CN115965175A - Skyline evaluation-oriented rating method and system - Google Patents
Skyline evaluation-oriented rating method and system Download PDFInfo
- Publication number
- CN115965175A CN115965175A CN202211363175.XA CN202211363175A CN115965175A CN 115965175 A CN115965175 A CN 115965175A CN 202211363175 A CN202211363175 A CN 202211363175A CN 115965175 A CN115965175 A CN 115965175A
- Authority
- CN
- China
- Prior art keywords
- data
- student
- evaluation
- students
- career
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to the technical field of privacy calculation, and particularly discloses a career evaluation-oriented rating method and a career evaluation-oriented rating system, wherein the method comprises the following steps: s1, data aggregation and data storage; s2, cleaning and converting data; s3, quantizing data aiming at each index; s4, extracting characteristics; and step S5, learning an algorithm. The invention constructs a multidimensional grading index evaluation system facing to the student career rating, and can realize multidimensional quantitative evaluation of morality, attendance, physical, intelligence and energy; based on a data mining technology, the method overcomes the limitation of a traditional student comprehensive evaluation expert scoring method, can cultivate full-flow big data based on students, collects various learning behaviors and result data of the students through an intelligent technology, processes and analyzes the learning behaviors and the result data in an automatic mode, extracts a tag set capable of describing the characteristics and the behaviors of the students, is beneficial to ensuring the reliability and the effectiveness of the career evaluation, and realizes the non-inductive evaluation and the concomitant evaluation.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a career evaluation-oriented rating method and system.
Background
According to the employment report of the university students in 2020 issued by the McKesi research institute of the third party in 2020, the employment rate of the graduates in this department has been slowly reduced for years, but the employment rate of the high-job and high-specialty has gradually increased. In employment departures, the rate of "employment work" of students from the division is continuously declining for five years. In the face of severe employment situations, schools need employment guidance services with pertinence, scientificity and accuracy. The whole process of student culture is opened up, and career planning service of students is supported. The method includes the steps that the whole-process growth data from school entrance to graduation of students are comprehensively recorded, the growth data during school such as school scores and the like are covered, a rich talent culture database is established for schools, and a personalized 'growth file' is established for students; based on student training process data, accurately depict student career planning portrait from a plurality of dimensions, indicate the employment direction of adaptation for every student.
The comprehensive evaluation is a student quality evaluation system which runs for many years in various colleges and universities in China, and is an important reference standard for student career quality evaluation. However, the existing comprehensive quality evaluation index system has subjectivity, the evaluation operation process is not standard, and the evaluation result does not support autonomous inquiry of students. The traditional mode of operating and managing by adopting paper is difficult to meet the existing requirements, and gradually exposes the defects of low efficiency, high error probability, opaque evaluation process, general lagging evaluation result, poor actual guidance and the like.
In recent years, the information construction level of the modern science and technology rapid development assisted education industry is continuously improved, and the campus big data environment is formed by the wide use of campus cards in consumption and access control and the accumulation of data in various platform systems of the campus. Through the analysis of campus data, the intrinsic and predictable characteristics of college students can be mined, which is of great significance for improving the informatization management level of colleges. However, although the application of the current data management platform provides basic data support for the comprehensive data analysis of schools, the current data management platform is still deficient in how to effectively utilize the result data and the process data to perform data analysis, and the data analysis is used for comprehensive quality evaluation and student employment guidance processes. The student portrait is an extension of a user portrait in education application, a labeled student model is abstracted according to school behavior data of students to obtain various stereoscopic student portraits, and a connection point of division of students to the school and the school-out performance is searched, so that fine, elaborate and precise employment guidance is provided.
In summary, it is necessary to construct a platform combining big data mining technology and comprehensive evaluation, quantify various characteristics such as student academic industry, behaviors, consumption and social interaction, depict stereo images of students, discuss and mine quantifiable indexes related to student industry selection, and provide guidance for professional employment.
