CN117036126A - College student comprehensive quality management system and method based on data analysis - Google Patents

Abstract

A college student comprehensive quality management system and method based on data analysis acquire educational administration system data, library system data, campus card system data and community system data of college student objects to be evaluated; performing joint analysis on the educational administration system data, the library system data, the campus card system data and the community system data to obtain a multi-dimensional semantic association feature vector of a student object; and determining the comprehensive quality estimation value of the college student object to be evaluated based on the multi-dimensional semantic association feature vector of the student object. Thus, the comprehensive quality estimated value of the college students can be intelligently calculated, and deep insight and intelligent decision making are provided for college education management.

Description

Comprehensive quality management system and method for college students based on data analysis

Technical field

This application relates to the field of intelligent management technology, and more specifically, to a comprehensive quality management system and method for college students based on data analysis.

Background technique

With the popularization and development of higher education, the comprehensive quality of college students has become one of the important indicators of educational evaluation. The comprehensive quality of college students not only includes academic performance, but also includes reading habits, lifestyle, social skills and other aspects.

However, the traditional comprehensive quality evaluation methods of college students usually only rely on subjective questionnaires or a single data source, which lacks objectivity and comprehensiveness and cannot truly reflect the multi-dimensional characteristics and potential value of college students. Therefore, we look forward to an optimized comprehensive quality management plan for college students.

Contents of the invention

In order to solve the above technical problems, this application is proposed. Embodiments of the present application provide a comprehensive quality management system and method for college students based on data analysis, which obtains the academic affairs system data, library system data, campus card system data and community system data of the college students to be evaluated; The system data, the library system data, the campus card system data and the club system data are jointly analyzed to obtain the multi-dimensional semantic association feature vector of the student object; and, based on the multi-dimensional semantic association feature vector of the student object, Determine the estimated comprehensive quality of the college student to be evaluated. In this way, the estimated comprehensive quality of college students can be calculated intelligently, providing profound insights and intelligent decision-making for university education management.

The first aspect provides a comprehensive quality management method for college students based on data analysis, which includes:

Obtain the academic affairs system data, library system data, campus card system data and club system data of the college students to be evaluated;

Conduct a joint analysis on the academic affairs system data, the library system data, the campus card system data and the club system data to obtain a multi-dimensional semantic association feature vector of student objects; and

Based on the multi-dimensional semantic association feature vector of the student object, the estimated comprehensive quality of the college student object to be evaluated is determined.

In the second aspect, a comprehensive quality management system for college students based on data analysis is provided, which includes:

The data acquisition module is used to obtain the academic affairs system data, library system data, campus card system data and community system data of the college students to be evaluated;

A joint analysis module for jointly analyzing the academic affairs system data, the library system data, the campus card system data and the club system data to obtain multi-dimensional semantic association feature vectors of student objects; and

The comprehensive quality estimation value determination module is used to determine the comprehensive quality estimation value of the college student object to be evaluated based on the multi-dimensional semantic association feature vector of the student object.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some of the drawings of the present application. Embodiments, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without exerting creative efforts.

Figure 1 is a flow chart of a comprehensive quality management method for college students based on data analysis according to an embodiment of the present application.

Figure 2 is a schematic structural diagram of a comprehensive quality management method for college students based on data analysis according to an embodiment of the present application.

Figure 3 is a block diagram of a comprehensive quality management system for college students based on data analysis according to an embodiment of the present application.

Figure 4 is a schematic diagram of a scenario of a comprehensive quality management method for college students based on data analysis according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

Unless otherwise stated, all technical and scientific terms used in the embodiments of this application have the same meanings as commonly understood by those skilled in the technical field of this application. The terminology used in this application is for the purpose of describing specific embodiments only and is not intended to limit the scope of this application.

In the description of the embodiments of this application, it should be noted that, unless otherwise stated and limited, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection, or it can be an internal connection between two elements, or it can be a direct connection. , or can be indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

It should be noted that the terms "first\second\third" involved in the embodiments of this application are only used to distinguish similar objects and do not represent a specific ordering of objects. It is understandable that "first\second\ Thirdly, the specific order or sequence may be interchanged where permitted. It is to be understood that the "first\second\third" distinction may be interchanged under appropriate circumstances so that the embodiments of the present application described herein may be practiced in sequences other than those illustrated or described herein.

