CN108320045A - Student performance prediction technique and device - Google Patents
Student performance prediction technique and device Download PDFInfo
- Publication number
- CN108320045A CN108320045A CN201711385634.3A CN201711385634A CN108320045A CN 108320045 A CN108320045 A CN 108320045A CN 201711385634 A CN201711385634 A CN 201711385634A CN 108320045 A CN108320045 A CN 108320045A
- Authority
- CN
- China
- Prior art keywords
- student
- data
- daily behavior
- result
- behavior data
- 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
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention discloses a kind of student performance prediction technique and devices.Wherein, this method includes：It obtains network playing by students data and obtains student's location information；According to the analysis result to location information and Internet data, the daily behavior data of student are obtained；Based on the disaggregated model built in advance, result prediction result corresponding with daily behavior data is obtained, wherein disaggregated model is built as that the model of result prediction result can be obtained according to daily behavior data.The present invention solves the technical issues of can not predicting in advance student result data in the prior art.
Description
Technical field
The present invention relates to computer internet fields, in particular to a kind of student performance prediction technique and device.
Background technology
At present in every teaching task in most institution of higher learning of China, the core of work is all around teaching
Management work carry out.In Campus MIS, the content for comparing core is the management for student performance.To being at present
Only, traditional management mode is also continued up to the score management pattern of student in most colleges and universities, to the achievement of student
The content being managed is predominantly stayed in be counted achievement and is recorded according to what various examinations or examination collected.
Traditional statistical method is very convenient for the performance information of global analysis teaching and student, but is significantly asked there are one
Topic be exactly information hysteresis quality, be unable to the information that look-ahead goes out student performance, in this way when some students there are extension section risks very
Early warning can not be identified and make in advance to the dangerous situation because extension section causes to leave school, this management and student to school instruction
Personal growth all there is larger risk, and colleges and universities to the early warning demand of student performance strongly, since above-mentioned tradition is learned
Raw Achievement Management lacks scientific and effective achievement data analysis means, therefore leads to the exposure achievement in mode change
Some problems in management system can not achieve the prediction to achievement and then carry out early warning.
The problem of can not being predicted in advance student result data in for the above-mentioned prior art, not yet proposes have at present
The solution of effect.
Invention content
An embodiment of the present invention provides a kind of student performance prediction technique and devices, at least to solve in the prior art can not
The technical issues of student result data is predicted in advance.
One side according to the ... of the embodiment of the present invention provides a kind of student performance prediction technique, including：It obtains on student
Network data and acquisition student's location information；According to the analysis result to location information and Internet data, the daily of student is obtained
Behavioral data；Based on the disaggregated model built in advance, result prediction result corresponding with daily behavior data is obtained, wherein point
Class model is built as that the model of result prediction result can be obtained according to daily behavior data.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of student performance prediction meanss, including：First obtains
Module, for obtaining network playing by students data and obtaining student's location information；First generation module, for according to location information
With the analysis result of Internet data, the daily behavior data of student are obtained；Second generation module, for based on point built in advance
Class model obtains result prediction result corresponding with daily behavior data, wherein disaggregated model is built as can be according to daily row
The model of result prediction result is obtained for data.
Another aspect according to the ... of the embodiment of the present invention, additionally provides a kind of storage medium, and storage medium includes the journey of storage
Sequence, wherein equipment executes above-mentioned student performance prediction technique where controlling storage medium when program is run.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of processor, and processor is used to run program,
In, program executes above-mentioned student performance prediction technique when running.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of terminal, including：First acquisition module, for obtaining
It takes network playing by students data and obtains student's location information；First generation module, for according to location information and Internet data
Analysis result, obtain the daily behavior data of student；Second generation module, for based on the disaggregated model built in advance, obtaining
To result prediction result corresponding with daily behavior data, wherein disaggregated model is built as to be obtained according to daily behavior data
To the model of result prediction result；Processor, processor run program, wherein program run when for from the first acquisition module,
First generation module and the data of the second generation module output execute above-mentioned student performance prediction technique.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of terminal, including：First acquisition module, for obtaining
It takes network playing by students data and obtains student's location information；First generation module, for according to location information and Internet data
Analysis result, obtain the daily behavior data of student；Second generation module, for based on the disaggregated model built in advance, obtaining
To result prediction result corresponding with daily behavior data, wherein disaggregated model is built as to be obtained according to daily behavior data
To the model of result prediction result；Storage medium, for storing program, wherein program from first at runtime for obtaining mould
The data of block, the first generation module and the output of the second generation module execute above-mentioned student performance prediction technique.