Disclosure of Invention
The invention aims to provide a ranking method and a ranking system for career evaluation, which are used for constructing a career evaluation and employment post matching index system and an algorithm model based on comprehensive evaluation standard research theoretical basis and a student culture scheme and in combination with multidimensional big data of the whole student culture process. Through sorting out student entrance guard data, academic achievement, book borrowing record and other in-school multidimensional data, the student in-school behavior track is constructed, student behavior labels are extracted, and the multi-dimensional grading quantitative evaluation and three-dimensional portrait construction of the students are achieved. The method overcomes the limitation of the traditional expert scoring method for the comprehensive evaluation of the undergraduate students and realizes accurate evaluation. On one hand, college managers are assisted to know the learning career state and behavior characteristics of students more, pay attention to abnormal learning situation in time and give early warning; on the other hand, capacity gaps among students are positioned through radar maps, and differences and regularity of behaviors of different graduate students in schools are contrastively analyzed, so that future graduation direction selection of the students is effectively predicted, personalized career planning is conducted on college students, the students have clear development targets in college graduations, and the problem of difficult employment of college students is solved.
In order to achieve the purpose, the invention provides the following technical scheme:
a career evaluation-oriented rating method comprises the following steps:
s1, data aggregation and data storage;
s2, cleaning and converting data;
s3, quantizing data aiming at each index;
s4, extracting characteristics;
and step S5, learning an algorithm.
As a preferred embodiment of the present invention, in the step S1, data acquisition is performed on student basic information, campus card consumption, entrance guard records of each site, educational administration information system, and library system records; the student basic information records comprise political face, academic information and employment information records of students; the entrance guard record comprises a library access record and a dormitory access record; the student card consumption records comprise canteen consumption records, supermarket consumption records, bathhouse consumption records and the like; the educational administration information records comprise student achievement records, qualification records and reward and punishment records; the library system records include book borrowing records for students.
As a preferred embodiment of the present invention, the step S2 of data cleaning mainly cleans and supplements data in the case that a part of data in the original real data in the step S1 is incorrect or unreasonable.
In a preferred embodiment of the present invention, the category-type qualitative data is digitized in step S3, and a discrete value processing method may be adopted so that the method can be applied to the evaluation index calculation.
As a preferred embodiment of the present invention, the learning characteristic index calculating method in step S4 is as follows:
(1) Observing law
The records of the student comprise warning, serious warning, recorded, checked and watched, and removed school and school; calculating according to a conservation-oriented index by 10 points of full scale, and calculating a deduction value according to the number of times of places subjected to discipline and the weighting of severity;
(2) Attitude of learning
Reflecting the learning attitude of the student by calculating an effort index; whether the students strive to learn and the attitude is correct can be quantified by calculating the ratio of the average duration of the weekend vacations of the students in the library to the longest duration of all the students, or the daily average library stay time;
(3) Learning habits
Respectively calculating the number of books borrowed in the year, including the number of books being read and the number of books being read in the year and the average reading time (days) of each book; weighting the three indexes to obtain a value of the learning habit, wherein the weight is determined by fitting principal component analysis;
(4) Habit of work and rest
By calculating 23 pm: 00 to the next day 4:30, obtaining the index of the work and rest habits of the students according to the ratio of the number of the sleeping times of the students to the total number of the sleeping times of the students, wherein the index is a reverse index;
(5) Law of life
Respectively calculating the rule indexes of the students entering and exiting the library and the rule indexes of the students entering and exiting the dormitory through the rule indexes (EV) calculated through the cross entropy, and then calculating the average of the rule indexes and the rule indexes to obtain the life rule of the students, wherein the rule indexes are reverse indexes;
the law index calculation formula is as follows:
wherein n is v (t i ) The number of times an action v occurs within a time interval in a given time period; the time period may be set to twenty-four hours and the time interval may be set to one hour;
(6) Physical condition
Measuring the physique condition of students through the performance of sports classes, and fuzzily matching the sports classes by keywords such as sports, balls, swimming, sports and the like; then, carrying out weighted summation on the courses, wherein the method for calculating the weighted average score is to take the credit occupied by the subject as the weight of the score fraction so as to obtain the physique score of the student;
the calculation formula is as follows:
wherein, w i And x i Respectively the credit and score of the course i;
(7) Foreign language horizon
By calculating English four-six level test result data and idiom result data, such as Russian (CRT), japanese (CJT), french (CFT), german (CGT) and other courses, if there are multiple tests, the highest historical result is taken, and the test score is fully normalized; after the principal component analysis is carried out, the foreign language level of each student is comprehensively obtained;
(8) Computer power
Measuring the computer skill level of a certain student by calculating the achievement of the relevant course; fuzzy matching is carried out on computer courses by using keywords such as programming, compiling, calculating and programming, and then a weighted summation is carried out on the courses, so that indexes reflecting the computer capacity of students are obtained, and a calculation formula is shown in a formula (2);
(9) Ability to practice
The practical ability level of the student is reflected by calculating the accumulated time (days) of the post of the work attendance of the student in the school, and the student is subjected to standardized treatment on the days in the school;
(10) Learning ability
Respectively calculating three indexes of excellent academic performance, excellent college entrance examination grade performance and existence of hanging records in the school learning period; weighting the three indexes to obtain a value of the learning habit, wherein the weight is determined by fitting principal component analysis;
(11) Award evaluation and optimization evaluation
The method comprises the following steps of comprehensively obtaining the award evaluation and optimization index of each student after performing principal component analysis by calculating the number of times that students honor and acquire award schooling in the school period and the accumulated amount of the honor and acquire award schooling in the school period;
(12) Academic early warning
Calculating the records of the students on the academic early warning relevant places during the school period by 10 points of full scale, and weighting and calculating the deduction value according to the times and the severity of the academic places (academic warning and trial reading);
finally, normalizing the index calculation result to be between 0 and 1, and sorting the index into a key-value format according to the ID number of the student, namely, after the ID of the student, carrying out quantization results on all indexes of the student; and extracting the student portrait label according to the value range setting based on the index table.