The comprehensive quality of college students refers to the comprehensive abilities and qualities of college students in terms of learning, thinking, interpersonal communication, innovation ability, social responsibility, etc. It not only includes the mastery of subject knowledge and the improvement of academic abilities, but also includes a wide range of personal qualities and social adaptability .

The following are several important aspects of the comprehensive quality of college students:

Academic ability: College students should have solid subject knowledge and academic research capabilities, be able to understand and master the basic theoretical and practical skills of their major, and have critical thinking and problem-solving abilities.

Comprehensive literacy: College students need to cultivate a wide range of knowledge and cultural literacy, including basic knowledge and understanding abilities in humanities, social sciences, natural sciences and other fields, and have interdisciplinary comprehensive thinking and comprehensive analysis capabilities.

Innovation ability: College students should have creative thinking and innovation ability, be able to think independently, propose new ideas and solve problems, and have innovative awareness and practical ability.

Social skills: College students need to have good interpersonal and cooperation skills, be able to effectively communicate, collaborate and resolve conflicts with others, and have teamwork and leadership skills.

Practical ability: College students should have practical ability, be able to apply the knowledge they have learned to solve practical problems, and have the ability to practice operations and experimental design.

Humanistic care and social responsibility: College students should have the qualities of caring for others, respecting diversity and having a sense of social responsibility, and be able to actively participate in social welfare activities, pay attention to social problems and propose solutions.

The comprehensive quality of college students is a multi-dimensional concept that requires comprehensive consideration of academic ability, comprehensive literacy, innovative ability, social ability, practical ability, humanistic care and social responsibility. The cultivation of these qualities is not only the goal of university education, but also It is also an important part of the overall personal development of college students.

Traditional comprehensive quality evaluation methods for college students usually rely on subjective questionnaires or a single data source, lacking objectivity and comprehensiveness. They include:

Subjective questionnaire survey: By issuing questionnaires to students, teachers or other relevant personnel, we collect their subjective evaluations and opinions on the comprehensive quality of college students. This method is easily affected by subjective factors, and the evaluation results may have subjective bias.

Student self-evaluation: Students are required to evaluate and reflect on their overall qualities. This method can understand students' perceptions of their own abilities, but there may be a tendency to self-exaggerate or underestimate.

Academic performance evaluation: Mainly based on students' performance in academic subjects to evaluate their overall quality. This method only focuses on academic performance and ignores other important dimensions, such as social skills, practical abilities, etc.

Award evaluation: Evaluating a student’s overall quality based on the awards, honors or competition results they have received. This method focuses on the student’s performance in a specific field and cannot fully reflect their overall quality.

Individual interviews and interviews: Through face-to-face communication, students’ oral expression skills, interpersonal skills, and thinking logic are evaluated. This method requires the subjective judgment of the evaluator, and the evaluation results may have certain subjective biases.

Traditional evaluation methods usually rely on subjective evaluations, such as subjective questionnaires and student self-evaluations. These evaluations are easily affected by personal subjective preferences, misunderstandings or biases, and the evaluation results may not be objective and accurate enough. Traditional evaluation methods often only focus on a few aspects or indicators and cannot comprehensively assess students' comprehensive qualities. For example, they only focus on academic performance and ignore other important qualities, or they only focus on subject knowledge and ignore comprehensive qualities and practical abilities. Traditional evaluation methods are usually one-time and cannot track and evaluate students' development and progress for a long time. This evaluation method cannot detect students' potential and problems in a timely manner and provide personalized support and guidance. Traditional evaluation methods lack the support of multi-source data and cannot make full use of data generated by students in learning, practice and social activities, which limits the accuracy and comprehensiveness of evaluation. Traditional evaluation methods usually require a lot of time and human resources, such as collecting and analyzing questionnaire data, organizing interviews and review processes, etc., which increases the cost and workload of evaluation.

The traditional comprehensive quality evaluation method of college students has some limitations and cannot comprehensively and objectively evaluate the multi-dimensional characteristics and potential value of students. Therefore, new methods such as multi-source data and intelligent computing are needed to improve the accuracy and comprehensiveness of evaluation.