In embodiments of the present invention, by the way of big data, by obtaining network playing by students data and obtaining student position
Confidence ceases；According to the analysis result to location information and Internet data, the daily behavior data of student are obtained；Based on advance structure
Disaggregated model, obtain result prediction result corresponding with daily behavior data, wherein disaggregated model is built as can be according to day
Normal behavioral data obtains the model of result prediction result, has achieved the purpose that carry out look-ahead to student performance, to realize
It is found in advance there are the student of extension section risk or achievement risk not up to standard, is talked or improved day by teacher to be conducive to
The methods of normal behavioural habits guides the higher student of risk, avoids the generation of true extension section, and improve the day of student
Normal behavioural habits, guiding student form good daily behavior custom, improve school grade, separate extension section to student or induce wind to retreat
Danger has highly important positive effect, and improving teaching to colleges and universities provides the technique effect of feasible scheme, and then solves
The technical issues of student result data can not be predicted in advance in the prior art.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is a kind of schematic diagram of student performance prediction technique according to the ... of the embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of optional student performance prediction technique according to the ... of the embodiment of the present invention；
Fig. 3 is a kind of schematic diagram of optional student performance prediction technique according to the ... of the embodiment of the present invention；
Fig. 4 is a kind of schematic diagram of optional student performance prediction technique according to the ... of the embodiment of the present invention；And
Fig. 5 is a kind of schematic diagram of student performance prediction meanss according to the ... of the embodiment of the present invention.
Specific implementation mode
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model that the present invention protects
It encloses.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
It includes to be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment to cover non-exclusive
Those of clearly list step or unit, but may include not listing clearly or for these processes, method, product
Or the other steps or unit that equipment is intrinsic.
Embodiment 1
According to embodiments of the present invention, a kind of embodiment of the method for student performance prediction technique is provided, it should be noted that
Step shown in the flowchart of the accompanying drawings can execute in the computer system of such as a group of computer-executable instructions, and
It, in some cases, can be to execute institute different from sequence herein and although logical order is shown in flow charts
The step of showing or describing.
Fig. 1 is student performance prediction technique according to the ... of the embodiment of the present invention, as shown in Figure 1, this method comprises the following steps：
Step S102 obtains network playing by students data and obtains student's location information；
Step S104 obtains the daily behavior data of student according to the analysis result to location information and Internet data；
Step S106, based on the disaggregated model built in advance, obtain result prediction corresponding with daily behavior data as a result,
Wherein, disaggregated model is built as that the model of result prediction result can be obtained according to daily behavior data.
Specifically, in step S102 when obtaining the Internet data of student, it can be by network collector from the upper of school
It is obtained in network data core switch, the internet information of student can be preserved in the core switch of school, and surf the Internet in school
It is typically required and carries out real-name authentication, or user authentication information real-name authentication can be carried out to internet information, therefore can be with
Map to obtain the Internet data of user by customer certification system to get to the Internet data of student's real name, a kind of specific
In embodiment, the Internet data got can be shown with data specifying information field shown in Fig. 2.In step S102
When obtaining student's location information, when using equipment for surfing the net to surf the Internet in the school due to student, need to connect access point in the school, i.e.,
AP, the position of AP is known in the school, therefore can determine the specific AP of the equipment for surfing the net connection of student first, and then according to AP
Position determine the location information of student, wherein the equipment for surfing the net that student uses can be the intelligence such as mobile phone, IPAD, computer
Terminal.