As a preferred embodiment of the present invention, the learning habit principal component analysis algorithm is described as follows:
inputting: sample set D = { x 1 ,x 2 ,.......,x m }；
Low dimensional space dimension d'
The process is as follows:
all samples were normalized:
calculating the covariance matrix XX of the samples T ；
For covariance matrix XX T Decomposing the characteristic value;
taking the eigenvector w corresponding to the largest d' eigenvalues 1 ，w 2 ，...,w d' ；
And (3) outputting: projection matrix W = (W) 1 ，w 2 ，...,w d' )；
And (4) obtaining a dimensionality reduction matrix according to the feature vector mapping, namely obtaining an index value by integrating the three indexes.
In a preferred embodiment of the present invention, in step S5, when the index evaluation value is comprehensively calculated to obtain the lifetime score, the relative importance, i.e., the weight, of each index should be determined first.
A career-oriented rating system, the system comprising:
the index system layer comprises a core literacy module and a comprehensive literacy module and is used for evaluating the quality of the student's career; forming a career evaluation index system under a core literacy vision field, and specifically setting five evaluation dimensions including ideality, learning performance, physical and mental health, academic performance and competence;
the data practice layer comprises a data acquisition module, a characteristic engineering module and a weight design module, wherein the data acquisition module acquires the basic information of students of a university corresponding to a school year and the daily behavior records of the students by using a database interface; the characteristic engineering module is used for carrying out characteristic linear construction on the basic attribute data set, extracting a fact label, and then obtaining a model label through rule judgment and model calculation; the weight design module is used for establishing a data mapping relation between the evaluation index and the model label according to the constructed multi-dimensional native career evaluation index system;
and the digital portrait layer is used for forming a comprehensive score of the lifetime quality and forming a student portrait label system.
As a preferred implementation scheme of the invention, the data collection module mainly derives from student campus card consumption, entrance guard records of each site and educational administration information systems; the method comprises the steps of preprocessing the information of the primary data of the college students, including data cleaning, missing value filling, format conversion and the like, and forming a standard basic attribute data set for data mining.
As a preferred embodiment of the invention, the digital portrait layer comprises a career scoring rating module and a student portrait tag system construction module; the career score rating module performs weighted calculation according to a plurality of dimensions of career comprehensive evaluation on the basis of evaluation indexes and index weights constructed by the data practice layer to form comprehensive scores and percentage ranking of the career quality; the student portrait label system construction module constructs a student portrait label system by screening and judging rules of the model labels extracted from the data practice layer.
Compared with the prior art, the invention has the beneficial effects that: the invention constructs a multidimensional grading index evaluation system facing to the student career rating, and can realize multidimensional quantitative evaluation of morality, attendance, physical, intelligence and energy.
Based on a data mining technology, the method overcomes the limitation of a traditional student comprehensive evaluation expert scoring method, can cultivate full-flow big data based on students, collects various learning behaviors and result data of the students through an intelligent technology, processes and analyzes the learning behaviors and the result data in an automatic mode, extracts a tag set capable of describing the characteristics and the behaviors of the students, is beneficial to ensuring the reliability and the effectiveness of the career evaluation, and realizes the non-inductive evaluation and the concomitant evaluation.