Figure 1 is a flow chart of a comprehensive quality management method for college students based on data analysis according to an embodiment of the present application. Figure 2 is a schematic structural diagram of a comprehensive quality management method for college students based on data analysis according to an embodiment of the present application. As shown in Figures 1 and 2, the comprehensive quality management method for college students based on data analysis includes: 110. Obtaining the academic administration system data, library system data, campus card system data and community system data of the college students to be evaluated; 120 , jointly analyze the academic affairs system data, the library system data, the campus card system data and the club system data to obtain the multi-dimensional semantic association feature vector of the student object; and, 130, based on the student object The multi-dimensional semantic association feature vector determines the estimated comprehensive quality of the college student to be evaluated.

In step 110, ensure that the process of obtaining data complies with relevant privacy protection laws and regulations to protect students' personal privacy and data security. Ensure that the data obtained is accurate and avoid errors or distortions during data collection or processing. By obtaining data from different systems, we can obtain information about students in academic, practical, social and other dimensions, and enrich the data sources for assessment. Integrating data from multiple systems can provide more comprehensive student information and help to fully understand students' comprehensive qualities and potential.

In step 120, the acquired data is cleaned, denoised and processed to ensure the consistency and availability of the data. According to the evaluation goals, relevant features are extracted from the data of each system and fused to form a multi-dimensional semantic association feature vector of the student object. Joint analysis of data from different systems can reveal the correlations and interactions between different dimensions and provide a more comprehensive picture of students. Through feature extraction and fusion, rich and diverse features can be obtained to more accurately describe students' comprehensive qualities and potential.

In step 130, appropriate algorithms and models are selected to analyze and evaluate the feature vectors of student objects, such as machine learning algorithms, data mining techniques, etc. According to the evaluation goals, corresponding evaluation indicators are defined, such as comprehensive quality estimates, ability levels, etc. Evaluation based on multi-dimensional semantic association feature vectors can improve the objectivity and accuracy of evaluation and reduce the influence of subjective factors. Through comprehensive quality estimates, personalized assessment results and development suggestions can be provided for each student to promote their all-round development and growth.

Through the above steps, multi-source data and intelligent computing methods can be used to improve the accuracy, comprehensiveness and personalization of evaluation, and better assess the overall quality of college students.

In response to the above technical problems, the technical concept of this application is to combine multi-source data to capture the potential characteristics of college students' comprehensive quality, intelligently calculate the estimated value of college students' comprehensive quality, and provide deep insights and intelligent decisions for college education management.

Specifically, in the technical solution of this application, first, the academic administration system data, library system data, campus card system data and club system data of the college students to be evaluated are obtained. Among them, the academic administration system data records students’ learning status, course grades, course selection records and other information. These data can reflect students’ academic performance and abilities; the library system data records students’ borrowing records, reading preferences and library activities. Participation status and other information, these data can reflect students' reading ability, subject interests and independent learning ability; campus card system data records students' consumption records, access control records and campus activity participation and other information, these data can reflect students' daily life Habits, social circles and degree of participation in campus activities; club system data records students’ participation in club activities, positions held and club achievements. These data can reflect students’ organizational skills, leadership skills and teamwork skills.

Among them, the academic administration system data includes students’ academic performance, course elective status, credit completion status, academic honors and other information. These data can reflect students’ academic performance and achievements. For example, a student's grade point average (GPA) can measure the quality of his or her academic performance, and credit completion status can help understand whether a student has completed academic requirements on time. Educational administration system data provides an important basis for evaluating students’ learning abilities and academic levels.

Library system data includes students’ borrowing records, library usage frequency, reading preferences and other information. These data can reflect students’ reading habits, knowledge acquisition and interests in different fields. For example, the type and number of books borrowed by students can show the breadth and depth of their subjects, and the frequency of library use can reflect students' enthusiasm for knowledge acquisition. Library system data provide important clues in assessing student knowledge and information literacy.

Campus card system data includes students’ consumption records, access control records, activity participation and other information. These data can reflect students’ participation, social ability and activity experience in campus life. For example, students' activity participation can show their teamwork and leadership skills, and consumption records can understand students' lifestyle and social circles. Campus card system data provides important clues to evaluate students' overall quality and social abilities.

