response speed of the system and the real-time nature of the data are improved. Finally, the dynamic selection indicators are synchronized on multiple terminals through the big data model. To sum up, the technical solution adopted in this application can pre-optimize the dynamic synchronization of large-scale moral education evaluation data to improve the consistency of dynamic evaluation indicators in real-time updates on multiple terminals. Embodiment 2

[0056] This application provides a moral education evaluation system based on big data, referring to Figure 2 As shown, this figure is a schematic diagram of a moral education selection system based on big data according to this embodiment of the present application, and the selection system includes: The information receiving module 100 is used to receive the selection interaction information of the youth moral education selection big data platform; The data screening module 200 is used to set a sliding window of selection characteristics during moral education selection, and screen the selection interaction information according to the sliding window of selection characteristics to obtain the selection behavior track during moral education selection; The feature extraction module 300 is used to obtain the classroom performance information of the teenagers from the electronic student card, determine the comment and reward features in the moral education interaction of the teenagers according to the classroom performance information, and determine the selection marginal value of the moral education selection according to the comment and reward features and the selection behavior trajectory; The data classification module 400 is used to obtain the living habit data of teenagers in the home-school collaborative education, classify the living habit data into data streams, obtain the evaluation attributes in the multiple categories of teenagers' moral education evaluation dimensions, and determine the evaluation contribution of the moral education evaluation according to the evaluation attributes; The data synchronization module 500 is used to dynamically integrate the evaluation marginal value of the moral education evaluation and the evaluation contribution of the moral education evaluation to obtain dynamic evaluation indicators during the comprehensive moral education evaluation, and synchronize the dynamic evaluation indicators on multiple terminals through a big data model.

[0057] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0058] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0059] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A method for processing moral education evaluation data based on big data, characterized in that: The data processing method comprises the following steps: Receive interactive information from the youth moral education selection big data platform; Setting a sliding window of selection characteristics during moral education selection, filtering the selection interaction information according to the sliding window of selection characteristics, and obtaining a selection behavior track during moral education selection; Acquire the classroom performance information of the teenagers from the electronic student ID card, determine the comment and reward characteristics in the moral education interaction of the teenagers according to the classroom performance information, and determine the selection marginal value of the moral education selection according to the comment and reward characteristics and the selection behavior trajectory; Acquire the life habit data of teenagers in home-school collaborative education, classify the life habit data into data streams, obtain the evaluation attributes in multiple categories of youth moral education evaluation dimensions, and determine the evaluation contribution of moral education evaluation according to the evaluation attributes; The marginal value of the moral education selection and the contribution of the moral education selection are dynamically integrated to obtain dynamic selection indicators for comprehensive moral education selection, and the dynamic selection indicators are synchronized on multiple terminals through a big data model.

2. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: Regularly receive interactive information on selection from the Youth Moral Education Selection Big Data Platform through scheduled tasks.

3. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: The sliding window of selection characteristics for setting moral education selection specifically includes: Obtain the selection index information during moral education selection; Determining the selection priority in the moral education selection according to the selection index information; The selection feature sliding window during moral education selection is set by the selection priority.

4. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: The selection interactive information is screened according to the selection feature sliding window to obtain the selection behavior trajectory during the moral education selection, which specifically includes: Determining data access parameters during moral education selection according to the selection interaction information; Determine the behavioral characteristics of moral education behavior in moral education selection; The data access parameters are mapped onto the behavior characteristics to obtain the evaluation behavior track during the moral education evaluation.

5. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: Obtaining information on adolescents’ classroom performance through a moral education rating model.

6. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: Determining the comment and reward features in the youth moral education interaction based on the classroom performance information specifically includes: Determining the support degree corresponding to the classroom performance according to the classroom performance information; Determine the initial comment value in the interaction of youth moral education; The comment reward characteristics in the youth moral education interaction are determined according to the support degree corresponding to the classroom performance and the initial comment value.

7. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: Lifestyle habit data is obtained through feedback provided by parents, students’ performance in school, and various smart devices (such as smart watches and health monitoring devices).

8. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: The data stream of the living habit data is classified to obtain multiple types of evaluation attributes in the youth moral education evaluation dimension, including: Determining the selection logic information during the moral education selection according to the living habit data; Extracting data stream samples during selection through the selection logic information; Determine the trend data of participation in each dimension of youth moral education selection; The evaluation trend data is divided through the data stream samples to obtain the evaluation attributes in multiple categories of youth moral education evaluation dimensions.

9. A method for processing moral education evaluation data based on big data as claimed in claim 1, characterized in that: The selection contribution of moral education selection is determined according to the selection attributes, specifically including: Determining the selection quantile of the moral education selection according to the selection attributes; Determine the contribution factors of moral education selection; The evaluation contribution degree of the moral education evaluation is determined according to the evaluation percentile and the evaluation contribution factor.

10. A moral education evaluation system based on big data, used to execute a moral education evaluation data processing method based on big data as claimed in any one of claims 1 to 9, characterized in that: The selection system includes: An information receiving module is used to receive the selection and interaction information of the youth moral education selection big data platform; A data screening module, used to set a sliding window of selection characteristics during moral education selection, and screen the selection interaction information according to the sliding window of selection characteristics to obtain the selection behavior track during moral education selection; A feature extraction module is used to obtain the classroom performance information of the teenagers from the electronic student card, determine the comment and reward features in the moral education interaction of the teenagers according to the classroom performance information, and determine the selection marginal value of the moral education selection according to the comment and reward features and the selection behavior trajectory; A data classification module is used to obtain the living habit data of teenagers in home-school collaborative education, classify the living habit data into data streams, obtain the evaluation attributes in multiple categories of youth moral education evaluation dimensions, and determine the evaluation contribution of moral education evaluation according to the evaluation attributes; The data synchronization module is used to dynamically integrate the selection marginal value and the selection contribution degree of the moral education selection to obtain the dynamic selection index during the comprehensive moral education selection, and synchronize the dynamic selection index on multiple terminals through a big data model.

Images