Through a dynamic data circulation process and a trigger mechanism design, an automatic data processing and index feature extraction pipeline is triggered to dynamically update along with student school entering data, school data and graduation going data, a student career scoring report form, a graded radar map and the like are formed, and a complete student growth track and a dynamic portrait trend are constructed.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 is a flowchart of a ranking method for lifetime assessment according to the present invention;
fig. 2 is a career evaluation system diagram facing career evaluation according to the invention;
FIG. 3 is a career evaluation oriented director evaluation index system table of the present invention;
fig. 4 is an index weight table for lifetime evaluation according to the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Referring to fig. 1 to 4, the present invention provides a ranking method for career evaluation, which includes the following specific embodiments: the method introduces various characteristics such as behaviors, academic industry and the like of students based on multidimensional campus data of the students, and establishes a three-layer career assessment index system, a three-dimensional portrait label process and a design idea of a data transfer mode. The career evaluation algorithm flow is shown in detail in fig. 2.
And S1, data aggregation and data storage.
The data set used by the invention is from the basic information of students in selected school years, campus card consumption, entrance guard records of each site, educational administration information system and library system records. Wherein the student basic information records comprise academic information and employment information records; the entrance guard record comprises a library access record and a dormitory access record; the student card consumption records comprise canteen consumption records, supermarket consumption records, bathhouse consumption records and the like; the educational administration information record comprises student score record, subsidy record and reward and punishment record; the library system records contain the student's book borrowing records.
Raw data of students is stored in an Oracle database, and SQL scripts containing structure definitions and data are exported by using an SQL script language. By periodically executing the sql scripts in batches and establishing and updating the student database based on the PostgreSQL, a data base is laid for subsequent study targets such as student behavior analysis and portrait construction.
And S2, cleaning and converting data.
Partial data errors or unreasonable situations exist in the original real data. For example, in an access record table recorded by a one-card, the conditions that the students enter or exit a library or a dormitory once and the entering time and the leaving time of the students are not equal to each other are repeatedly recorded; in the student score table, data of partial students are lost; in the recording of award and punishment, there are some items and the condition of award schooling amount loss. Therefore, the acquired raw data of the students needs to be firstly subjected to data cleaning. For example, for repeatedly recorded access control data, screening and deleting are required; for missing data records, a reasonable padding is required. E.g., using a median score or a scalar value to fill in missing score values in the score table; and the reward and punishment rule is used for requiring filling missing reward and punishment records and the like.
And step S3, quantizing the data aiming at each index.
In addition, the category-type qualitative data may be numerically processed in a discrete value processing manner so as to be applicable to evaluation index calculation.
And S4, extracting characteristics.
The specific calculation method for the career evaluation index is as follows:
(1) Observing method
The records of the student's office include "warning", "serious warning", "remembering", "checking and watching", "removing school" and so on. According to the law of discipline, the score is calculated by 10 points of full scale, and the deduction value is weighted and calculated according to the number of times of places subjected to discipline and the severity.
(2) Attitude of learning
The learning attitude of the student is reflected by calculating the effort index. Whether the students are struggling to learn and the attitudes are correct can be quantified by calculating the ratio of the average length of the students' weekend vacations in the library to the longest length of all students, or the daily average library stay time.
(3) Learning habits
Respectively calculating the number of books borrowed in the year, including the number of books being read and the number of books being read in the year and the average reading time (days) of each book; and weighting the three indexes to obtain a value of the learning habit, wherein the weight is determined by fitting principal component analysis.
The principal component analysis algorithm is described as follows:
and (4) obtaining a dimensionality reduction matrix according to the feature vector mapping, namely obtaining an index value by integrating the three indexes.
(4) Habit of work and rest
By calculating 23 pm: 00 to the next day 4: and (3) obtaining the index of the work and rest habits of the students according to the ratio of the number of the sleeping times of the students to the total number of the sleeping times of the students, wherein the index is a reverse index.
(5) Law of life
And (3) calculating rule indexes (EV) of the cross entropy calculation, namely calculating rule indexes of the students entering and exiting the library and rule indexes of the students entering and exiting the dormitory respectively, and calculating the average of the rule indexes and the rule indexes to obtain the life rule of the students, wherein the rule indexes are reverse indexes.
The law index calculation formula is as follows:
wherein n is v (t i ) The number of times an action v occurs within a time interval in a given time period. The time period may be set to twenty-four hours and the time interval may be set to one hour.