Club system data includes information such as the clubs students participate in, positions they hold, and activity participation. These data can reflect students' organizational skills, leadership skills, and teamwork skills in club activities. For example, students’ positions and participation in activities in clubs can demonstrate their leadership potential and organizational abilities. Club system data provide important clues in assessing students’ leadership and social skills. Comprehensive use of academic administration system data, library system data, campus card system data and club system data can comprehensively understand the comprehensive quality and potential of students from multiple dimensions such as academic, practical, and social, and provide a more accurate and comprehensive basis for evaluation.

Obtaining the academic affairs system data, library system data, campus card system data and club system data of the college students to be evaluated plays an important role in finalizing the estimated comprehensive quality of the college students to be evaluated. The data of each system provides different dimensions of information, which can comprehensively evaluate the quality of students from multiple perspectives such as academic, practical, and social. The data of the academic administration system reflects students' academic performance and academic achievements, and the data of the library system reflects students' reading and knowledge. In terms of acquisition status, the campus card system data reflects students’ activity participation and campus life, and the club system data reflects students’ teamwork and leadership skills. Combining these data can more accurately evaluate students’ comprehensive qualities.

By obtaining data from different systems, we can obtain information about students in multiple aspects, help understand students' interests, expertise, participation and development potential, etc., and help comprehensively evaluate students' personality characteristics, development trends and adaptability. By comprehensively analyzing data from multiple systems, students' potential and problems can be discovered. For example, the academic administration system data may show that students perform well in a certain subject, while the club system data may show that students have potential in leadership skills. These findings can provide Students are provided with individualized support and developmental guidance. Comprehensive analysis of multi-source data can improve the accuracy of the assessment. Data from different systems corroborate each other, increasing the credibility of the assessment results. At the same time, by using technologies such as big data analysis and machine learning, hidden features in the data can be unearthed. Correlations and patterns, thereby more accurately estimating the overall quality of students.

Obtaining data from multiple systems can provide a more comprehensive, accurate and objective assessment basis, help determine the estimated comprehensive quality of college students to be assessed, and provide targeted support and guidance for students' personalized development.

In one embodiment of the present application, a joint analysis is performed on the academic affairs system data, the library system data, the campus card system data and the club system data to obtain a multi-dimensional semantic association feature vector of student objects, including : Semantically encode the academic affairs system data, the library system data, the campus card system data and the community system data respectively to obtain the academic affairs system data semantic encoding feature vector, the library system data semantic encoding feature vector, Campus card system data semantic coding feature vector and community system data semantic coding feature vector; and, extract the academic affairs system data semantic coding feature vector, the library system data semantic coding feature vector, the campus card system data semantic coding feature vector The semantic correlation feature between the vector and the community system data semantic encoding feature vector is used to obtain the multi-dimensional semantic correlation feature vector of the student object.

Then, perform semantic coding on the academic affairs system data, the library system data, the campus card system data and the club system data respectively to obtain the academic affairs system data semantic coding feature vector and the library system data semantic coding feature vector. , campus card system data semantic encoding feature vector and community system data semantic encoding feature vector. That is, the academic administration system data, the library system data, the campus card system data and the club system data are converted into structured vector representations to facilitate subsequent model reading and identification.

In one embodiment of the present application, the semantic coding feature vector of the academic administration system data, the semantic coding feature vector of the library system data, the semantic coding feature vector of the campus card system data, and the semantic coding feature vector of the club system data are extracted. Semantic correlation features between vectors to obtain multi-dimensional semantic correlation feature vectors of student objects, including: semantic coding feature vectors of the academic affairs system data, semantic coding feature vectors of the library system data, and semantic coding of the campus card system data The feature vector and the semantic encoding feature vector of the community system data are arranged into a two-dimensional feature matrix and then passed through the text convolutional neural network model to obtain the multi-dimensional semantic association feature vector of the student object.

Then, the academic affairs system data semantic coding feature vector, the library system data semantic coding feature vector, the campus card system data semantic coding feature vector and the community system data semantic coding feature vector are arranged into a two-dimensional feature matrix Finally, the text convolutional neural network model is used to obtain the multi-dimensional semantic association feature vector of the student object. That is, the text convolutional neural network model is used to extract implicit correlation feature information in multi-source data. It should be understood that assessing the comprehensive quality of college students needs to cover multiple aspects, including academic ability, innovation ability, teamwork ability, communication ability, social ability, practical ability, etc. Therefore, a single data often cannot comprehensively assess a student's overall quality. Through the text convolutional neural network model, the high-dimensional feature distribution under each data source is comprehensively analyzed and feature mined to capture a more comprehensive feature expression and provide a more accurate source of information for the comprehensive quality assessment of college students.