Specifically, traditional statistical method largely only rests on what school collected according to various examinations or examination
Performance information, the acquisition of daily life behavior and custom to student substantially also in blank stage, but student's daily life and
The behavioural habits of study and the final result of student have a closely contact, thus in the present invention in step S104 by being learned
Daily behavior data based on student predict achievement in raw daily behavior data and step S106, can overcome
Traditional approach reflects the missing on students' learning ability according to the single performance information collected, makes colleges and universities to student's
The daily behavior custom for influencing achievement has more comprehensive understanding, so as to manage student's work convenient for the development of more three-dimensional
Make.
In embodiments of the present invention, by the way of big data, by obtaining network playing by students data and obtaining student position
Confidence ceases；According to the analysis result to location information and Internet data, the daily behavior data of student are obtained；Based on advance structure
Disaggregated model, obtain result prediction result corresponding with daily behavior data, wherein disaggregated model is built as can be according to day
Normal behavioral data obtains the model of result prediction result, has achieved the purpose that carry out look-ahead to student performance, to realize
It is found in advance there are the student of extension section risk or achievement risk not up to standard, is talked or improved day by teacher to be conducive to
The methods of normal behavioural habits guides the higher student of risk, avoids the generation of true extension section, and improve the day of student
Normal behavioural habits, guiding student form good daily behavior custom, improve school grade, separate extension section to student or induce wind to retreat
Danger has highly important positive effect, and improving teaching to colleges and universities provides the technique effect of feasible scheme, and then solves
The technical issues of student result data can not be predicted in advance in the prior art.
In a kind of optional embodiment, daily behavior data include at least one of following：Access different type website
Number, equipment for surfing the net type and residence time of different places in school.
Specifically, when daily behavior data include accessing the number of different type website, need to carry out Internet data
Analysis, specifically by asking the analysis of url to obtain user's visit study class, game class, film/TV-like in Internet data
The number of equal websites.
Specifically, when daily behavior data include equipment for surfing the net type, need to analyze Internet data, specially
By obtaining device type that student uses to the analysis of requesting method in Internet data (request_method), pass through this kind
Mode can also obtain the third party application i.e. number information of APP that student uses equipment for surfing the net to access, the number information
Different type website can be included into herein, if for example, requesting method is " Netease cloud music 3.7.4rv:670(iPhone；iOS
10.1.1；Zh_CN) ", then it represents that user uses iphone equipment, and has used Netease cloud music APP, is based on this, Ke Yitong
Count out the device types such as type of cell phone or the pc that user uses.
Specifically, when daily behavior data include the residence time of different places in school, need to location information
Analyzed, so as to obtain student the different places such as the library, bedroom or classroom of school residence time.
In a kind of optional embodiment, according to the analysis result to location information and Internet data in step S104, obtain
To the daily behavior data of student, including：Internet data is compared step S202 with presetting database, obtains student's visit
Ask the number and/or equipment for surfing the net type of different type website, wherein presetting database includes the data letter of different type website
The data information of breath and/or equipment for surfing the net type.
Specifically, in the daily behavior number for obtaining student, need to Internet data carry out parsing and with database into
Row compares, for example, when daily behavior data include accessing the number of different type website, needs through the comparison with database
It identifies different types of website, and then obtains accessing the number of different type website, therefore by Internet data in the present invention
Further include the steps that prebuild presetting database before being compared with presetting database, and database can be carried out not
Disconnected abundant and modification, preferably to identify different types of website, the access different type in corresponding daily behavior data
The number and equipment for surfing the net type of website may include data information, the equipment for surfing the net type of different type website in database
Data information etc..
In a kind of optional embodiment, based on the disaggregated model built in advance in step S106, obtain and daily behavior
Before the corresponding result prediction result of data, data cleansing and/or quantization can be carried out to daily behavior data, inputted again later
To disaggregated model.