(6) Physical condition
The physical conditions of students are measured through the performances of sports classes, and the sports classes are matched by keywords such as sports, balls, swimming, sports and the like in a fuzzy way. And then carrying out weighted summation on the courses, wherein the method for calculating the weighted average score is to take the credit occupied by the subject as the weight of the score so as to obtain the constitutional status score of the student.
The calculation formula is as follows:
wherein, w i And x i Respectively the credits and achievements of course i.
(7) Foreign language horizon
By calculating English four-six level test result data and Chinese level result data, such as Russian (CRT), japanese (CJT), french (CFT), german (CGT) courses, the highest historical result is obtained if there are multiple tests, and the normalization processing is carried out according to the full score of the test. And after the principal component analysis is carried out, the foreign language level of each student is comprehensively obtained.
(8) Computer power
The computer skill level of a student is measured by calculating the performance of the relevant course. The computer courses are fuzzy matched by using keywords such as programming, compiling, calculating and program, and then a weighted summation is carried out on the courses, so as to obtain indexes reflecting the computer capacity of students, and the calculation formula is shown in formula (2).
(9) Capability of practice
The level of practical ability of students is reflected by calculating the accumulated time (days) of the posts of the students serving as the school attendance and the study, and the students carry out standardized treatment on the days of the school.
(10) Learning ability
Respectively calculating three indexes of excellent academic performance, excellent college entrance examination filing performance and whether on-hook records exist during school learning; and obtaining a value of the learning habit by weighting the three indexes, wherein the weight is determined by fitting through principal component analysis.
(11) Prize evaluation and optimization evaluation
The method comprises the steps of calculating the times of the students for honoring and obtaining the prize and the amount of the accumulated money for the students during the school, and after the main component analysis, comprehensively obtaining the prize evaluation and the optimization indexes of each student.
(12) Academic early warning
The deduction value is calculated by calculating whether students have related points recorded by academic early warning during school, calculating by 10 points of full scale, and weighting and calculating according to the times and severity of the points (academic warning and trial reading) suffered by the academic.
And finally, normalizing the index calculation result to be between 0 and 1, and rearranging the index into a key-value format according to the student ID number, namely, the student ID is followed by all index quantization results of the student. And extracting the student portrait label according to the value range setting based on the index table.
And step S5, learning an algorithm.
Because the importance of each index in the index system is different, when the index evaluation value is comprehensively calculated to obtain the career score, the relative importance, namely the weight, of each index is determined.
In the invention, the initial weight of a three-level index system is drawn up on the basis of literature research, interview and practical experience. In order to realize the connection with the existing comprehensive evaluation system of the university, the index weight is mainly set as the original weight; for the subdivided evaluation items which are not related in the existing evaluation system, the dimensions and the weight setting of the existing domestic and foreign student evaluation are comprehensively referred, and the original weight is expanded by classifying and combing the dimensions and the weight setting of the comprehensive evaluation standard. Specific weight settings are seen in fig. 4.
Please refer to fig. 1 for further development; the invention discloses a multidimensional-based lifetime evaluation method and a multidimensional-based lifetime evaluation system, which specifically comprise an index system layer, a data practice layer and a digital portrait layer, and are shown in figure 1. The index system layer is used for guiding data gathering, storage, cleaning and index calculation work of the data practice layer; and forming a career score rating and student portrait label system of the data portrait layer based on the indexes and the weights constructed by the data practice layer.
The university of sea H above the index system layer is a research carrier, and the quality of the student's career is evaluated from two modules of ' academic performance ' and ' comprehensive quality ' according to the training characteristics and the learning concept of school students, the combing and summarizing of related career evaluation academic research documents and policy texts. The method is characterized in that a learning career evaluation index system under the core literacy vision field is formed, and five evaluation dimensions including ideality (moral), learning performance (duty), physical and mental health (physical), academic achievement (intelligence) and competence (competence) are specifically set. The table of the index system is detailed in figure 3.
The data practice layer comprises data acquisition, feature engineering and weight design. The data acquisition module acquires basic information of students of selected school years of university H and daily behavior records of the students through a database interface, and the data set mainly comes from student campus card consumption, entrance guard records of various places and educational administration information systems. The method comprises the steps of preprocessing the information of the primary data of the college students, including data cleaning, missing value filling, format conversion and the like, and forming a standard basic attribute data set for data mining. And the characteristic engineering module performs characteristic linear construction on the basic attribute data set, extracts the fact label, and then obtains a model label through rule judgment and model calculation. And establishing a data mapping relation between the evaluation index and the model label according to the established multidimensional chive evaluation index system. And the weight design module combines the indexes with strong correlation by combining a principal component analysis method based on the expert scoring result, thereby constructing the index weight.