In one embodiment of the present application, determining the comprehensive quality estimate of the college student object to be evaluated based on the multi-dimensional semantic association feature vector of the student object includes: performing feature distribution on the multi-dimensional semantic association feature vector of the student object Optimize to obtain the multi-dimensional semantic correlation feature vector of the optimized student object; and perform decoding and regression on the multi-dimensional semantic correlation feature vector of the optimized student object through the decoder to obtain the decoding value, and the decoding value is used to represent the college student to be evaluated. The overall quality estimate of the subject.

Further, the multi-dimensional semantic correlation feature vector of the student object is decoded and regressed through a decoder to obtain a decoded value. The decoded value is used to represent the estimated comprehensive quality of the college student object to be evaluated. By converting data from multiple systems into feature vectors and performing decoding regression through the decoder, the information in each dimension can be integrated to obtain a comprehensive evaluation value, which can comprehensively consider students' academic, practical, social and other aspects. performance, and avoid one-sided assessment or over-reliance on one aspect of data.

The process of decoding regression using a decoder is an objective calculation based on data and algorithms, reducing the interference and bias of subjective evaluation. Compared with the traditional subjective evaluation method, this data-based evaluation method is more objective and fair and can reduce the impact of subjective factors on the evaluation results. The decoded value can be used to represent the estimated comprehensive quality of college students to be evaluated, which means that each student can get personalized assessment results. The decoded value can reflect the student's performance and potential in different dimensions, providing students with targeted Provide development suggestions and guidance to help them better develop and improve their overall quality. The method of using decoders for decoding regression can efficiently handle large amounts of data and can adapt to different student objects and characteristics. Since the decoder is based on machine learning and model training methods, it can be continuously improved by increasing training data and optimizing algorithms. Decoder performance and accuracy.

Decoding and regressing the multi-dimensional semantic association feature vectors of student objects through the decoder can provide more comprehensive, objective and personalized assessment results, reduce the impact of subjective factors, and provide targeted support and guidance for student development. This method has good results and can be applied to large-scale student assessments.

In the technical solution of the present application, the semantic coding feature vector of the academic affairs system data, the semantic coding feature vector of the library system data, the semantic coding feature vector of the campus card system data and the semantic coding feature vector of the club system data are After being arranged into a two-dimensional feature matrix, the text convolutional neural network model can be used to extract the semantic coding feature vectors of the academic affairs system data, the semantic coding feature vectors of the library system data, the semantic coding feature vectors of the campus card system data, and the semantic coding feature vectors of the campus card system data. The cross-sample high cross-sample semantic features of a single sample among the coded text semantic features of the academic affairs system data, library system data, campus card system data and community system data of the college student object to be evaluated are respectively expressed by the semantic coding feature vectors of the community system data. However, if the academic affairs system data semantic coding feature vector, the library system data semantic coding feature vector, the campus card system data semantic coding feature vector and the club system data semantic coding feature vector are each The encoded text semantic features of each are used as foreground object features. When extracting cross-sample high-order semantic correlation features, background distribution noise related to the feature distribution interference of single-sample semantic features will also be introduced. Moreover, the multi-dimensional semantics of the student objects The associated feature vector has a characteristic expression of hierarchical association of features. Therefore, it is expected to enhance the expression effect based on the distribution characteristics of the multi-dimensional semantic associated feature vector of the student object.

Therefore, the applicant of this application performs distribution gain on the multi-dimensional semantic association feature vector of the student object based on the probability density feature imitation paradigm, which is specifically expressed as: using the following optimization formula to perform a distribution gain on the multi-dimensional semantic association feature vector of the student object based on The probability density feature imitates the distribution gain of the paradigm; where the optimization formula is:

Wherein, V is the multi-dimensional semantic association feature vector of the student object, v _i ^′ is the feature value at the i-th position of the optimized student object multi-dimensional semantic association feature vector, and L is the multi-dimensional semantic association feature vector of the student object. The length of v _i is the feature value of the i-th position of the multi-dimensional semantic association feature vector V of the student object, represents the square of the second norm of the multi-dimensional semantic association feature vector V of the student object, and α is a weighted hyperparameter, and exp(·) represents the calculation of the natural exponential function value with the numerical value as the power.