In a kind of optional embodiment, based on the disaggregated model built in advance in step S106, daily behavior number is obtained
Before corresponding result prediction result, method further includes：
Step S302 builds disaggregated model；
Wherein, disaggregated model is built in step S302 includes：
Step S402 obtains the history Internet data of sample student and obtains the history bit confidence of historical sample student
Breath；
Step S404 obtains going through for sample student according to the analysis result to historical position information and history Internet data
History daily behavior data；
Step S406 builds disaggregated model according to the Historical Results information of history daily behavior data and sample student.
Specifically, the sample student chosen is more, the accuracy of the disaggregated model of structure is higher, the history day of sample student
The Historical Results information of normal behavioral data and sample student can be the information or data of preset time period, the preset time period
Self-defined it can be arranged.The Historical Results information of sample student includes the performance information of extension section student and Bu Gua sections student, in structure
It, can be using history daily behavior data as characteristic information, using Historical Results information as prediction training when building disaggregated model
Indication information., can be by the statistics to the daily behavior data of student in a time cycle after obtaining disaggregated model, profit
With the disaggregated model, complete the prediction to student performance, prediction student whether You Gua sections risk.
In a kind of optional embodiment, according to the Historical Results information of history daily behavior data and sample student, structure
It builds before disaggregated model, data cleansing and/or quantization can be carried out to history daily behavior data, be further used as structure classification later
The characteristic information of model.
In a kind of optional embodiment, in step S406 according to history daily behavior data and the history of sample student at
Achievement information builds disaggregated model, including：
Step S502 is calculated according to the Historical Results information of history daily behavior data and sample student using random forest
Method builds disaggregated model.
Specifically, random forest is exactly by the thought of integrated study by a kind of integrated algorithm of more trees, it basic
Unit is decision tree, and decision tree is a kind of tree structure, wherein each internal node indicates the test on an attribute, Mei Gefen
Zhi represents a test output, and each leaf node represents a kind of classification, and its essence belongs to a big branch-of machine learning
Integrated study (Ensemble Learning) method.When for classification problem, every decision tree is all one in random forest
Grader, for an input sample, N tree has N number of classification results, and random forest is integrated with all classification ballot knots
The most classification of number of voting can be appointed as final output by fruit, and here it is a kind of simplest Bagging thoughts.
Further include to history daily behavior data and sample student specifically, during building disaggregated model algorithm
The cleaning of Historical Results information, the setting of hyper parameter and tuning in standardization processing and random forests algorithm, such as at random
The setting of the number and depth set in forest algorithm and tuning.
In a kind of specific embodiment, the flow of random forest disaggregated model is built as shown in figure 3, the position of user is believed
The location information for the AP that the equipment for surfing the net that breath can use station acquisition device to be used by student connects is determined, and user's is upper
Network data can be obtained by network collector from the Internet data core switch of school, can by the location information of user
To count student in the duration in the places such as library, classroom and bedroom, student couple can be obtained by the Internet data of user
The type for the equipment for surfing the net that game class, film/TV-like, the access times of study class website and student use, by above-mentioned
Student is in the duration in the places such as library, classroom and bedroom and student to game class, film/TV-like, study class website
The type for the equipment for surfing the net that access times and student use can obtain student's daily behavior characteristic information, in conjunction with student
Performance information, you can structure the disaggregated model based on random forests algorithm.
In a kind of specific embodiment, overall flow of the invention is as shown in figure 4, pass through mode root as shown in Figure 3
After obtaining disaggregated model according to historical data, disaggregated model can be stored as off-line files, need to carry out in advance new data
When survey, daily behavior data can be obtained according to new data, load offline disaggregated model, you can day is obtained according to disaggregated model
The corresponding result prediction result of normal behavioral data.
Embodiment 2
According to embodiments of the present invention, a kind of product embodiments of student performance prediction meanss are provided, Fig. 5 is according to this hair
The student performance prediction meanss of bright embodiment, as shown in figure 5, the device includes the first acquisition module, the first generation module and the
Two generation modules, wherein the first acquisition module, for obtaining network playing by students data and obtaining student's location information；First life
At module, for according to the analysis result to location information and Internet data, obtaining the daily behavior data of student；Second generates
Module, for based on the disaggregated model built in advance, obtaining result prediction result corresponding with daily behavior data, wherein point
Class model is built as that the model of result prediction result can be obtained according to daily behavior data.