The digital portrait layer comprises a career score rating and student portrait label system construction. The career score rating is based on the evaluation index and index weight constructed by the data practice layer, and the comprehensive score and percentage ranking of the career quality are formed through weighted calculation according to a plurality of dimensions of the career comprehensive evaluation. In addition, a student portrait label system is constructed by screening and judging rules of model labels extracted from the data practice layer.
The invention solves the problems that the evaluation work of students in the prior art causes the work of teachers to be complicated, the subjective scoring evaluation is not objective enough, and the expected effect can not be achieved or even the students can not fall to the ground. The intelligent technology is used for collecting various learning behaviors and result data of students, objective facts are taken as bases, and the data are processed and analyzed in an automatic mode, so that a label set capable of describing the characteristics and behaviors of the students is extracted, the evaluation content is rich and complete, and the method is more scientific, fair, objective and comprehensive.
Illustratively, the processor fetches instructions from the memory one by one, analyzes the instructions, then completes corresponding operations according to the instruction requirements, generates a series of control commands, enables all parts of the computer to automatically, continuously and coordinately act to form an organic whole, realizes the input of programs, the input of data and the operation and outputs results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) which is used for storing computer programs, and a protection device is arranged outside the Memory.
Illustratively, a computer program can be partitioned into one or more modules, which are stored in memory and executed by a processor to implement the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
Those skilled in the art will appreciate that the above description of the service device is merely exemplary and not limiting of the terminal device, and may include more or less components than those described, or combine certain components, or different components, such as may include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal equipment and connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs required by at least one function (such as an information acquisition template display function, a product information publishing function and the like) and the like; the storage data area may store data created according to the use of the berth status display system (such as product information acquisition templates corresponding to different product categories, product information that needs to be issued by different product providers, and the like). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The terminal device integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the modules/units in the system according to the above embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the functions of the embodiments of the system. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one of 8230, and" comprising 8230does not exclude the presence of additional like elements in a process, method, article, or apparatus comprising the element.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A career evaluation-oriented rating method, comprising the steps of:
s1, data aggregation and data storage;
s2, cleaning and converting data;
s3, quantizing data aiming at each index;
s4, extracting characteristics;
and step S5, learning career evaluation algorithm.
2. The career evaluation oriented rating method as claimed in claim 1, wherein the step S1 collects data of student basic information, campus card consumption, entrance guard records of each site, educational information system and library system records; the student basic information records comprise political face, academic information and employment information records of students; the entrance guard record comprises a library access record and a dormitory access record; the student card consumption records comprise canteen consumption records, supermarket consumption records and bathhouse consumption records; the educational administration information record comprises student score record, subsidy record and reward and punishment record; the library system records contain the student's book borrowing records.
3. A career evaluation oriented rating method as claimed in claim 2, wherein in the step S2, data cleaning is performed, and data cleaning and supplementing are mainly performed when partial data errors or unreasonable data exist in the original real data in the step S1.
4. The career evaluation oriented rating method according to claim 3, wherein in the step S3, the category type qualitative data is processed in a numerical manner, and a discrete value processing manner is adopted, so that the method can be applied to evaluation index calculation.