Here, based on the feature imitation paradigm of the natural Gaussian distribution on the probability density based on the standard Cauchy distribution, the distribution gain based on the probability density feature imitation paradigm can use the feature scale as an imitation mask to distinguish foreground object features in a high-dimensional feature space. and background distribution noise, so as to perform distributed soft matching of semantic cognition of feature space mapping on the high-dimensional space based on the time-domain spatial hierarchical semantics of high-dimensional features to obtain unconstrained distribution gain of high-dimensional feature distribution and improve the above-mentioned The expression effect of the multi-dimensional semantic correlation feature vector of the student object based on the feature distribution characteristics improves the accuracy of the decoding value obtained by the decoder of the multi-dimensional semantic correlation feature vector of the student object.

In summary, the comprehensive quality management method 100 of college students based on data analysis is clarified based on the embodiment of the present application. It combines multi-source data to capture the potential characteristics of college students' comprehensive quality, and intelligently calculates the estimated value of college students' comprehensive quality, providing a solution for colleges and universities. Education management provides deep insights and intelligent decision-making.

In one embodiment of the present application, FIG. 3 is a block diagram of a comprehensive quality management system for college students based on data analysis according to an embodiment of the present application. As shown in Figure 3, the comprehensive quality management system 200 for college students based on data analysis according to the embodiment of the present application includes: a data acquisition module 210, which is used to obtain the academic administration system data, library system data, and campus card system of the college students to be evaluated. Data and club system data; the joint analysis module 220 is used to jointly analyze the academic affairs system data, the library system data, the campus card system data and the club system data to obtain multi-dimensional semantic associations of student objects. Feature vector; and, the comprehensive quality estimation value determination module 230 is used to determine the comprehensive quality estimation value of the college student object to be evaluated based on the multi-dimensional semantic association feature vector of the student object.

In the comprehensive quality management system for college students based on data analysis, the joint analysis module includes: a semantic coding unit for separately analyzing the academic affairs system data, the library system data, the campus card system data and The club system data is semantically encoded to obtain the academic affairs system data semantic encoding feature vector, the library system data semantic encoding feature vector, the campus card system data semantic encoding feature vector and the club system data semantic encoding feature vector; and, a feature vector extraction unit , used to extract the semantic association between the semantic coding feature vector of the academic affairs system data, the semantic coding feature vector of the library system data, the semantic coding feature vector of the campus card system data, and the semantic coding feature vector of the community system data. Features to obtain multi-dimensional semantic association feature vectors of student objects.

In the comprehensive quality management system for college students based on data analysis, the feature vector extraction unit is used to: combine the semantic coding feature vector of the academic affairs system data, the semantic coding feature vector of the library system data, and the campus card The system data semantic coding feature vector and the community system data semantic coding feature vector are arranged into a two-dimensional feature matrix and then passed through the text convolutional neural network model to obtain the multi-dimensional semantic association feature vector of the student object.

In the comprehensive quality management system for college students based on data analysis, the comprehensive quality estimation value determination module includes: an optimization unit for performing feature distribution optimization on the multi-dimensional semantic association feature vector of the student object to obtain an optimized student object. Multi-dimensional semantic correlation feature vector; and, a decoding unit, used to decode and regress the optimized student object multi-dimensional semantic correlation feature vector through a decoder to obtain a decoded value, where the decoded value is used to represent the college student object to be evaluated. comprehensive quality estimate.

In the comprehensive quality management system for college students based on data analysis, the optimization unit is used to perform distribution gain based on the probability density feature imitation paradigm on the multi-dimensional semantic association feature vector of the student object using the following optimization formula; wherein, The optimization formula is:

Wherein, V is the multi-dimensional semantic association feature vector of the student object, v _i ^′ is the feature value at the i-th position of the optimized student object multi-dimensional semantic association feature vector, and L is the multi-dimensional semantic association feature vector of the student object. The length of v _i is the feature value of the i-th position of the multi-dimensional semantic association feature vector V of the student object, represents the square of the second norm of the multi-dimensional semantic association feature vector V of the student object, and α is a weighted hyperparameter, and exp(·) represents the calculation of the natural exponential function value with the numerical value as the power.

Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the above-mentioned comprehensive quality management system for college students based on data analysis have been described above with reference to the comprehensive quality management method for college students based on data analysis in Figures 1 to 2 are described in detail in the description, and therefore, repeated description thereof will be omitted.

As mentioned above, the comprehensive quality management system 200 for college students based on data analysis according to the embodiment of the present application can be implemented in various terminal devices, such as servers for comprehensive quality management of college students based on data analysis. In one example, the comprehensive quality management system 200 for college students based on data analysis according to the embodiment of the present application can be integrated into the terminal device as a software module and/or hardware module. For example, the comprehensive quality management system 200 for college students based on data analysis may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the college student comprehensive quality management system 200 based on data analysis The comprehensive quality management system 200 can also be one of the many hardware modules of the terminal device.

Alternatively, in another example, the comprehensive quality management system 200 for college students based on data analysis and the terminal device can also be separate devices, and the comprehensive quality management system 200 for college students based on data analysis can be connected through a wired and/or wireless network. Connect to the terminal device and transmit interactive information according to the agreed data format.

Figure 4 is a schematic diagram of a scenario of a comprehensive quality management method for college students based on data analysis according to an embodiment of the present application. As shown in Figure 4, in this application scenario, first, obtain the academic administration system data (for example, C1 as shown in Figure 4) and library system data (for example, as shown in Figure 4) of the college student to be evaluated (for example, as shown in Figure 4 C2), campus card system data (for example, C3 as shown in Figure 4) and club system data (for example, C4 as shown in Figure 4); then, the obtained academic administration system data, library system data, The campus card system data and the club system data are input into a server (for example, S as shown in Figure 4) deployed with a data analysis-based comprehensive quality management algorithm for college students, wherein the server can manage college students' comprehensive quality based on data analysis. The algorithm processes the academic affairs system data, the library system data, the campus card system data and the club system data to determine the estimated comprehensive quality of the college student to be evaluated.

It should also be pointed out that in the device, equipment and method of the present application, each component or each step can be decomposed and/or recombined. These decompositions and/or recombinations shall be considered equivalent versions of this application.

The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, this application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for the purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the form disclosed herein. Although various example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims (10)