In embodiments of the present invention, by the way of big data, by the first acquisition module obtain network playing by students data with
And obtain student's location information；First generation module obtains student's according to the analysis result to location information and Internet data
Daily behavior data；Second generation module obtains achievement corresponding with daily behavior data based on the disaggregated model built in advance
Prediction result, wherein disaggregated model is built as that the model of result prediction result can be obtained according to daily behavior data, reaches
The purpose that look-ahead is carried out to student performance finds that there are extension section risk or achievement risks not up to standard in advance to realize
Student, to be conducive to draw to the higher student of risk by the method for teacher's talk or improvement daily behavior custom
It leads, avoids the generation of true extension section, and improve the daily behavior custom of student, guiding student is formed good daily behavior and practised
Used, improving school grade, separate extension section to student or induce risk to retreat has highly important positive effect, improves colleges and universities and imparts knowledge to students
The technique effect of feasible scheme is provided, and then solves student result data can not be predicted in advance in the prior art
The technical issues of.
Herein it should be noted that above-mentioned first acquisition module, the first generation module and the second generation module correspond in fact
The step S102 to step S106 in example 1 is applied, above-mentioned module is identical as example and application scenarios that corresponding step is realized, but
It is not limited to the above embodiments 1 disclosure of that.It should be noted that above-mentioned module can be such as a part of of device
It is executed in the computer system of a group of computer-executable instructions.
In a kind of optional embodiment, daily behavior data include at least one of following：Access different type website
Number, equipment for surfing the net type and residence time of different places in school.
In a kind of optional embodiment, the first generation module, including：Comparing module is used for Internet data and presets
Database is compared, and obtains number and/or equipment for surfing the net type that student accesses different type website, wherein preset data
Library includes the data information of different type website and/or the data information of equipment for surfing the net type.
Herein it should be noted that above-mentioned comparing module correspond to embodiment 1 in step S202, above-mentioned module with it is corresponding
The step of the example realized it is identical with application scenarios, but be not limited to the above embodiments 1 disclosure of that.It needs to illustrate
It is that above-mentioned module can be executed as a part of of device in the computer system of such as a group of computer-executable instructions.
In a kind of optional embodiment, device further includes：First structure module, it is pre- for being based in the second generation module
The disaggregated model first built before obtaining the corresponding result prediction result of daily behavior data, builds disaggregated model；Wherein,
One structure module includes the second acquisition module, third generation module and the second structure module, wherein the second acquisition module is used for
It obtains the history Internet data of sample student and obtains the historical position information of historical sample student；Third generation module is used
According to the analysis result to historical position information and history Internet data, the history daily behavior data of sample student are obtained；
Second structure module builds disaggregated model for the Historical Results information according to history daily behavior data and sample student.
Herein it should be noted that above-mentioned first structure module, the second acquisition module, third generation module and the second structure
Module corresponds to step S302 and step S402 to step S406 in embodiment 1, and above-mentioned module and corresponding step institute are real
Existing example is identical with application scenarios, but is not limited to the above embodiments 1 disclosure of that.It should be noted that above-mentioned module
A part of as device can execute in the computer system of such as a group of computer-executable instructions.
In a kind of optional embodiment, the second structure module, including：Third builds module, for daily according to history
The Historical Results information of behavioral data and sample student builds disaggregated model using random forests algorithm.
Herein it should be noted that above-mentioned third structure module correspond to embodiment 1 in step S502, above-mentioned module with
The example that corresponding step is realized is identical with application scenarios, but is not limited to the above embodiments 1 disclosure of that.It needs to illustrate
, above-mentioned module can hold as a part of of device in the computer system of such as a group of computer-executable instructions
Row.
Embodiment 3
According to embodiments of the present invention, a kind of product embodiments of storage medium are provided, which includes storage
Program, wherein equipment executes above-mentioned student performance prediction technique where controlling storage medium when program is run.