5. The career evaluation-oriented rating method according to claim 4, wherein the learning feature index calculation method in the step S4 is as follows:
(1) Observing method
The records of the student comprise warning, serious warning, recorded, checked and watched, and removed school and school; calculating according to a conservation law index by 10 points of full scale, and weighting and calculating a deduction value according to the number of times of branchs and the severity degree;
(2) Attitude of learning
Reflecting the learning attitude of the student by calculating an effort index; whether the students make efforts for learning and the attitudes are correct can be quantified by calculating the ratio of the average duration of the holidays of the students in the library to the longest duration of all students or the daily average library residence time;
(3) Learning habits
Respectively calculating the number of books borrowed in the year, including the number of books being read and the number of books being read in the year and the average reading time (days) of each book; weighting the three indexes to obtain a value of the learning habit, wherein the weight is determined by fitting principal component analysis;
(4) Habit of work and rest
By calculating 23 pm: 00 to the next day 4:30, obtaining the index of the work and rest habits of the students according to the ratio of the number of the sleeping times of the students to the total number of the sleeping times of the students, wherein the index is a reverse index;
(5) Law of life
Respectively calculating the rule indexes of the students entering and exiting the library and the rule indexes of the students entering and exiting the dormitory through the rule indexes (EV) calculated through the cross entropy, and then calculating the average of the rule indexes and the rule indexes to obtain the life rule of the students, wherein the rule indexes are reverse indexes;
the law index calculation formula is as follows:
wherein n is v (t i ) The number of times that an action v occurs within a time interval in a given time period; the time period may be set to twenty-four hours and the time interval may be set to one hour;
(6) Physical condition
Measuring the physical condition of students through the performance of sports courses, and fuzzily matching the sports courses by using keywords of sports, balls, swimming and sports; then, carrying out weighted summation on the courses, wherein the method for calculating the weighted average score is to take the credit occupied by the subject as the weight of the score fraction so as to obtain the physique score of the student;
the calculation formula is as follows:
wherein w i And x i Respectively the credit and score of the course i;
(7) Foreign language horizon
By calculating English four-six level test result data and idiom result data, such as Russian (CRT), japanese (CJT), french (CFT) and German (CGT) courses, if there are multiple tests, the highest historical result is taken, and the test is normalized according to the full score of the test; after the principal component analysis is carried out, the foreign language level of each student is comprehensively obtained;
(8) Computer power
Measuring the computer skill level of a certain student by calculating the achievement of the relevant course; fuzzy matching is carried out on computer classes by using keywords of programming, compiling, calculating and program, and then a weighted summation is carried out on the classes, so as to obtain an index reflecting the computer capability of the student, wherein a calculation formula is shown in a formula (2);
(9) Capability of practice
The practical ability level of the student is reflected by calculating the accumulated time (days) of the post of the work attendance of the student in the school, and the student is subjected to standardized treatment on the days in the school;
(10) Learning ability
Respectively calculating three indexes of excellent academic performance, excellent college entrance examination filing performance and whether on-hook records exist during school learning; weighting the three indexes to obtain a value of the learning habit, wherein the weight is determined by fitting principal component analysis;
(11) Award evaluation and optimization evaluation
The method comprises the steps of performing principal component analysis by calculating the times of the students for honoring and obtaining the prize and income in the school period and the accumulated amount of the honoring and obtaining the prize and evaluation index of each student comprehensively;
(12) Academic early warning
Calculating the records of the students on the academic early warning relevant places during the school period by 10 points of full scale, and weighting and calculating the deduction value according to the times and the severity of the academic places (academic warning and trial reading);
finally, normalizing the index calculation result to be between 0 and 1, and rearranging the index into a key-value format according to the student ID number, namely, the student ID is followed by all index quantization results of the student; and based on the index table, extracting the student portrait label according to the value range setting.
6. A career-oriented rating method as claimed in claim 5, wherein the learning habit principal component analysis algorithm is described as follows:
inputting: sample set D = { x 1 ,x 2 ,.......,x m }；
Low dimensional spatial dimension d'
The process is as follows:
all samples were normalized:
calculating the covariance matrix XX of the samples T ；
For covariance matrix XX T Decomposing the characteristic value;
taking the eigenvector w corresponding to the largest d' eigenvalues 1 ，w 2 ，...,w d' ；
And (3) outputting: projection matrixW*＝(w 1 ，w 2 ，...,w d' )；
And (4) obtaining a dimensionality reduction matrix according to the feature vector mapping, namely obtaining an index value by integrating the three indexes.
7. The career evaluation-oriented rating method according to claim 6, wherein in step S5, when the indicator evaluation values are comprehensively calculated to obtain the career score, the relative importance, namely the weight, of each indicator is determined.
8. A career-oriented rating system according to claims 1-7, wherein the system comprises:
the index system layer comprises a core literacy module and a comprehensive literacy module and is used for evaluating the quality of the student's career; forming a learning career evaluation index system under a core literacy vision field, and specifically setting five evaluation dimensions including ideness, learning performance, physical and mental health, academic performance and competence literacy;
the data practice layer comprises a data acquisition module, a characteristic engineering module and a weight design module, wherein the data acquisition module acquires the basic information of students of a university corresponding to a school year and the daily behavior records of the students by using a database interface; the characteristic engineering module is used for carrying out characteristic linear construction on the basic attribute data set, extracting a fact label, and then obtaining a model label through rule judgment and model calculation; the weight design module is used for establishing a data mapping relation between the evaluation index and the model label according to the constructed multi-dimensional native career evaluation index system;
and the digital portrait layer is used for forming a comprehensive score of the lifetime quality and forming a student portrait label system.