1. A comprehensive quality management method for college students based on data analysis, which is characterized by including: Obtain the academic affairs system data, library system data, campus card system data and club system data of the college students to be evaluated; Conduct a joint analysis on the academic affairs system data, the library system data, the campus card system data and the club system data to obtain a multi-dimensional semantic association feature vector of student objects; and Based on the multi-dimensional semantic association feature vector of the student object, the estimated comprehensive quality of the college student object to be evaluated is determined. 2. The comprehensive quality management method for college students based on data analysis according to claim 1, characterized in that: the academic affairs system data, the library system data, the campus card system data and the community system data are processed. Joint analysis to obtain multi-dimensional semantic association feature vectors of student objects, including: Semantically encode the academic affairs system data, the library system data, the campus card system data and the community system data respectively to obtain the academic affairs system data semantic encoding feature vector, the library system data semantic encoding feature vector, and the campus Card system data semantic encoding feature vector and community system data semantic encoding feature vector; and Extract the semantic correlation features between the semantic coding feature vectors of the academic administration system data, the semantic coding feature vectors of the library system data, the semantic coding feature vectors of the campus card system data, and the semantic coding feature vectors of the club system data to obtain Multi-dimensional semantic association feature vector of student objects. 3. The comprehensive quality management method for college students based on data analysis according to claim 2, characterized by extracting the semantic coding feature vector of the academic affairs system data, the semantic coding feature vector of the library system data, and the campus card system. The semantic correlation features between the data semantic encoding feature vector and the community system data semantic encoding feature vector to obtain the multi-dimensional semantic correlation feature vector of the student object include: Arrange the semantic coding feature vectors of the academic affairs system data, the semantic coding feature vectors of the library system data, the semantic coding feature vectors of the campus card system data and the semantic coding feature vectors of the club system data into a two-dimensional feature matrix and then pass The text convolutional neural network model is used to obtain the multi-dimensional semantic association feature vector of the student object. 4. The comprehensive quality management method of college students based on data analysis according to claim 3, characterized in that, based on the multi-dimensional semantic association feature vector of the student object, the comprehensive quality estimated value of the college student object to be evaluated is determined, including: Perform feature distribution optimization on the multi-dimensional semantic association feature vector of the student object to obtain an optimized multi-dimensional semantic association feature vector of the student object; and The optimized multi-dimensional semantic correlation feature vector of the student object is decoded and regressed through a decoder to obtain a decoded value. The decoded value is used to represent the estimated comprehensive quality of the college student object to be evaluated. 5. The comprehensive quality management method for college students based on data analysis according to claim 4, characterized in that feature distribution optimization is performed on the multi-dimensional semantic association feature vector of the student object to obtain an optimized multi-dimensional semantic association feature vector of the student object, It includes: using the following optimization formula to perform distribution gain based on the probability density feature imitation paradigm on the multi-dimensional semantic association feature vector of the student object; Among them, the optimization formula is: Wherein, V is the multi-dimensional semantic association feature vector of the student object, v′ _i is the feature value at the i-th position of the optimized student object multi-dimensional semantic association feature vector, and L is the multi-dimensional semantic association feature vector of the student object. The length of v _i is the feature value of the i-th position of the multi-dimensional semantic association feature vector V of the student object, represents the square of the second norm of the multi-dimensional semantic association feature vector V of the student object, and α is a weighted hyperparameter, and exp(·) represents the calculation of the natural exponential function value with the numerical value as the power. 6. A comprehensive quality management system for college students based on data analysis, which is characterized by including: The data acquisition module is used to obtain the academic affairs system data, library system data, campus card system data and community system data of the college students to be evaluated; A joint analysis module for jointly analyzing the academic affairs system data, the library system data, the campus card system data and the club system data to obtain multi-dimensional semantic association feature vectors of student objects; and The comprehensive quality estimation value determination module is used to determine the comprehensive quality estimation value of the college student object to be evaluated based on the multi-dimensional semantic association feature vector of the student object. 7. The comprehensive quality management system for college students based on data analysis according to claim 6, characterized in that the joint analysis module includes: Semantic coding unit, used to perform semantic coding on the academic affairs system data, the library system data, the campus card system data and the community system data respectively to obtain the semantic coding feature vector of the academic affairs system data and the library system data. Semantic coding feature vectors, campus card system data semantic coding feature vectors and community system data semantic coding feature vectors; and A feature vector extraction unit, used to extract one of the semantic coding feature vectors of the academic affairs system data, the semantic coding feature vectors of the library system data, the semantic coding feature vectors of the campus card system data, and the semantic coding feature vectors of the club system data. The semantic correlation features between them are used to obtain the multi-dimensional semantic correlation feature vector of the student object. 8. The comprehensive quality management system for college students based on data analysis according to claim 7, characterized in that the feature vector extraction unit is used for: Arrange the semantic coding feature vectors of the academic affairs system data, the semantic coding feature vectors of the library system data, the semantic coding feature vectors of the campus card system data and the semantic coding feature vectors of the club system data into a two-dimensional feature matrix and then pass The text convolutional neural network model is used to obtain the multi-dimensional semantic association feature vector of the student object. 9. The comprehensive quality management system for college students based on data analysis according to claim 8, characterized in that the comprehensive quality estimation value determination module includes: An optimization unit configured to perform feature distribution optimization on the multi-dimensional semantic correlation feature vector of the student object to obtain an optimized multi-dimensional semantic correlation feature vector of the student object; and The decoding unit is used to decode and regress the optimized multi-dimensional semantic correlation feature vector of the student object through a decoder to obtain a decoded value. The decoded value is used to represent the estimated comprehensive quality of the college student object to be evaluated. 10. The comprehensive quality management system for college students based on data analysis according to claim 9, characterized in that the optimization unit is used to perform probability density-based optimization on the multi-dimensional semantic association feature vector of the student object with the following optimization formula Distribution gain of feature imitation paradigm; Among them, the optimization formula is: Wherein, V is the multi-dimensional semantic association feature vector of the student object, v _i ^′ is the feature value at the i-th position of the optimized student object multi-dimensional semantic association feature vector, and L is the multi-dimensional semantic association feature vector of the student object. The length of v _i is the feature value of the i-th position of the multi-dimensional semantic association feature vector V of the student object, represents the square of the second norm of the multi-dimensional semantic association feature vector V of the student object, and α is a weighted hyperparameter, and exp(·) represents the calculation of the natural exponential function value with the numerical value as the power.