Embodiment 4
According to embodiments of the present invention, a kind of product embodiments of processor are provided, which is used to run program,
In, program executes above-mentioned student performance prediction technique when running.
Embodiment 5
According to embodiments of the present invention, a kind of product embodiments of terminal are provided, which includes the first acquisition module, the
One generation module, the second generation module and processor, wherein the first acquisition module, for obtaining network playing by students data and obtaining
Take student's location information；First generation module, for according to the analysis result to location information and Internet data, obtaining student's
Daily behavior data；Second generation module, it is corresponding with daily behavior data for based on the disaggregated model built in advance, obtaining
Result prediction result, wherein disaggregated model is built as that the model of result prediction result can be obtained according to daily behavior data；Place
Device is managed, processor runs program, wherein for being generated from the first acquisition module, the first generation module and second when program is run
The data of module output execute above-mentioned student performance prediction technique.
Embodiment 6
According to embodiments of the present invention, a kind of product embodiments of terminal are provided, which includes the first acquisition module, the
One generation module, the second generation module and storage medium, wherein the first acquisition module, for obtain network playing by students data and
Obtain student's location information；First generation module, for according to the analysis result to location information and Internet data, obtaining student
Daily behavior data；Second generation module, it is corresponding with daily behavior data for based on the disaggregated model built in advance, obtaining
Result prediction result, wherein disaggregated model is built as that the model of result prediction result can be obtained according to daily behavior data；
Storage medium, for storing program, wherein program is at runtime for from the first acquisition module, the first generation module and second
The data of generation module output execute above-mentioned student performance prediction technique.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
In the above embodiment of the present invention, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment
The part of detailed description may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, for example, the unit division, Ke Yiwei
A kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
It connects, can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
On unit.Some or all of unit therein can be selected according to the actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can to store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of student performance prediction technique, which is characterized in that including：
It obtains network playing by students data and obtains student's location information；
According to the analysis result to the location information and the Internet data, the daily behavior data of the student are obtained；
Based on the disaggregated model built in advance, result prediction result corresponding with the daily behavior data is obtained, wherein described
Disaggregated model is built as that the model of the result prediction result can be obtained according to the daily behavior data.
2. according to the method described in claim 1, it is characterized in that, the daily behavior data include at least one of following：It visits
Ask the number of different type website, equipment for surfing the net type and residence time of different places in school.
3. according to the method described in claim 2, it is characterized in that, dividing according to the location information and the Internet data
Analysis as a result, obtain the daily behavior data of the student, including：
The Internet data is compared with presetting database, obtain the student access different type website number and/
Or equipment for surfing the net type, wherein the presetting database includes the data information and/or equipment for surfing the net type of different type website
Data information.
4. according to the method described in claim 1, it is characterized in that, based on the disaggregated model built in advance, obtain described daily
Before the corresponding result prediction result of behavioral data, the method further includes：
Build the disaggregated model；
Wherein, building the disaggregated model includes：
It obtains the history Internet data of sample student and obtains the historical position information of the historical sample student；
According to the analysis result to the historical position information and the history Internet data, the history of the sample student is obtained
Daily behavior data；
According to the Historical Results information of the history daily behavior data and the sample student, the disaggregated model is built.
5. according to the method described in claim 4, it is characterized in that, according to the history daily behavior data and the sample
Raw Historical Results information builds the disaggregated model, including：
According to the Historical Results information of the history daily behavior data and the sample student, built using random forests algorithm
The disaggregated model.
6. a kind of student performance prediction meanss, which is characterized in that including：
First acquisition module, for obtaining network playing by students data and obtaining student's location information；
First generation module, for according to the analysis result to the location information and the Internet data, obtaining the student
Daily behavior data；
Second generation module, for based on the disaggregated model built in advance, obtaining achievement corresponding with the daily behavior data
Prediction result, wherein the disaggregated model is built as that the result prediction result can be obtained according to the daily behavior data
Model.
7. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require student performance prediction technique described in any one of 1 to 5.
8. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Profit requires the student performance prediction technique described in any one of 1 to 5.