9. The career evaluation oriented rating system of claim 8, wherein the data collection module data set is mainly derived from student campus card consumption, access control record of each site and educational information systems; the method comprises the steps of preprocessing the information of the primary data of the college students, including data cleaning, missing value filling and format conversion, and forming a standard basic attribute data set for data mining.
The career assessment-oriented rating system of claim 8, wherein the digital image layer comprises a career score rating module and a student image tag system building module; the career score rating module performs weighted calculation according to a plurality of dimensions of career comprehensive evaluation on the basis of evaluation indexes and index weights constructed by the data practice layer to form comprehensive scores and percentage ranks of career quality; the student portrait label system construction module constructs a student portrait label system by screening and judging rules of model labels extracted from the data practice layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211363175.XA CN115965175A (en) | 2022-11-02 | 2022-11-02 | Skyline evaluation-oriented rating method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211363175.XA CN115965175A (en) | 2022-11-02 | 2022-11-02 | Skyline evaluation-oriented rating method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115965175A true CN115965175A (en) | 2023-04-14 |
Family
ID=87351818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211363175.XA Pending CN115965175A (en) | 2022-11-02 | 2022-11-02 | Skyline evaluation-oriented rating method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115965175A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342342A (en) * | 2023-05-25 | 2023-06-27 | 深圳市捷易科技有限公司 | Student behavior detection method, electronic device and readable storage medium |
| CN116956181A (en) * | 2023-09-20 | 2023-10-27 | 云南师范大学 | Student comprehensive evaluation method based on digital portrait |
-
2022
- 2022-11-02 CN CN202211363175.XA patent/CN115965175A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342342A (en) * | 2023-05-25 | 2023-06-27 | 深圳市捷易科技有限公司 | Student behavior detection method, electronic device and readable storage medium |
| CN116956181A (en) * | 2023-09-20 | 2023-10-27 | 云南师范大学 | Student comprehensive evaluation method based on digital portrait |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107230174B (en) | Online interactive learning system and method based on network | |
| Barredo et al. | Modelling future urban scenarios in developing countries: an application case study in Lagos, Nigeria | |
| Miller | Species distribution models: Spatial autocorrelation and non-stationarity | |
| Kennedy | Oh no! I got the wrong sign! What should I do? | |
| CN115965175A (en) | Skyline evaluation-oriented rating method and system | |
| Weaver | The press and government restriction: A cross-national study over time | |
| CN111709575A (en) | Academic achievement prediction method based on C-LSTM | |
| Härdle et al. | Introduction to statistics: using interactive MM* Stat elements | |
| CN112052396A (en) | Course matching method, system, computer equipment and storage medium | |
| Hoffmeyer-Zlotnik et al. | Sociodemographic questionnaire modules for comparative social surveys | |
| Blasques et al. | Dynamic factor models with clustered loadings: Forecasting education flows using unemployment data | |
| Zhang et al. | Enabling rapid large-scale seismic bridge vulnerability assessment through artificial intelligence | |
| Fotheringham et al. | Multiscale Geographically Weighted Regression: Theory and Practice | |
| Kocakoç et al. | Exploring decision rules for election results by classification trees | |
| Faigel | Methods and issues in collection evaluation today | |
| Chou et al. | Spatial knowledge databases as applied to the detection of changes in urban land use | |
| CN112598944B (en) | Intelligent English teaching system | |
| Manhães et al. | Evaluating performance and dropouts of undergraduates using educational data mining | |
| Ngo et al. | Exploration and integration of job portals in Vietnam | |
| Symeonaki et al. | Assessing the intergenerational educational mobility in European countries based on ESS data: 2002–2016 | |
| Diylami et al. | Designing educators’ information literacy model at the agricultural technical schools in Mazandaran province, Iran | |
| Van Thiel et al. | Development of a testing service system | |
| Jasim | Elements and Methodologies for Accomplishing Scientific Research and Studies (With Case Studies) | |
| Xiaoguo | Analysis and Research on Ideological and Political Learning Outcomes of College Students Based on Education Data Mining | |
| Boit | Socio-Economic Distribution and Higher Education Participation of Students in Kenya |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |