CN110245826A - A kind of data analysing method and device - Google Patents
A kind of data analysing method and device Download PDFInfo
- Publication number
- CN110245826A CN110245826A CN201910374337.1A CN201910374337A CN110245826A CN 110245826 A CN110245826 A CN 110245826A CN 201910374337 A CN201910374337 A CN 201910374337A CN 110245826 A CN110245826 A CN 110245826A
- Authority
- CN
- China
- Prior art keywords
- data
- student
- factor
- evaluated
- analysis model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 114
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000007405 data analysis Methods 0.000 claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000000007 visual effect Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 20
- 239000000284 extract Substances 0.000 claims description 14
- 241001269238 Data Species 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 11
- 238000004445 quantitative analysis Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 230000036541 health Effects 0.000 claims description 7
- 238000007477 logistic regression Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 230000003014 reinforcing effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000005728 strengthening Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000012790 confirmation Methods 0.000 description 6
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000004630 mental health Effects 0.000 description 4
- 230000009323 psychological health Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013502 data validation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Technology (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a kind of data analysing method and devices, and the present invention relates to field of artificial intelligence, method includes: the multi-dimensional data for obtaining student to be evaluated during school, and multi-dimensional data includes numerical value class data and text class data;Quantify multi-dimensional data using different data analysis tools, obtains the score value of multiple impact factors;Creation analysis model, and analysis model is trained using the impact factor of the Ontario Scholar prestored;By in the analysis model after the impact factor input training of student to be evaluated, the weak factor of the student to be evaluated of analysis model output is obtained, the weak factor is at least one of multiple impact factors;It is called the specific aim corresponding with the weak factor prestored to strengthen according to the weak factor to suggest;Strengthened based on multiple impact factors, the weak factor and specific aim and suggests generating Visual evaluation information.The embodiment of the present invention is able to solve the problem low by manual analysis mode accuracy of student data in the prior art.
Description
[technical field]
The present invention relates to field of artificial intelligence more particularly to a kind of data analysing methods and device.
[background technique]
Currently, school in educational management, lacks student and portrays assessment comprehensively, learning ability is only focused on more, pay close attention to face
It is single, the learning ability of student is evaluated unilaterally, is easy so that student loses the confidence, student is also difficult to self-recognition to weakness
, pointedly strengthen the weak item of oneself.Therefore, it is necessary to comprehensively collect the data of student, student is analyzed by data
Various aspects learning ability, help student.It is general now by teacher according to the learning ability of student performance subjective analysis student,
This manual analysis mode accuracy is low.
[summary of the invention]
In view of this, the embodiment of the invention provides a kind of data analysing method and devices, to solve in the prior art
The student data problem low by manual analysis mode accuracy.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of data analysing method, the method
Include:
Multi-dimensional data of the student to be evaluated during school is obtained, the multi-dimensional data includes numerical value class data and text
Class data;Using multi-dimensional data described in different analysis model quantitative analysis, the score value of multiple impact factors is obtained;Building point
Model is analysed, and the analysis model is trained using the impact factor of the Ontario Scholar prestored;By the student to be evaluated
Impact factor input training after the analysis model in, obtain the thin of the student to be evaluated of analysis model output
The weak factor, the weakness factor is at least one of multiple described impact factors;It is prestored according to the weak factor calling
Specific aim corresponding with the weakness factor, which is strengthened, suggests;Based on multiple impact factors, the weak factor and described
Specific aim strengthens the Visual evaluation information for suggesting generating the student to be evaluated.
Further, described using multi-dimensional data described in different analysis model quantitative analysis, obtain multiple influences because
The score value of son, comprising: the numerical value of the numerical value class data in the multi-dimensional data is extracted respectively, the numerical value class data
Impact factor includes and physiological characteristic, achievement, ranking, contest score, attendance, sports achievement, interpersonal, family's care degree and society
The relevant impact factor of activity;Using the numerical value of extraction as the score value of the impact factor.
Further, described using multi-dimensional data described in different analysis model quantitative analysis, obtain multiple influences because
The score value of son, comprising: the text class data are subjected to word segmentation processing, wherein the impact factor of the text class data includes
With household register, nationality, birthplace, home background, outlook on life, values, learning ability, thinking ability, health, sport speciality
Relevant impact factor;The word of the impact factor each of is obtained to the word segmentation processing based on keyword weight computational algorithm
It converges and successively carries out weight evaluation and be ranked up according to the weighted value of the vocabulary;Weight selection value is in the top from big to small
The vocabulary of quantity is set as Feature Words;The Feature Words are matched with preset Feature Words-score table, obtain the spy
Levy the score value of word;The score value of multiple Feature Words is added up into the score value as the impact factor.
Further, the multi-dimensional data for obtaining student to be evaluated during school, comprising: obtained by preset interface
Take the student data of each system in school;The system comprises attendance checking system, library's entrance guard system, examine business system, campus
Hospital system, school lunch service's system, school's supermarket system, student's activities management system;According to the identity of the student to be evaluated
Information filters out the target data of the student to be evaluated from each student data;Each target data is carried out
Cleaning, filtering do not meet the data of preset rules;Cleaned multiple target datas are subjected to standardization processing, are gone
Except the Outlier Data for deviateing preset interval range;Using multiple target datas after standardization processing as the student to be evaluated
Multi-dimensional data.
Further, creation analysis model, and using the impact factor of Ontario Scholar prestored to the analysis model into
Row training, comprising: obtain the impact factor of the Ontario Scholar prestored, and using the score value of the impact factor of the Ontario Scholar as
Training data;The training data is inputted into the analysis model, wherein the convolutional neural networks in the analysis model extract
The score value of each impact factor;The score value of same impact factor from multiple Ontario Scholars is clustered, obtains one
A aggregate of data;The center score value for identifying the aggregate of data, using the center score value as the same influence of Ontario Scholar because
The ideal score value of son.
Further, by the analysis model after the impact factor input training of the student to be evaluated, institute is obtained
State analysis model output the student to be evaluated the weak factor, comprising: by the influence to be evaluated of the student to be evaluated because
The analysis model after son input training, wherein the convolutional neural networks of the analysis model extract described to be evaluated
The score value of impact factor;The number of the impact factor of the score value and the Ontario Scholar of the impact factor to be evaluated will be extracted
It is compared according to the center score value of cluster;When the score value of the impact factor to be evaluated deviates the center score value preset range,
Confirm the impact factor to be evaluated of the student to be evaluated for the weak factor.
Further, described using multi-dimensional data described in different analysis model quantitative analysis, obtain multiple influences because
After the score value of son, the method also includes: the multiple impact factors extracted described in input in Xiang Biye whereabouts prediction model,
So that the graduation whereabouts prediction model obtains institute according to any one method in logistic regression, decision tree, random forest
State the graduation whereabouts classification of student to be evaluated.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of data analysis set-up, described device
It include: acquiring unit, for obtaining multi-dimensional data of the student to be evaluated during school, the multi-dimensional data includes numerical value class
Data and text class data;Analytical unit, for obtaining more using multi-dimensional data described in different analysis model quantitative analysis
The score value of a impact factor;Construction unit is used for creation analysis model, and using the impact factor of the Ontario Scholar prestored to institute
Analysis model is stated to be trained;Input unit, for by described in after the input training of the impact factor of the student to be evaluated points
It analyses in model, obtains the weak factor of the student to be evaluated of the analysis model output, the weakness factor is multiple institutes
State at least one of impact factor;Call unit is prestoring with the weak factor for being called according to the weak factor
Corresponding specific aim, which is strengthened, suggests;Generation unit, for based on multiple impact factors, the weak factor and the needle
Strengthen the Visual evaluation information for suggesting generating the student to be evaluated to property.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of computer non-volatile memories are situated between
Matter, the storage medium include the program of storage, control equipment where the storage medium in described program operation and execute
The data analysing method stated.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of computer equipment, including storage
Device, processor and storage in the memory and the computer program that can run on the processor, the processor
The step of above-mentioned data analysing method is realized when executing the computer program.
In the present solution, more quickly assessing student's in all directions by the multi-dimensional data of big data analysis student
Performance;And the weak factor for extracting student is analyzed, specific aim is given for the weak factor and strengthens suggestion, facilitates students ' understanding to certainly
Oneself shortcoming reduces teacher's subjectivity and conjestures, evaluates student fair and justly, find the weak spot of student, to provide more
Good reinforcing suggestion, and then the precision of analysis of student data is improved, reduce subjective one-sided.
[Detailed description of the invention]
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this field
For those of ordinary skill, without any creative labor, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow chart of optional data analysing method provided in an embodiment of the present invention;
Fig. 2 is a kind of schematic diagram of optional data analysis set-up provided in an embodiment of the present invention;
Fig. 3 is a kind of schematic diagram of optional computer equipment provided in an embodiment of the present invention.
[specific embodiment]
For a better understanding of the technical solution of the present invention, being retouched in detail to the embodiment of the present invention with reference to the accompanying drawing
It states.
It will be appreciated that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
Its embodiment, shall fall within the protection scope of the present invention.
The term used in embodiments of the present invention is only to be not intended to be limiting merely for for the purpose of describing particular embodiments
The present invention.In the embodiment of the present invention and the "an" of singular used in the attached claims, " described " and "the"
It is also intended to including most forms, unless the context clearly indicates other meaning.
It should be appreciated that term "and/or" used herein is only a kind of incidence relation for describing affiliated partner, indicate
There may be three kinds of relationships, for example, A and/or B, can indicate: individualism A, exist simultaneously A and B, individualism B these three
Situation.In addition, character "/" herein, typicallys represent the relationship that forward-backward correlation object is a kind of "or".
It will be appreciated that though terminal may be described using term first, second, third, etc. in embodiments of the present invention,
But these terminals should not necessarily be limited by these terms.These terms are only used to for terminal being distinguished from each other out.For example, not departing from the present invention
In the case where scope of embodiments, first terminal can also be referred to as second terminal, and similarly, second terminal can also be referred to as
One terminal.
Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination " or " in response to detection ".Similarly, depend on context, phrase " if it is determined that " or " if detection
(condition or event of statement) " can be construed to " when determining " or " in response to determination " or " when the detection (condition of statement
Or event) when " or " in response to detection (condition or event of statement) ".
Fig. 1 is a kind of flow chart of data analysing method according to an embodiment of the present invention, as shown in Figure 1, this method comprises:
Step S101, obtains multi-dimensional data of the student to be evaluated during school, and multi-dimensional data includes numerical value class data
With text class data;
Step S102 quantifies multi-dimensional data using different data analysis tools, obtains the score value of multiple impact factors;
Step S103, creation analysis model, and analysis model is instructed using the impact factor of the Ontario Scholar prestored
Practice;
It is defeated to obtain analysis model by the analysis model after the impact factor input training of student to be evaluated by step S104
The weak factor of student to be evaluated out, the weak factor are at least one of multiple impact factors;
Step S105 calls the specific aim corresponding with the weak factor prestored to strengthen according to the weak factor and suggests;
Step S106, strengthened based on multiple impact factors, the weak factor and specific aim suggest generating student to be evaluated can
Depending on changing evaluation information.
In the present solution, more quickly assessing student's in all directions by the multi-dimensional data of big data analysis student
Performance;And the weak factor for extracting student is analyzed, specific aim is given for the weak factor and strengthens suggestion, facilitates students ' understanding to certainly
Oneself shortcoming reduces teacher's subjectivity and conjestures, evaluates student fair and justly, find the weak spot of student, to provide more
Good reinforcing suggestion, and then the precision of analysis of student data is improved, reduce subjective one-sided.
Wherein, multi-dimensional data be roughly divided into from content the basic data of student, moral, intellectual and physical education data, performance force data this
Three classes.
Optionally, quantify multi-dimensional data using different data analysis tools, obtain the score value of multiple impact factors, wrap
It includes:
The numerical value of the numerical value class data in multi-dimensional data is extracted respectively, and the impact factor of numerical value class data includes and physiology
Feature, achievement, ranking, contest score, attendance, sports achievement, interpersonal, family's care degree and the relevant influence of social activities because
Son;
Using the numerical value of extraction as the score value of impact factor.
Such as: physiological characteristic includes height, weight, heart rate, blood pressure etc.;Achievement include student's all types course at
Achievement;Contest score, which can be, participates in olympic math match achievement, whole city's chemistry competition achievement etc.;Attendance can be to be late, ask
Number that is false, leaving early;Sports achievement can be the duration of 400-Meter Dash step, the number of sit-ups, the height of high jump, into fortune
The frequency etc. in dynamic place;The interpersonal positive rating that can be classmate;Family's care degree can be the visit number of its household;Society is living
It is dynamic to can be the number participated in social activity.It is to be appreciated that numerical value class data are one for can directly being embodied with numerical value
The data of impact factor.
In one embodiment, each impact factor and its score value extracted is stored in pre- in the form of key-value pair
If tables of data in, to facilitate the data processing counted, excavated, predicted etc..
Optionally, quantify multi-dimensional data using different data analysis tools, obtain the score value of multiple impact factors, wrap
It includes:
Text class data are subjected to word segmentation processing, wherein the impact factor of text class data includes household register, nationality, birth
Ground, home background, outlook on life, values, learning ability, thinking ability, health, sport speciality;Based on keyword weight
The vocabulary for each impact factor that computational algorithm obtains word segmentation processing successively carries out weight evaluation and according to the weighted value of vocabulary
It is ranked up;The vocabulary of weight selection value setting quantity in the top from big to small is as Feature Words;By Feature Words and preset
Feature Words-score table matched, obtain the score value of Feature Words;The score value of multiple Feature Words is added up as impact factor
Score value.
Wherein, keyword weight computational algorithm uses tf-idf (Term Frequency-Inverse Document
Frequency, the inverse text frequency of word frequency -) algorithm.
It is to be appreciated that text class data refer to the impact factor of plain text, such as values, teacher can be to the valence of student
Value, which is seen, carries out verbal description, and student can also summarize the values of oneself with self.Such as: values for it is modest, have love, make great efforts,
Innovation.Obtained " modest ", " having love " " effort " " innovation " are so segmented as Feature Words directly to carry out with Feature Words-score table
Matching, the score value for obtaining values this impact factor is 8 points.Such as learning ability this impact factor, the comment of teacher are
" can quickly absorb the thinking of solving a problem of teacher, be good at summarizing, and draw inferences about other cases from one instance, there is stronger academic ability ", then according to power
Weight values obtain " relatively strong ", " quick ", " absorption " " summary " these Feature Words after being ranked up, by feature word Feature Words-point
After value table is matched, the score value for obtaining learning ability this impact factor is 8 points.When national this text class influence because
National (such as: Han nationality) is directly carried out Feature Words-score value as Feature Words and matched by the period of the day from 11 p.m. to 1 a.m.
Optionally, quantify multi-dimensional data using different data analysis tools, obtain the score value of multiple impact factors, wrap
It includes:
Text class data are input to preset data analysis tool;Obtain the numeralization mark of data analysis tool output
Label.For example, by the description text input psychological health analysis model to be evaluated of the mental health about student in education administration system
In, psychological health analysis model is obtained by the description sample training of a large amount of mental healths, description text to be evaluated can be analyzed,
Obtain the numeralization label of description text to be evaluated.Training logistic regression can be used, support vector machines, determine by analyzing quantitative model
The analysis methods such as plan tree, random forest.
Similarly, analysis quantification tool further includes outlook on life analysis model, values analysis model, learning ability analysis mould
Type, thinking ability analysis model, health analysis model, sport speciality analysis model, interpersonal analysis model.By corresponding
Text class data are switched to the label that quantizes by analysis quantitative model.
In one embodiment, each impact factor and its score value extracted stores equally in the form of key-value pair
In preset tables of data, to facilitate the data processing counted, excavated, predicted etc..
Optionally, multi-dimensional data of the student to be evaluated during school is obtained, comprising: school is obtained by preset interface
In each system student data;System includes attendance checking system, library's entrance guard system, examines business system, campus hospital system, learns
School dining room system, school's supermarket system, student's activities management system;According to the identity information of student to be evaluated from each number of students
The target data of student to be evaluated is filtered out in;Each target data is cleaned, filtering does not meet the number of preset rules
According to;Cleaned multiple target datas are subjected to standardization processing, removal deviates the Outlier Data of preset interval range;
Using multiple target datas after standardization processing as the multi-dimensional data of student to be evaluated.
Such as: the physiological characteristic data of the student are as follows: height 175cm, weight 65kg, 75 beats/min of heart rate, and 5 surveys
In test result, 4 times are height 175cm, and 1 time is height 170cm, and height data (170cm) therein deviates preset section model
It encloses, such as the pre-set interval of height is 175 ± 1cm, has deviated from preset interval range, then it should be by this height data
Removal.
In one embodiment, the identity information of student to be evaluated includes student name, student's identity card number, identification card number
Deng.
Optionally, creation analysis model, and analysis model is trained using the impact factor of the Ontario Scholar prestored,
It include: the impact factor for the Ontario Scholar that acquisition prestores, and using the score value of the impact factor of Ontario Scholar as training data;It will
Training data inputs analysis model, wherein the convolutional neural networks in analysis model extract the score value of each impact factor;In the future
It is clustered from the score value of the same impact factor of multiple Ontario Scholars, obtains an aggregate of data;Identify the center point of aggregate of data
Value, using center score value as the ideal score value of the same impact factor of Ontario Scholar.
It is to be appreciated that using the data of the impact factor of some Ontario Scholars as training basis, so that analysis model can
Repeatedly learnt with passing through, learn the feature of the impact factor of Ontario Scholar, and in the analysis model as the storage of ideal score value,
In, ideal score value is a preset score range, such as each subject achievement 85~90/.Here Ontario Scholar can be with
It is that true some Ontario Scholars represent in school, is also possible to a virtual object, such as the Ontario Scholar that teacher approves
The characteristic of each impact factor.
Optionally, by the analysis model after the impact factor input training of student to be evaluated, analysis model output is obtained
Student to be evaluated the weak factor, comprising: by the analysis model after the input training of the impact factor to be evaluated of student to be evaluated,
Wherein, the convolutional neural networks of analysis model extract the score value of impact factor to be evaluated;Point of impact factor to be evaluated will be extracted
Value is compared with the center score value of the aggregate of data of the impact factor of Ontario Scholar;In the score value of impact factor to be evaluated deviates
When heart score value preset range, confirm the impact factor to be evaluated of student to be evaluated for the weak factor.
By the way that the impact factor of student to be evaluated is all input to analysis model, analysis model can be analyzed by data and
Comparison obtains the weak factor of this student.
Optionally, using different analysis model quantitative analysis multi-dimensional datas, obtain multiple impact factors score value it
Afterwards, method further include: the multiple impact factors extracted are inputted in Xiang Biye whereabouts prediction model, so that graduation whereabouts prediction
Model obtains the graduation whereabouts classification of student to be evaluated according to any one method in logistic regression, decision tree, random forest.
In one embodiment, whereabouts prediction model uses Logic Regression Models, the learning procedure of whereabouts prediction model
It include: to obtain the multi-dimensional data sample of multiple students, and extract the score value of the impact factor in each sample;Compare various dimensions
The score value difference of multiple impact factors between data sample;Multi-dimensional data sample is divided into training set and verifying collection, will be instructed
The score value difference for practicing multiple impact factors of the multi-dimensional data sample of collection is used as predictive variable, graduation whereabouts variable in response
Establish whereabouts prediction model.
In one embodiment, the prediction of whereabouts prediction model is verified using the multi-dimensional data sample that verifying is concentrated
The degree of fitting of whereabouts prediction model is assessed in accuracy.
The embodiment of the invention provides a kind of data analysis set-up, the device is for executing above-mentioned data analysing method, such as
Shown in Fig. 2, which includes: acquiring unit 10, analytical unit 20, construction unit 30, input unit 40, call unit 50, life
At unit 60.
Acquiring unit 10, for obtaining multi-dimensional data of the student to be evaluated during school, multi-dimensional data includes numerical value
Class data and text class data;
Analytical unit 20 obtains multiple impact factors for quantifying multi-dimensional data using different data analysis tools
Score value;
Construction unit 30 is used for creation analysis model, and using the impact factor of the Ontario Scholar prestored to analysis model
It is trained;
Input unit 40, for obtaining analysis in the analysis model after the impact factor input training by student to be evaluated
The weak factor of the student to be evaluated of model output, the weak factor are at least one of multiple impact factors;
Call unit 50, for calling the specific aim corresponding with the weak factor prestored reinforcing to build according to the weak factor
View;
Generation unit 60 suggests generating to be evaluated for strengthening based on multiple impact factors, the weak factor and specific aim
Raw Visual evaluation information.
In the present solution, more quickly assessing student's in all directions by the multi-dimensional data of big data analysis student
Performance;And the weak factor for extracting student is analyzed, specific aim is given for the weak factor and strengthens suggestion, facilitates students ' understanding to certainly
Oneself shortcoming reduces teacher's subjectivity and conjestures, evaluates student fair and justly, find the weak spot of student, to provide more
Good reinforcing suggestion, and then the precision of analysis of student data is improved, reduce subjective one-sided.
Wherein, multi-dimensional data be roughly divided into from content the basic data of student, moral, intellectual and physical education data, performance force data this
Three classes.
Optionally, analytical unit 20 includes the first extraction subelement, the first confirmation subelement.
First extracts subelement, for extracting the numerical value of the numerical value class data in multi-dimensional data, numerical value class data respectively
Impact factor include and physiological characteristic, achievement, ranking, contest score, attendance, sports achievement, interpersonal, family's care degree and society
It can the relevant impact factor of activity;
First confirmation subelement, score value of the numerical value as impact factor for that will extract.
Such as: physiological characteristic includes height, weight, heart rate, blood pressure etc.;Achievement include student's all types course at
Achievement;Contest score, which can be, participates in olympic math match achievement, whole city's chemistry competition achievement etc.;Attendance can be to be late, ask
Number that is false, leaving early;Sports achievement can be the duration of 400-Meter Dash step, the number of sit-ups, the height of high jump, into fortune
The frequency etc. in dynamic place;The interpersonal positive rating that can be classmate;Family's care degree can be the visit number of its household;Society is living
It is dynamic to can be the number participated in social activity.It is to be appreciated that numerical value class data are one for can directly being embodied with numerical value
The data of impact factor.
In one embodiment, each impact factor and its score value extracted is stored in pre- in the form of key-value pair
If tables of data in, to facilitate the data processing counted, excavated, predicted etc..
Optionally, analytical unit 20 include processing subelement, evaluation subelement, second confirmation subelement, coupling subelement,
Summarize subelement.
Subelement is handled, for text class data to be carried out word segmentation processing, wherein the impact factor of text class data includes
Household register, nationality, birthplace, home background, outlook on life, values, learning ability, thinking ability, health, sport speciality;
Evaluate subelement, the vocabulary of each impact factor for being obtained based on keyword weight computational algorithm to word segmentation processing successively into
Row weight is evaluated and is ranked up according to the weighted value of vocabulary;Second confirmation subelement, is arranged from big to small for weight selection value
The vocabulary of the forward setting quantity of name is as Feature Words;Coupling subelement is used for Feature Words and preset Feature Words-score table
It is matched, obtains the score value of Feature Words;Summarize subelement, for adding up the score value of multiple Feature Words as impact factor
Score value.
Wherein, keyword weight computational algorithm uses tf-idf (Term Frequency-Inverse Document
Frequency, the inverse text frequency of word frequency -) algorithm.
It is to be appreciated that text class data refer to the impact factor of plain text, such as values, teacher can be to the valence of student
Value, which is seen, carries out verbal description, and student can also summarize the values of oneself with self.Such as: values for it is modest, have love, make great efforts,
Innovation.Obtained " modest ", " having love " " effort " " innovation " are so segmented as Feature Words directly to carry out with Feature Words-score table
Matching, the score value for obtaining values this impact factor is 8 points.Such as learning ability this impact factor, the comment of teacher are
" can quickly absorb the thinking of solving a problem of teacher, be good at summarizing, and draw inferences about other cases from one instance, there is stronger academic ability ", then according to power
Weight values obtain " relatively strong ", " quick ", " absorption " " summary " these Feature Words after being ranked up, by feature word Feature Words-point
After value table is matched, the score value for obtaining learning ability this impact factor is 8 points.When national this text class influence because
National (such as: Han nationality) is directly carried out Feature Words-score value as Feature Words and matched by the period of the day from 11 p.m. to 1 a.m.
Optionally, analytical unit 20 further includes input subelement and acquisition subelement.
Subelement is inputted, for text class data to be input to preset data analysis tool;Subelement is obtained, for obtaining
The numeralization label for taking data analysis tool to export.For example, by the to be evaluated of the mental health about student in education administration system
It describes in text input psychological health analysis model, the description sample training that psychological health analysis model passes through a large amount of mental healths
It obtains, description text to be evaluated can be analyzed, obtain the numeralization label of description text to be evaluated.Analysis quantitative model can be adopted
With analysis methods such as training logistic regression, support vector machines, decision tree, random forests.
Similarly, analysis quantification tool further includes outlook on life analysis model, values analysis model, learning ability analysis mould
Type, thinking ability analysis model, health analysis model, sport speciality analysis model, interpersonal analysis model.By corresponding
Text class data are switched to the label that quantizes by analysis quantitative model.
In one embodiment, each impact factor and its score value extracted stores equally in the form of key-value pair
In preset tables of data, to facilitate the data processing counted, excavated, predicted etc..
Optionally, acquiring unit 10 include second obtain subelement, screening subelement, filtering subelement, processing subelement,
Data validation subelement.
Second obtains subelement, for obtaining the student data of each system in school, system packet by preset interface
Attendance checking system, library's entrance guard system are included, business system is examined, campus hospital system, school lunch service's system, school's supermarket system, learns
Raw event management system;Subelement is screened, for filtering out from each student data according to the identity information of student to be evaluated
The target data of student to be evaluated;Subelement is filtered, for cleaning each target data, filtering does not meet preset rules
Data;Subelement is handled, for cleaned multiple target datas to be carried out standardization processing, removal deviates preset
The Outlier Data of interval range;Data validation subelement, for using multiple target datas after standardization processing as to be evaluated
The multi-dimensional data of student.
Such as: the physiological characteristic data of the student are as follows: height 175cm, weight 65kg, 75 beats/min of heart rate, and 5 surveys
In test result, 4 times are height 175cm, and 1 time is height 170cm, and height data (170cm) therein deviates preset section model
It encloses, such as the pre-set interval of height is 175 ± 1cm, has deviated from preset interval range, then it should be by this height data
Removal.
In one embodiment, the identity information of student to be evaluated includes student name, student's identity card number, identification card number
Deng.
Optionally, construction unit 30 includes that third obtains subelement, the second input subelement, cluster subelement, identification
Unit.
Third obtains subelement, for obtaining the impact factor of the Ontario Scholar prestored, and by the influence of Ontario Scholar because
The score value of son is as training data;Second input subelement, for training data to be inputted analysis model, wherein analysis model
In convolutional neural networks extract the score value of each impact factor;Subelement is clustered, for will be from the same of multiple Ontario Scholars
The score value of one impact factor is clustered, and an aggregate of data is obtained;Identify subelement, for identification the center score value of aggregate of data,
Using center score value as the ideal score value of the same impact factor of Ontario Scholar.
It is to be appreciated that using the data of the impact factor of some Ontario Scholars as training basis, so that analysis model can
Repeatedly learnt with passing through, learn the feature of the impact factor of Ontario Scholar, and in the analysis model as the storage of ideal score value,
In, ideal score value is a preset score range, such as each subject achievement 85~90/.Here Ontario Scholar can be with
It is that true some Ontario Scholars represent in school, is also possible to a virtual object, such as the Ontario Scholar that teacher approves
The characteristic of each impact factor.
Optionally, input unit 40 includes third input subelement, comparing subunit, third confirmation subelement.
Third inputs subelement, for the impact factor to be evaluated of student to be evaluated to be inputted to the analysis model after training,
Wherein, the convolutional neural networks of analysis model extract the score value of impact factor to be evaluated;Comparing subunit, it is to be evaluated for that will extract
The center score value of the aggregate of data of the impact factor of the score value and Ontario Scholar of valence impact factor is compared;Third confirmation is single
Member, for confirming the shadow to be evaluated of student to be evaluated when the score value of impact factor to be evaluated deviates center score value preset range
Ringing the factor is the weak factor.
By the way that the impact factor of student to be evaluated is all input to analysis model, analysis model can be analyzed by data and
Comparison obtains the weak factor of this student.
Optionally, using different analysis model quantitative analysis multi-dimensional datas, obtain multiple impact factors score value it
Afterwards, method further include: the multiple impact factors extracted are inputted in Xiang Quxiang prediction model, so that graduation whereabouts prediction model
The graduation whereabouts classification of student to be evaluated is obtained according to any one method in logistic regression, decision tree, random forest.
The embodiment of the invention provides a kind of computer non-volatile memory medium, storage medium includes the program of storage,
Wherein, when program is run, equipment where control storage medium executes following steps: it is more during school to obtain student to be evaluated
Dimension data, multi-dimensional data include numerical value class data and text class data;Quantify multidimensional using different data analysis tools
Degree evidence obtains the score value of multiple impact factors;Creation analysis model, and using the impact factor of Ontario Scholar prestored to point
Analysis model is trained;By in the analysis model after the impact factor input training of student to be evaluated, analysis model output is obtained
Student to be evaluated the weak factor, the weak factor is at least one of multiple impact factors;It is called according to the weak factor pre-
The specific aim corresponding with the weak factor deposited, which is strengthened, suggests;It is built based on multiple impact factors, the weak factor and specific aim reinforcing
View generates the Visual evaluation information of student to be evaluated.
Optionally, when program is run, equipment where control storage medium executes following steps: extracting multidimensional degree respectively
The numerical value of numerical value class data in, the impact factor of numerical value class data include with physiological characteristic, achievement, ranking, contest score,
Attendance, sports achievement, interpersonal, family's care degree and the relevant impact factor of social activities;Using the numerical value of extraction as influence because
The score value of son.
Optionally, when program is run, equipment where control storage medium executes following steps: text class data are carried out
Word segmentation processing, wherein the impact factor of text class data includes and household register, nationality, birthplace, home background, outlook on life, value
Sight, learning ability, thinking ability, health, the relevant impact factor of sport speciality;Based on keyword weight computational algorithm pair
The vocabulary for each impact factor that word segmentation processing obtains successively carries out weight evaluation and is ranked up according to the weighted value of vocabulary;Choosing
The vocabulary of weighting weight values setting quantity in the top from big to small is as Feature Words;By Feature Words and preset Feature Words-point
Value table is matched, and the score value of Feature Words is obtained;The score value of multiple Feature Words is added up into the score value as impact factor.
Optionally, when program is run, equipment where control storage medium executes following steps: being obtained by preset interface
Take the student data of each system in school;System includes attendance checking system, library's entrance guard system, examines business system, campus hospital
System, school lunch service's system, school's supermarket system, student's activities management system;According to the identity information of student to be evaluated from every
The target data of student to be evaluated is filtered out in a student data;Each target data is cleaned, filtering does not meet default
The data of rule;Cleaned multiple target datas are subjected to standardization processing, removal deviates preset interval range
Outlier Data;Using multiple target datas after standardization processing as the multi-dimensional data of student to be evaluated.
Optionally, when program is run, equipment where control storage medium executes following steps: obtaining outstanding prestored
Raw impact factor, and using the score value of the impact factor of Ontario Scholar as training data;Training data is inputted into analysis model,
Wherein, the convolutional neural networks in analysis model extract the score value of each impact factor;It will be from the same of multiple Ontario Scholars
The score value of impact factor is clustered, and an aggregate of data is obtained;The center score value for identifying aggregate of data, using center score value as outstanding
The ideal score value of the same impact factor of student.
Optionally, when program is run, equipment where control storage medium executes following steps: by student to be evaluated to
Analysis model after evaluating impact factor input training, wherein the convolutional neural networks of analysis model extract influence to be evaluated because
The score value of son;The center score value that the aggregate of data of the impact factor of the score value and Ontario Scholar of impact factor to be evaluated will be extracted carries out
Compare;When the score value of impact factor to be evaluated deviates center score value preset range, the influence to be evaluated of student to be evaluated is confirmed
The factor is the weak factor.
Fig. 3 is a kind of schematic diagram of computer equipment provided in an embodiment of the present invention.As shown in figure 3, the meter of the embodiment
Machine equipment 100 is calculated to include: processor 101, memory 102 and storage in the memory 102 and can run on processor 101
Computer program 103, processor 101 execute computer program 103 when realize embodiment in data analysing method, to avoid
It repeats, does not repeat one by one herein.Alternatively, realizing data analysis dress in embodiment when the computer program is executed by processor 101
The function of each model/unit does not repeat one by one herein in setting to avoid repeating.
Computer equipment 100 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.Computer equipment may include, but be not limited only to, processor 101, memory 102.It will be understood by those skilled in the art that Fig. 3
The only example of computer equipment 100 does not constitute the restriction to computer equipment 100, may include than illustrate it is more or
Less component perhaps combines certain components or different components, such as computer equipment can also be set including input and output
Standby, network access equipment, bus etc..
Alleged processor 101 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
Memory 102 can be the internal storage unit of computer equipment 100, for example, computer equipment 100 hard disk or
Memory.What memory 102 was also possible to be equipped on the External memory equipment of computer equipment 100, such as computer equipment 100 inserts
Connect formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash memory
Block (Flash Card) etc..Further, memory 102 can also both including computer equipment 100 internal storage unit or
Including External memory equipment.Memory 102 is for storing other program sum numbers needed for computer program and computer equipment
According to.Memory 102 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or group
Part can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown
Or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that device (can be personal computer, server or network equipment etc.) or processor (Processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (10)
1. a kind of data analysing method, which is characterized in that the described method includes:
Multi-dimensional data of the student to be evaluated during school is obtained, the multi-dimensional data includes numerical value class data and text class number
According to;
Quantify the multi-dimensional data using different data analysis tools, obtains the score value of multiple impact factors;
Creation analysis model, and the analysis model is trained using the impact factor of the Ontario Scholar prestored;
By in the analysis model after the impact factor input training of the student to be evaluated, the analysis model output is obtained
The student to be evaluated the weak factor, the weakness factor is at least one of multiple described impact factors;
It is called the specific aim corresponding with the weakness factor prestored to strengthen according to the weak factor to suggest;
Strengthened based on multiple impact factors, the weak factor and the specific aim and suggests generating the student's to be evaluated
Visual evaluation information.
2. the method according to claim 1, wherein described using more described in different analysis model quantitative analysis
Dimension data obtains the score value of multiple impact factors, comprising:
The numerical value of the numerical value class data in the multi-dimensional data, the impact factor packet of the numerical value class data are extracted respectively
It includes relevant to physiological characteristic, achievement, ranking, contest score, attendance, sports achievement, interpersonal, family's care degree and social activities
Impact factor;
Using the numerical value of extraction as the score value of the impact factor.
3. the method according to claim 1, wherein described using more described in different analysis model quantitative analysis
Dimension data obtains the score value of multiple impact factors, comprising:
The text class data are subjected to word segmentation processing, wherein the impact factor of the text class data includes and household register, the people
Race, birthplace, home background, outlook on life, values, learning ability, thinking ability, health, the relevant shadow of sport speciality
Ring the factor;
The vocabulary for each of obtaining the impact factor to the word segmentation processing based on keyword weight computational algorithm successively carries out
Weight is evaluated and is ranked up according to the weighted value of the vocabulary;
The vocabulary of weight selection value setting quantity in the top from big to small is as Feature Words;
The Feature Words are matched with preset Feature Words-score table, obtain the score value of the Feature Words;
The score value of multiple Feature Words is added up into the score value as the impact factor.
4. the method according to claim 1, wherein the multidimensional degree for obtaining student to be evaluated during school
According to, comprising:
The student data of each system in school is obtained by preset interface;The system comprises attendance checking systems, library's door
Access control system examines business system, campus hospital system, school lunch service's system, school's supermarket system, student's activities management system;
The mesh of the student to be evaluated is filtered out from each student data according to the identity information of the student to be evaluated
Mark data;
Each target data is cleaned, filtering does not meet the data of preset rules;
Cleaned multiple target datas are subjected to standardization processing, removal deviates peeling off for preset interval range
Data;
Using multiple target datas after standardization processing as the multi-dimensional data of the student to be evaluated.
5. the method according to claim 1, wherein creation analysis model, and utilizing the Ontario Scholar's prestored
Impact factor is trained the analysis model, comprising:
The impact factor of the Ontario Scholar prestored is obtained, and using the score value of the impact factor of the Ontario Scholar as training number
According to;
The training data is inputted into the analysis model, wherein the convolutional neural networks in the analysis model extract each
The score value of the impact factor;
The score value of same impact factor from multiple Ontario Scholars is clustered, an aggregate of data is obtained;
The center score value for identifying the aggregate of data, using the center score value as the reason of the same impact factor of Ontario Scholar
Think score value.
6. according to the method described in claim 5, it is characterized in that, by after the impact factor input training of the student to be evaluated
The analysis model in, obtain the weak factor of the student to be evaluated of analysis model output, comprising:
By the analysis model after the impact factor to be evaluated input training of the student to be evaluated, wherein the analysis mould
The convolutional neural networks of type extract the score value of the impact factor to be evaluated;
The center of the aggregate of data of the impact factor of the score value and the Ontario Scholar of the impact factor to be evaluated will be extracted
Score value is compared;
When the score value of the impact factor to be evaluated deviates the center score value preset range, confirm the student's to be evaluated
Impact factor to be evaluated is the weak factor.
7. the method according to claim 1, wherein described using more described in different analysis model quantitative analysis
Dimension data, after obtaining the score value of multiple impact factors, the method also includes:
The multiple impact factors extracted described in input into graduation whereabouts prediction model, so that the graduation whereabouts predicts mould
Type obtains the graduation whereabouts class of the student to be evaluated according to any one method in logistic regression, decision tree, random forest
Not.
8. a kind of data analysis set-up, which is characterized in that described device includes:
Acquiring unit, for obtaining multi-dimensional data of the student to be evaluated during school, the multi-dimensional data includes numerical value class
Data and text class data;
Analytical unit, for obtaining multiple impact factors using multi-dimensional data described in different analysis model quantitative analysis
Score value;
Construction unit, is used for creation analysis model, and using the impact factor of Ontario Scholar prestored to the analysis model into
Row training;
Input unit, for obtaining institute in the analysis model after the impact factor input training by the student to be evaluated
State analysis model output the student to be evaluated the weak factor, it is described weakness the factor be multiple impact factors in extremely
It is one few;
Call unit, for calling the specific aim reinforcing corresponding with the weakness factor prestored to build according to the weak factor
View;
Generation unit suggests generating institute for strengthening based on multiple impact factors, the weak factor and the specific aim
State the Visual evaluation information of student to be evaluated.
9. a kind of computer non-volatile memory medium, the storage medium includes the program of storage, which is characterized in that described
Equipment perform claim requires data analysing method described in 1 to 7 any one program controls the storage medium when running where.
10. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realizes claim 1 to 7 when executing the computer program
The step of data analysing method described in any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910374337.1A CN110245826A (en) | 2019-05-07 | 2019-05-07 | A kind of data analysing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910374337.1A CN110245826A (en) | 2019-05-07 | 2019-05-07 | A kind of data analysing method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110245826A true CN110245826A (en) | 2019-09-17 |
Family
ID=67883780
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910374337.1A Pending CN110245826A (en) | 2019-05-07 | 2019-05-07 | A kind of data analysing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110245826A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112101786A (en) * | 2020-09-15 | 2020-12-18 | 广东工贸职业技术学院 | Student data analysis method and device based on big data and computer equipment |
CN113870641A (en) * | 2021-09-29 | 2021-12-31 | 上海乐项信息技术有限公司 | Simulation training method and system for live broadcast of tape goods |
CN114077956A (en) * | 2020-08-21 | 2022-02-22 | 潘垚天 | Subject evaluation method, device and system |
CN115935191A (en) * | 2023-01-05 | 2023-04-07 | 广东中大管理咨询集团股份有限公司 | Big data analysis-based capacity measurement method and device |
-
2019
- 2019-05-07 CN CN201910374337.1A patent/CN110245826A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114077956A (en) * | 2020-08-21 | 2022-02-22 | 潘垚天 | Subject evaluation method, device and system |
CN112101786A (en) * | 2020-09-15 | 2020-12-18 | 广东工贸职业技术学院 | Student data analysis method and device based on big data and computer equipment |
CN113870641A (en) * | 2021-09-29 | 2021-12-31 | 上海乐项信息技术有限公司 | Simulation training method and system for live broadcast of tape goods |
CN115935191A (en) * | 2023-01-05 | 2023-04-07 | 广东中大管理咨询集团股份有限公司 | Big data analysis-based capacity measurement method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110245826A (en) | A kind of data analysing method and device | |
Ward et al. | The perils of policy by p-value: Predicting civil conflicts | |
CN109817312A (en) | A kind of medical bootstrap technique and computer equipment | |
CN110222171A (en) | A kind of application of disaggregated model, disaggregated model training method and device | |
CN107729915A (en) | For the method and system for the key character for determining machine learning sample | |
Shai et al. | Case studies in network community detection | |
van Eck et al. | Guided interaction exploration in artifact-centric process models | |
CN110046889A (en) | A kind of detection method, device and the server of abnormal behaviour main body | |
CN115050442B (en) | Disease category data reporting method and device based on mining clustering algorithm and storage medium | |
Hompes et al. | Detecting changes in process behavior using comparative case clustering | |
Thorleuchter et al. | Mining innovative ideas to support new product research and development | |
JP2018147407A (en) | Factor estimation device, factor estimation system, and factor estimation method | |
Magdon-Ismail et al. | Locating hidden groups in communication networks using hidden markov models | |
CN110021386B (en) | Feature extraction method, feature extraction device, equipment and storage medium | |
CN109815391A (en) | News data analysis method and device, electric terminal based on big data | |
Duxbury | Micro Effects on Macro Structure in Social Networks | |
CN113779954A (en) | Similar text recommendation method and device and electronic equipment | |
Sakti et al. | Determination of hospital rank by using analytic hierarchy process (ahp) and multi objective optimization on the basis of ratio analysis (moora) | |
Lera-Leri et al. | Aggregating value systems for decision support | |
Tekieh et al. | Analysing healthcare coverage with data mining techniques | |
Raufi | Hybrid models of performance using mental workload and usability features via supervised machine learning | |
CN113962216A (en) | Text processing method and device, electronic equipment and readable storage medium | |
Simon et al. | Association rule mining to identify the student dropout in MOOCs | |
Romeu | On operations research and statistics techniques: Keys to quantitative data mining | |
CN112396114A (en) | Evaluation system, evaluation method and related product |
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 |