9. a kind of terminal, which is characterized in that including：
First acquisition module, for obtaining network playing by students data and obtaining student's location information；
First generation module, for according to the analysis result to the location information and the Internet data, obtaining the student
Daily behavior data；
Second generation module, for based on the disaggregated model built in advance, obtaining achievement corresponding with the daily behavior data
Prediction result, wherein the disaggregated model is built as that the result prediction result can be obtained according to the daily behavior data
Model；
Processor, the processor run program, wherein for from first acquisition module, described when described program is run
First generation module and the data perform claim of second generation module output require the student described in any one of 1 to 5
Result prediction method.
10. a kind of terminal, which is characterized in that including：
First acquisition module, for obtaining network playing by students data and obtaining student's location information；
First generation module, for according to the analysis result to the location information and the Internet data, obtaining the student
Daily behavior data；
Second generation module, for based on the disaggregated model built in advance, obtaining achievement corresponding with the daily behavior data
Prediction result, wherein the disaggregated model is built as that the result prediction result can be obtained according to the daily behavior data
Model；
Storage medium, for storing program, wherein described program is at runtime for from first acquisition module, described
One generation module and the data perform claim of second generation module output require the student described in any one of 1 to 5 at
Achievement prediction technique.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711385634.3A CN108320045A (en) | 2017-12-20 | 2017-12-20 | Student performance prediction technique and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711385634.3A CN108320045A (en) | 2017-12-20 | 2017-12-20 | Student performance prediction technique and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108320045A true CN108320045A (en) | 2018-07-24 |
Family
ID=62892776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711385634.3A Pending CN108320045A (en) | 2017-12-20 | 2017-12-20 | Student performance prediction technique and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108320045A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985522A (en) * | 2018-08-02 | 2018-12-11 | 杭州华网信息技术有限公司 | A kind of Intelligent campus extension section's method for early warning and system |
| CN110110939A (en) * | 2019-05-15 | 2019-08-09 | 杭州华网信息技术有限公司 | The academic record prediction and warning method of behavior is serialized based on deep learning student |
| CN111091481A (en) * | 2019-11-25 | 2020-05-01 | 珠海格力电器股份有限公司 | Registration information verification method and device, storage medium and electronic equipment |
| CN111754097A (en) * | 2020-06-18 | 2020-10-09 | 上海交通大学 | Student achievement prediction system based on multi-view encoder-decoder architecture |
| CN112116142A (en) * | 2020-09-14 | 2020-12-22 | 桂林电子科技大学 | Student score prediction system and method based on deep learning |
| CN112232609A (en) * | 2020-12-18 | 2021-01-15 | 北京几原科技有限责任公司 | Method and system for estimating student score in real time by using machine learning model |
| CN112668750A (en) * | 2020-11-25 | 2021-04-16 | 紫光云技术有限公司 | Distributed FP-Growth result early warning model based on behavior time sequence weight |
| CN113256865A (en) * | 2020-11-06 | 2021-08-13 | 上海兴容信息技术有限公司 | Control method and system of intelligent access control |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894119A (en) * | 2016-04-05 | 2016-08-24 | 成都寻道科技有限公司 | Student ranking prediction method based on campus data |
| CN106157204A (en) * | 2016-06-20 | 2016-11-23 | 山东师范大学 | A kind of Forecasting The Scores method and system based on BP neural network model |
| CN107451861A (en) * | 2017-07-27 | 2017-12-08 | 中兴软创科技股份有限公司 | A kind of method of user's online feature recognition under big data |
-
2017
- 2017-12-20 CN CN201711385634.3A patent/CN108320045A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894119A (en) * | 2016-04-05 | 2016-08-24 | 成都寻道科技有限公司 | Student ranking prediction method based on campus data |
| CN106157204A (en) * | 2016-06-20 | 2016-11-23 | 山东师范大学 | A kind of Forecasting The Scores method and system based on BP neural network model |
| CN107451861A (en) * | 2017-07-27 | 2017-12-08 | 中兴软创科技股份有限公司 | A kind of method of user's online feature recognition under big data |
Non-Patent Citations (2)
| Title |
|---|
| 吴鲲;: "基于机器学习的学生成绩预警系统建模与研究", 太原城市职业技术学院学报, no. 12, pages 178 - 180 * |
| 王景兰;葛亚军;: "基于数据挖掘的大学生上网行为数据分析与研究", 电脑迷, no. 08 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985522A (en) * | 2018-08-02 | 2018-12-11 | 杭州华网信息技术有限公司 | A kind of Intelligent campus extension section's method for early warning and system |
| CN110110939A (en) * | 2019-05-15 | 2019-08-09 | 杭州华网信息技术有限公司 | The academic record prediction and warning method of behavior is serialized based on deep learning student |
| CN111091481A (en) * | 2019-11-25 | 2020-05-01 | 珠海格力电器股份有限公司 | Registration information verification method and device, storage medium and electronic equipment |
| CN111754097A (en) * | 2020-06-18 | 2020-10-09 | 上海交通大学 | Student achievement prediction system based on multi-view encoder-decoder architecture |
| CN112116142A (en) * | 2020-09-14 | 2020-12-22 | 桂林电子科技大学 | Student score prediction system and method based on deep learning |
| CN113256865A (en) * | 2020-11-06 | 2021-08-13 | 上海兴容信息技术有限公司 | Control method and system of intelligent access control |
| CN113256865B (en) * | 2020-11-06 | 2023-01-06 | 上海兴容信息技术有限公司 | Control method and system of intelligent access control |
| CN112668750A (en) * | 2020-11-25 | 2021-04-16 | 紫光云技术有限公司 | Distributed FP-Growth result early warning model based on behavior time sequence weight |
| CN112668750B (en) * | 2020-11-25 | 2023-07-07 | 紫光云技术有限公司 | Distributed FP-Growth achievement early warning model based on behavior time sequence weight |
| CN112232609A (en) * | 2020-12-18 | 2021-01-15 | 北京几原科技有限责任公司 | Method and system for estimating student score in real time by using machine learning model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108320045A (en) | Student performance prediction technique and device | |
| CN108595494B (en) | Method and device for acquiring reply information | |
| US20160162794A1 (en) | Decision tree data structures generated to determine metrics for child nodes | |
| CN106126524B (en) | Information pushing method and device | |
| CN108320044A (en) | Student learns duration prediction method and apparatus | |
| CN112749749B (en) | Classification decision tree model-based classification method and device and electronic equipment | |
| CN109472305A (en) | Answer quality determines model training method, answer quality determination method and device | |
| CN110442737A (en) | The twin method and system of number based on chart database | |
| CN108198040A (en) | Educational resource distribution method, device, computer equipment and storage medium | |
| CN106097043A (en) | The processing method of a kind of credit data and server | |
| CN106776928A (en) | Recommend method in position based on internal memory Computational frame, fusion social environment and space-time data | |
| CN110535850A (en) | Treating method and apparatus, storage medium and the electronic device that account number logs in | |
| CN109948016A (en) | Application message method for pushing, device, server and computer readable storage medium | |
| CN110209875A (en) | User content portrait determines method, access object recommendation method and relevant apparatus | |
| Bicans et al. | Student learning style extraction from on-campus learning context data | |
| CN108563648A (en) | data display method and device, storage medium and electronic device | |
| CN113535848A (en) | Block chain-based credit investigation grade determination method, device, equipment and storage medium | |
| US20170228680A1 (en) | Improvement message based on element score | |
| US10970490B2 (en) | Automatic evaluation of artificial intelligence-based processes | |
| CN105630960B (en) | The method and apparatus of testing field Task conversational system | |
| CN108460475A (en) | Poor student's prediction technique and device based on network playing by students behavior | |
| CN108335242A (en) | Student's differentiating method and device | |
| Velásquez et al. | A case study: Ingestion analysis of wsn data in databases using docker | |
| CN114580794A (en) | Data processing method, apparatus, program product, computer device and medium | |
| US11651270B2 (en) | Search, question answering, and classifier construction |
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 |