CN117291773A - Online examination system based on deep learning technology - Google Patents
Online examination system based on deep learning technology Download PDFInfo
- Publication number
- CN117291773A CN117291773A CN202311555933.2A CN202311555933A CN117291773A CN 117291773 A CN117291773 A CN 117291773A CN 202311555933 A CN202311555933 A CN 202311555933A CN 117291773 A CN117291773 A CN 117291773A
- Authority
- CN
- China
- Prior art keywords
- examination
- reminding
- examinee
- module
- 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
- 238000005516 engineering process Methods 0.000 title claims abstract description 26
- 238000013135 deep learning Methods 0.000 title claims abstract description 24
- 238000013461 design Methods 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000012360 testing method Methods 0.000 claims description 64
- 238000007726 management method Methods 0.000 claims description 34
- 230000004438 eyesight Effects 0.000 claims description 33
- 238000000034 method Methods 0.000 claims description 32
- 238000003860 storage Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 21
- 238000013524 data verification Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 13
- 239000012634 fragment Substances 0.000 claims description 11
- 230000002068 genetic effect Effects 0.000 claims description 11
- 230000007246 mechanism Effects 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000001771 impaired effect Effects 0.000 claims description 9
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 208000032041 Hearing impaired Diseases 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/604—Tools and structures for managing or administering access control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Biology (AREA)
- Bioethics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Automation & Control Theory (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an online examination system based on a deep learning technology, and relates to the technical field of online examination, wherein the system comprises an information acquisition unit, a discriminant design unit, an examination reminding unit, an examination management unit and an invigoration analysis unit; the information acquisition unit is used for acquiring personal data of the examinee and encrypting and storing the data; the judging and designing unit is used for dividing the examinees into normal examinees and special examinees according to the personal data of the examinees and designing corresponding examination modes; the examination reminding unit is used for making different reminding plans based on the examination mode and the examination plan and sending examination reminding to the examinee; the examination management unit is used for calling examination contents, receiving input of an examinee and storing answer data in real time; and the invigilation analysis unit is used for analyzing the invigilation video by using a deep learning technology and automatically detecting whether cheating conditions exist in the examinee. According to the invention, the personalized examination mode is designed according to the type of the examinee by the discrimination design unit, so that the individuation of the examination is realized.
Description
Technical Field
The invention relates to the technical field of online examination, in particular to an online examination system based on a deep learning technology.
Background
Examination is a formalized evaluation method, which is mainly used for testing and evaluating the level of an examinee in a certain course, knowledge field or capability. The examination is carried out by designing various questions, testing the mastering degree and application capability of the examinee on the course knowledge points, reflecting the progress of the examinee in the learning process through the examination result, and judging whether the examinee reaches the expected target or not, wherein the examination result can provide feedback for teachers, know the teaching effect, adjust the teaching method and influence part of examination results on future development of the examinee, such as recruiter examination. In a word, the examination is a fair and objective evaluation method, can comprehensively and directly detect the study level of the examinee, and has important reference value for teaching and management.
With the progress of information technology, the examination technology is mature, the young generation uses network learning and online communication to be more, the online examination accords with the habit of an examinee, the online examination system is powerful in function, the functions of examination supervision management, answer record, automatic scoring and the like can be realized, the examination efficiency is improved, the online examination does not need a physical field, large-scale examination can be realized through a network, the cost is saved, the answer environment of the online examination examinee is basically uniform, the inconvenience caused by regional difference is reduced, the safety of personal information and the answer process of the examinee is ensured through anti-cheating technology such as monitoring software and the like, so that the online examination becomes a mainstream form of current education evaluation, the right of the examinee is ensured, and the examination efficiency is improved.
However, the existing online examination system cannot take care of individual differences of examinees when in use, cannot realize individual examination service, cannot provide more convenient examination modes for the examinees with uncomfortable body or disabilities, and the examinees may miss examination time due to no prompt in time, so that examination resources cannot be fully utilized, and time and cost are wasted.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an online examination system based on a deep learning technology, so as to overcome the technical problems existing in the prior related art.
For this purpose, the invention adopts the following specific technical scheme:
the on-line examination system based on the deep learning technology comprises an information acquisition unit, a discriminant design unit, an examination reminding unit, an examination management unit and an invigoration analysis unit;
the information acquisition unit is connected with the discrimination design unit, the discrimination design unit is connected with the examination reminding unit, the examination reminding unit is connected with the examination management unit, and the examination management unit is connected with the examination analysis unit;
the information acquisition unit is used for acquiring personal data of the examinee and encrypting and storing the data;
the judging and designing unit is used for dividing the examinees into normal examinees and special examinees according to the personal data of the examinees and designing corresponding examination modes;
the examination reminding unit is used for making different reminding plans based on the examination mode and the examination plan and sending examination reminding to the examinee;
the examination management unit is used for calling examination contents, receiving input of an examinee and storing answer data in real time;
and the invigilation analysis unit is used for analyzing the invigilation video by using a deep learning technology and automatically detecting whether cheating conditions exist in the examinee.
Further, the information acquisition unit comprises a user registration module, a data verification module, an encryption storage module and an access control module;
the user registration module is connected with the data verification module, the data verification module is connected with the encryption storage module, and the encryption storage module is connected with the access control module;
the user registration module is used for providing information data for the test login test platform, wherein the information data comprises personal information, physical conditions, academic backgrounds and personality characteristics;
the data verification module is used for supervising information data provided by a background verification examinee and judging the accuracy and the integrity of the data content;
the encryption storage module is used for encrypting and storing the information data by using a homomorphic encryption algorithm;
and the access control module is used for improving a single management mechanism in the memory based on a secret sharing algorithm and setting a plurality of groups of management to limit control access jointly.
Further, encrypting and storing the information data by using the homomorphic encryption algorithm comprises:
the supervision background generates a public key and a secret key in advance on the basis of a homomorphic encryption algorithm according to the information data, and encrypts the information data by using the secret key to obtain an information document set;
the supervision background extracts all different keywords from the information document set in the encryption domain, constructs a keyword set, encrypts the keywords through a public key and obtains an encrypted keyword set;
and re-encrypting the information document set and the keyword set by using the public key, and uploading the information document set and the keyword set to a memory supported by homomorphic encryption.
Further, improving a single management mechanism in the memory based on the secret sharing algorithm, setting a plurality of groups of management common restriction control access includes:
the storage receives the information data to generate a group public key and a group private key, and the group private key is used as a private value, different prime numbers are randomly selected, and polynomial function construction is carried out on the premise of different prime numbers;
obtaining fragments of a group private key according to a polynomial function result, and respectively generating different fragments to the invigilation manager according to the number of the invigilation manager;
when different visitors initiate memory access, the visitors locally generate homomorphic encrypted public keys and private keys, the public keys are sent to each proctorial manager, and the private keys are sent to the memory through a secure channel;
the proctor selects the random number, encrypts the random number by using the respective group private key fragments to obtain a ciphertext, and sends the ciphertext to the memory;
the memory calculates the ciphertext product to obtain a ciphertext block and calculates a ciphertext code, the memory sends the ciphertext block to a visitor, and the ciphertext code is sent to a proctorial manager;
the visitor logs in the memory according to the ciphertext block and verifies through the ciphertext code at the proctorial manager;
if the verification is passed, the visitor is allowed to access the query data, and if the verification is not passed, the visitor is not allowed to access the query data.
Further, the judging and designing unit comprises an examinee classifying module, an examination designing module, an examinee recording module and an examination executing module;
the examination room classifying module is connected with the examination design module, the examination design module is connected with the examination room recording module, and the examination room recording module is connected with the examination execution module;
the examinee classification module is used for classifying the examinees into normal examinees and special examinees according to personal information conditions of the examinees;
the examination design module is used for establishing examination modes of different types based on the genetic algorithm and the task parameters;
the examinee recording module is used for recording and tracking the whole examination process of the examinee;
and the examination execution module is used for managing and coordinating the actual operation process of the examination.
Further, dividing the test taker into a normal test taker and a special test taker according to the personal information condition of the test taker comprises:
selecting vision and hearing information data in the information data, and respectively quantizing and converting the vision and hearing information data of the examinee into signal data by utilizing digital optics and digital audio technology;
windowing is carried out on the vision and hearing signal data by adopting short-time Fourier transform;
extracting vision degree in vision signal data, carrying out probability analysis on the vision degree, and classifying vision types through the probability analysis to obtain two groups of normal vision and impaired vision;
and mapping the hearing data to a high-dimensional feature space by using a support vector machine, constructing an optimal classification hyperplane, and classifying to obtain two groups of normal hearing and impaired hearing.
Further, establishing different types of examination modes based on the genetic algorithm and the task parameters comprises:
based on task parameters and teaching modes, comprehensively considering examination duration, examination difficulty and examination plans to establish a multi-machine collaborative operation function;
constructing a multi-variant grouping genetic algorithm according to a multi-machine collaborative operation function, designing two-section codes, wherein the two-section codes comprise a normal mode code and a special mode code, and designing an examination mode under the normal mode;
analyzing the influence of different items in a multi-machine collaborative operation function on the hearing and eyesight of a test taker aiming at the coded content in a special mode, and determining the weight coefficient of the eyesight and the hearing;
and selecting a limit selection method and a weight coefficient to design an examination mode in a special mode, and performing simulation aiming at the examination mode.
Further, the expression of the multi-machine collaborative job function is:
；
in the method, in the process of the invention,findicating the cooperation of a plurality of machines,、/>and->Weights respectively representing examination duration, examination difficulty and examination plan, +.>Represent the firstiLoad parameters of the field examination application device, +.>Represent the firstiThe upper limit of the load of the field examinee,mindicating the number of fields of the examination.
Further, the examination reminding unit comprises an examination planning module, a reminding sending module and a reminding tracking module;
the examination planning module is connected with the reminding planning module, the reminding planning module is connected with the reminding sending module, and the reminding sending module is connected with the reminding tracking module;
the examination planning module is used for storing and managing various information of examination, wherein the information comprises examination places, dates, examination duration and examination subjects;
the reminding plan module is used for making different reminding plans according to the examination plans and categories of the examinees;
the reminding sending module is used for sending examination reminding to the examinee according to the reminding plan at the appointed time;
the reminding tracking module is used for tracking the sending state of the reminding and confirming whether the examinee receives the reminding or not.
Further, the making of different reminder plans according to the examination plan and the category of the examinee includes:
after the test taker logs in the platform to finish the test registration operation, the test platform sends a message prompt to the test taker;
identifying the category of the examinee of the category of the examinee at the examination platform according to login information of the examinee, generating a link for a normal examinee by the examination platform, and setting corresponding selection data in the link;
normal examinees click into the links, fill in service requests in the links, determine the sending frequency and time of the reminding, formulate the content when sending the reminding according to the reminding frequency and time selected by the examinees, and select corresponding reminding modes in the links, wherein the reminding modes comprise telephone reminding, alarm reminding and short message reminding;
after the examination platform identifies a special examinee, the frequency and time of transmission are determined through the voice reminding service if the examination platform is the visually impaired examinee, and the frequency and time of transmission are determined through the short message reminding service if the examination platform is the hearing impaired examinee.
The beneficial effects of the invention are as follows:
1. the invention provides an on-line examination system, which is characterized in that personal data of an examinee is acquired through an information acquisition unit, basic data is provided for the follow-up division of the examinee type and the design of an examination mode, the design of the personalized examination mode is designed by a design judging and designing unit according to the examinee type, the individuation of the examination is realized, meanwhile, a differentiated prompt is sent through an examination prompting unit based on the examination mode, the examination time of the examinee is conveniently prompted, an examination management unit is arranged for storing answering data in real time, the original data support is provided for the examination analysis, the cheating is finally detected by an examination analysis unit, the examination crediting force is improved, the functions of classification identification, individuation service, automatic examination monitoring and the like of the examinee are integrally realized, the examination efficiency is improved, and the system has a good integral effect.
2. The invention adopts homomorphic encryption and secret sharing algorithm to carry out safe storage and access control on information data, realizes strong encryption of examinee data in the storage process, improves the data security, designs a plurality of groups of management mechanisms by using the secret sharing algorithm, realizes distributed control of storage access, prevents single-point authority abuse, improves the system security, distributes group private key fragments to a plurality of managers for holding, can finish verification only by needing multiparty participation, greatly increases the difficulty of recovering the whole private key, prevents key leakage, requires multiparty participation for data access, and improves the security and reliability of the system.
3. According to the invention, visual and hearing information is quantified through a digital technology, characteristics are extracted to carry out probability analysis and support vector machine classification, automatic classification of visual and hearing ability of an examinee is realized, normal examinee and different types of special examinees are provided with basis for the design of a follow-up personalized examination mode, a multi-machine collaborative operation function is established, two-section codes are designed based on a genetic algorithm, examination modes are designed for the normal examinee and the special examinee respectively, personalized service is realized, and the intelligent personalized online examination system is facilitated to be constructed, and the examination service level is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic block diagram of an on-line examination system based on a deep learning technique according to an embodiment of the present invention.
In the figure:
1. an information acquisition unit; 101. a user registration module; 102. a data verification module; 103. an encryption storage module; 104. an access control module; 2. a discriminant design unit; 201. the examinee classifying module; 202. an examination design module; 203. the examinee recording module; 204. an examination execution module; 3. an examination reminding unit; 301. an examination planning module; 302. a reminder planning module; 303. a reminding sending module; 304. a reminding tracking module; 4. an examination management unit; 5. and a invigilation analysis unit.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used for illustrating the embodiments and for explaining the principles of the operation of the embodiments in conjunction with the description thereof, and with reference to these matters, it will be apparent to those skilled in the art to which the present invention pertains that other possible embodiments and advantages of the present invention may be practiced.
According to an embodiment of the invention, an online examination system based on a deep learning technology is provided.
Referring to the drawings and the specific embodiments, as shown in fig. 1, the on-line examination system based on the deep learning technology according to the embodiment of the invention includes an information acquisition unit 1, a discriminant design unit 2, an examination reminding unit 3, an examination management unit 4 and an invigilation analysis unit 5.
The information acquisition unit 1 is connected with the discrimination design unit 2, the discrimination design unit 2 is connected with the examination reminding unit 3, the examination reminding unit 3 is connected with the examination management unit 4, and the examination management unit 4 is connected with the invigilation analysis unit 5.
The information acquisition unit 1 is used for acquiring personal data of the examinee and encrypting and storing the data.
In this embodiment, the information acquisition unit 1 includes a user registration module 101, a data verification module 102, an encryption storage module 103, and an access control module 104.
The user registration module 101 is connected with the data verification module 102, the data verification module 102 is connected with the encryption storage module 103, and the encryption storage module 103 is connected with the access control module 104.
Specifically, the user registration module 101 is configured to provide information data for the test taker login test platform, where the information data includes personal information, physical condition, academic background, and personality characteristics.
The data verification module 102 is used for supervising information data provided by a background verification examinee and judging the accuracy and the integrity of the data content.
The method for judging the accuracy and the completeness of the data content comprises the following steps of:
verifying whether the name of the examinee is matched with an effective certificate such as an identity card, verifying whether the contact way of the examinee such as a mobile phone number is correct and can contact the examinee, verifying whether a mailbox address provided by the examinee is truly effective, sending a verification mail to verify, judging whether the head portrait uploaded by the examinee is the examinee, checking whether other basic information filled by the examinee such as the address is complete and authentic, analyzing the operation behaviors of the examinee at different nodes, judging whether the behaviors are natural and reasonable, manually checking all the information provided by the examinee, finding out problems to inquire and verify, feeding back a verification result to the examinee, and requiring the examinee to perfect or modify non-compliance information according to requirements.
And the encryption storage module 103 is used for carrying out encryption storage on the information data by utilizing a homomorphic encryption algorithm.
The method for encrypting and storing the information data by using the homomorphic encryption algorithm comprises the following steps:
the supervision background generates a public key and a secret key in advance on the basis of a homomorphic encryption algorithm according to the information data, and encrypts the information data by using the secret key to obtain an information document set;
the supervision background extracts all different keywords from the information document set in the encryption domain, constructs a keyword set, encrypts the keywords through a public key and obtains an encrypted keyword set;
and re-encrypting the information document set and the keyword set by using the public key, and uploading the information document set and the keyword set to a memory supported by homomorphic encryption.
The access control module 104 is configured to improve a single management mechanism in the memory based on the secret sharing algorithm, and set multiple groups of management common restriction control access.
Wherein improving a single management mechanism in the memory based on a secret sharing algorithm, setting a plurality of groups of management common restriction control access includes:
the storage receives the information data to generate a group public key and a group private key, and the group private key is used as a private value, different prime numbers are randomly selected, and polynomial function construction is carried out on the premise of different prime numbers;
obtaining fragments of a group private key according to a polynomial function result, and respectively generating different fragments to the invigilation manager according to the number of the invigilation manager;
when different visitors initiate memory access, the visitors locally generate homomorphic encrypted public keys and private keys, the public keys are sent to each proctorial manager, and the private keys are sent to the memory through a secure channel;
the proctor selects the random number, encrypts the random number by using the respective group private key fragments to obtain a ciphertext, and sends the ciphertext to the memory;
the memory calculates the ciphertext product to obtain a ciphertext block and calculates a ciphertext code, the memory sends the ciphertext block to a visitor, and the ciphertext code is sent to a proctorial manager;
the visitor logs in the memory according to the ciphertext block and verifies through the ciphertext code at the proctorial manager;
if the verification is passed, the visitor is allowed to access the query data, and if the verification is not passed, the visitor is not allowed to access the query data.
It is to be noted that, the homomorphic encryption and secret sharing algorithm are adopted to perform secure storage and access control on information data, so as to realize strong encryption of examinee data in the storage process, improve data security, and design multiple groups of management mechanisms by using the secret sharing algorithm, so as to realize distributed control of storage access, and improve security and reliability of the system.
The discriminant design unit 2 is used for dividing the examinees into normal examinees and special examinees according to the personal data of the examinees and designing corresponding examination modes.
In this embodiment, the discriminant design unit 2 includes an examinee classification module 201, an examination design module 202, an examinee recording module 203, and an examination execution module 204.
The test design module 202 is connected with the test recording module 203, and the test recording module 203 is connected with the test execution module 204.
The test taker classification module 201 is configured to divide the test taker into a normal test taker and a special test taker according to personal information of the test taker.
Specifically, dividing the test taker into a normal test taker and a special test taker according to personal information conditions of the test taker comprises:
selecting vision and hearing information data in the information data, and respectively quantizing and converting the vision and hearing information data of the examinee into signal data by utilizing digital optics and digital audio technology;
windowing is carried out on the vision and hearing signal data by adopting short-time Fourier transform;
extracting vision degree in vision signal data, carrying out probability analysis on the vision degree, and classifying vision types through the probability analysis to obtain two groups of normal vision and impaired vision;
and mapping the hearing data to a high-dimensional feature space by using a support vector machine, constructing an optimal classification hyperplane, and classifying to obtain two groups of normal hearing and impaired hearing.
The test design module 202 is configured to establish different types of test modes based on genetic algorithms and task parameters.
Specifically, establishing different types of examination modes based on genetic algorithm and task parameters includes:
based on task parameters and teaching modes, comprehensively considering examination duration, examination difficulty and examination plans to establish a multi-machine collaborative operation function;
constructing a multi-variant grouping genetic algorithm according to a multi-machine collaborative operation function, designing two-section codes, wherein the two-section codes comprise a normal mode code and a special mode code, and designing an examination mode under the normal mode;
analyzing the influence of different items in a multi-machine collaborative operation function on the hearing and eyesight of a test taker aiming at the coded content in a special mode, and determining the weight coefficient of the eyesight and the hearing;
and selecting a limit selection method and a weight coefficient to design an examination mode in a special mode, and performing simulation aiming at the examination mode.
The expression of the multi-machine collaborative operation function is as follows:
the expression of the multi-machine collaborative job function is:
；
in the method, in the process of the invention,findicating the cooperation of a plurality of machines,、/>and->Weights respectively representing examination duration, examination difficulty and examination plan, +.>Represent the firstiLoad parameters of the field examination application device, +.>Represent the firstiThe upper limit of the load of the field examinee,mindicating the number of fields of the examination.
The examinee recording module 203 is used for recording and tracking the whole examination process of the examinee.
Specifically, the whole process of recording and tracking the examination of the examinee mainly comprises the following steps:
the method comprises the steps of recording the time and place of clicking to start the test by an examinee in the beginning stage of the test, periodically recording and storing the current answering page of the examinee in the test process, and monitoring the operation record of the examinee computer in the test process, wherein the operation record comprises a browser and an opening and closing log of an application program.
The network access record of the examinee is monitored in the examination process, the network access record comprises access of a search engine and a non-examination related website, facial expression and eyeball dynamic of the examinee are collected in the examination process, the concentration degree of the examinee is judged, the time of the examinee submitting an answer sheet and finishing the examination is recorded after the examination is finished, the complete answer details and automatic scoring results of the examinee are stored, the examination behaviors of the examinee can be effectively supervised through the whole recording process, cheating behaviors are prevented, and examination fairness is guaranteed.
The test execution module 204 is configured to manage and coordinate actual operation processes of the test.
And the examination reminding unit 3 is used for making different reminding plans based on the examination mode and the examination plan and sending examination reminding to the examinee.
In this embodiment, the examination reminding unit 3 includes an examination planning module 301, a reminding planning module 302, a reminding sending module 303 and a reminding tracking module 304.
The examination planning module 301 is connected with the reminder planning module 302, the reminder planning module 302 is connected with the reminder sending module 303, and the reminder sending module 303 is connected with the reminder tracking module 304.
The examination planning module 301 is configured to store and manage various types of information of an examination, where the information includes an examination place, a date, an examination duration, and an examination subject.
Specifically, various types of information for storing and managing an examination mainly include:
according to the examination work, a structure of an examination information data table is designed, basic data are collected and input, examination registration information, examination arrangement information and the like are collected and input into corresponding database tables, a data dictionary is built, the names and meanings of the word segments of the data tables are recorded, and data consistency is guaranteed.
The test information input, query, modification and statistical analysis functions are realized based on the database, the test information management system is developed, the regular data maintenance is carried out, the database optimization, the data cleaning, the addition of new table fields and the like are included, and various types of test information are efficiently and safely stored and utilized through scientific database design and perfect management flow.
The reminding plan module 302 is configured to make different reminding plans according to the examination plan and the category of the examinee.
Wherein, the making of different reminding plans according to the examination plan and the category of the examinee comprises:
after the test taker logs in the platform to finish the test registration operation, the test platform sends a message prompt to the test taker;
identifying the category of the examinee of the category of the examinee at the examination platform according to login information of the examinee, generating a link for a normal examinee by the examination platform, and setting corresponding selection data in the link;
normal examinees click into the links, fill in service requests in the links, determine the sending frequency and time of the reminding, formulate the content when sending the reminding according to the reminding frequency and time selected by the examinees, and select corresponding reminding modes in the links, wherein the reminding modes comprise telephone reminding, alarm reminding and short message reminding;
after the examination platform identifies a special examinee, the frequency and time of transmission are determined through the voice reminding service if the examination platform is the visually impaired examinee, and the frequency and time of transmission are determined through the short message reminding service if the examination platform is the hearing impaired examinee.
And the reminding sending module 303 is used for sending the examination reminding to the examinee according to the reminding plan at the appointed time.
Specifically, sending an examination reminder to the test taker according to the specified time includes:
and extracting examinee data such as names, mobile phone numbers and other contact modes needing to be sent from the information data system, triggering a timing task to send according to a time point set by a reminding plan, and generating dynamic examination reminding short message content which can contain important information such as examination time, examination place and the like.
And calling a short message sending interface to send the short message content to the mobile phone number of the examinee, returning a result by the short message interface, recording the sending state of each short message, analyzing the sending state of the short message, carrying out subsequent resending of the failed short message, and deleting the reminding plan and the short message sending record of the examination after the examination is finished.
The reminder tracking module 304 is configured to track a sending state of the reminder, and confirm whether the examinee receives the reminder.
Specifically, tracking the sending state of the reminder, and confirming whether the examinee receives the reminder includes:
after the short message interface is called to send the examination reminding short message, the short message interface returns a sending status code of each short message.
Classifying according to the returned state codes: and if the short message is successfully transmitted, the short message is normally transmitted to the mobile phone of the examinee, if the short message is transmitted failure, such as error of the mobile phone number, and the like, the transmission state result is recorded into a database state table, is associated with the information data table, the state table is analyzed, and the number of successful transmission and the number of failed transmission are counted.
And carrying out subsequent processing on the failed sent short message: checking whether the failed mobile phone number is correct or not from the contact list of the examinee; attempts to resend the failed message.
After the examination is finished, through the feedback of the examinee or the check-in condition of the examination, the examinee actually receiving the reminding is confirmed, the reminding sending effect is evaluated by comparing with the state table data, the number of missing examinees is counted, the reason is analyzed, the reminding mechanism is perfected, the training is recorded, the follow-up reminding working quality is improved, and the actual effect of the reminding sending can be effectively tracked and evaluated in the above steps.
And the examination management unit 4 is used for calling examination contents, receiving the input of the examinee and storing answer data in real time.
Specifically, the examination content is called, the input of an examinee is received, and answer data is stored in real time:
after an examinee logs in an online examination system, the system calls examination paper content to be loaded to the examinee terminal, the examinee starts answering, answering data are submitted to a server in real time through Ajax and other technologies, formatting is carried out after the server receives the answering data, information such as question numbers and answer content is extracted, the extracted answering information is stored in a temporary answering table, and the temporary answering table is associated with the information data for storage, so that the storage according to the examinee is realized.
Meanwhile, a background process is started, temporary answer sheet data are summarized and imported into the main answer sheet data at regular intervals, full-scale storage is achieved, and after an examinee submits an answer, a page feeds back a submitted state in real time, so that repeated submission is avoided. Through the steps, the real-time receiving and storing of the on-line answer questions of the examinee are realized, and support is provided for subsequent automatic reading and score statistics.
And the invigilation analysis unit 5 is used for analyzing the invigilation video by using a deep learning technology and automatically detecting whether cheating conditions exist in the examinee.
In this embodiment, analyzing the invigilated video by using the deep learning technology, and automatically detecting whether the cheating situation exists in the examinee includes:
collecting a large amount of marked data, recording cheating behavior video clips of examinees, building a convolutional neural network model by using a deep learning framework, extracting features of the video frames, training the model on a marked data set, enabling the model to learn how to identify video features of different cheating behaviors, evaluating the identification accuracy of the trained model on a test set, and continuously optimizing the model structure and the parameter improvement effect.
The actual invigilation video is input into a trained model for reasoning and predicting, the model gives the cheating probability score of each video segment, the cheating suspicion exists when the cheating probability score exceeds a threshold value, the recognition result is manually rechecked, false alarm is reduced, a suspected examinee is monitored and confirmed again when necessary, the detection result is recorded into a database, a report is generated after the examination is finished, video content recognition is realized through deep learning, the invigilation work can be effectively assisted, and the reliability of the result is still ensured by manual participation.
Specifically, deep learning is a machine learning method that learns data representations or features using an artificial neural network, which accomplishes tasks through the distribution of learning data, rather than through programming.
In summary, by means of the above technical scheme, the invention provides an online examination system, firstly, personal data of an examinee is collected through an information collecting unit, basic data is provided for dividing the examinee type and designing an examination mode subsequently, a design distinguishing and designing unit designs an individualized examination mode according to the examinee type, examination individuation is achieved, meanwhile, a differentiated prompt is sent through an examination prompting unit based on the examination mode, the examination time of the examinee is prompted conveniently, an examination management unit is arranged to store answer data in real time, original data support is provided for examination analysis, cheating is detected finally through an examination analysis unit, examination public trust is improved, functions of classification identification, individuation service, automatic examination and the like of the examinee are integrally achieved, examination efficiency is improved, and the system has good integral effect. The invention adopts homomorphic encryption and secret sharing algorithm to carry out safe storage and access control on information data, realizes strong encryption of examinee data in the storage process, improves the data security, designs a plurality of groups of management mechanisms by using the secret sharing algorithm, realizes distributed control of storage access, prevents single-point authority abuse, improves the system security, distributes group private key fragments to a plurality of managers for holding, can finish verification only by needing multiparty participation, greatly increases the difficulty of recovering the whole private key, prevents key leakage, requires multiparty participation for data access, and improves the security and reliability of the system. According to the invention, visual and hearing information is quantified through a digital technology, characteristics are extracted to carry out probability analysis and support vector machine classification, automatic classification of visual and hearing ability of an examinee is realized, normal examinee and different types of special examinees are provided with basis for the design of a follow-up personalized examination mode, a multi-machine collaborative operation function is established, two-section codes are designed based on a genetic algorithm, examination modes are designed for the normal examinee and the special examinee respectively, personalized service is realized, and the intelligent personalized online examination system is facilitated to be constructed, and the examination service level is improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. The on-line examination system based on the deep learning technology is characterized by comprising an information acquisition unit (1), a discrimination design unit (2), an examination reminding unit (3), an examination management unit (4) and an invigilation analysis unit (5);
the information acquisition unit (1) is connected with the discrimination design unit (2), the discrimination design unit (2) is connected with the examination reminding unit (3), the examination reminding unit (3) is connected with the examination management unit (4), and the examination management unit (4) is connected with the invigilation analysis unit (5);
the information acquisition unit (1) is used for acquiring personal data of the examinee and encrypting and storing the data;
the judging and designing unit (2) is used for dividing the examinees into normal examinees and special examinees according to the personal data of the examinees and designing corresponding examination modes;
the examination reminding unit (3) is used for making different reminding plans based on the examination mode and the examination plan and sending examination reminding to the examinee;
the examination management unit (4) is used for calling examination contents, receiving input of an examinee and storing answer data in real time;
and the invigilation analysis unit (5) is used for analyzing the invigilation video by using a deep learning technology and automatically detecting whether cheating conditions exist in the examinee.
2. The online examination system based on the deep learning technology according to claim 1, wherein the information acquisition unit (1) comprises a user registration module (101), a data verification module (102), an encryption storage module (103) and an access control module (104);
the user registration module (101) is connected with the data verification module (102), the data verification module (102) is connected with the encryption storage module (103), and the encryption storage module (103) is connected with the access control module (104);
the user registration module (101) is used for providing information data for the examinee login examination platform, wherein the information data comprises personal information, physical conditions, academic backgrounds and personality characteristics;
the data verification module (102) is used for supervising information data provided by a background verification examinee and judging the accuracy and the integrity of the data content;
the encryption storage module (103) is used for encrypting and storing the information data by using a homomorphic encryption algorithm;
the access control module (104) is configured to modify a single management mechanism in the memory based on a secret sharing algorithm, and to set a plurality of groups of management common restriction control access.
3. The system for on-line examination based on the deep learning technique of claim 2, wherein the encrypting and storing the information data using the homomorphic encryption algorithm comprises:
the supervision background generates a public key and a secret key in advance on the basis of a homomorphic encryption algorithm according to the information data, and encrypts the information data by using the secret key to obtain an information document set;
the supervision background extracts all different keywords from the information document set in the encryption domain, constructs a keyword set, encrypts the keywords through a public key and obtains an encrypted keyword set;
and re-encrypting the information document set and the keyword set by using the public key, and uploading the information document set and the keyword set to a memory supported by homomorphic encryption.
4. An online examination system based on a deep learning technique according to claim 3, wherein the secret sharing algorithm improves a single management mechanism in the memory, and setting a plurality of groups of management common limit control access comprises:
the storage receives the information data to generate a group public key and a group private key, and the group private key is used as a private value, different prime numbers are randomly selected, and polynomial function construction is carried out on the premise of different prime numbers;
obtaining fragments of a group private key according to a polynomial function result, and respectively generating different fragments to the invigilation manager according to the number of the invigilation manager;
when different visitors initiate memory access, the visitors locally generate homomorphic encrypted public keys and private keys, the public keys are sent to each proctorial manager, and the private keys are sent to the memory through a secure channel;
the proctor selects the random number, encrypts the random number by using the respective group private key fragments to obtain a ciphertext, and sends the ciphertext to the memory;
the memory calculates the ciphertext product to obtain a ciphertext block and calculates a ciphertext code, the memory sends the ciphertext block to a visitor, and the ciphertext code is sent to a proctorial manager;
the visitor logs in the memory according to the ciphertext block and verifies through the ciphertext code at the proctorial manager;
if the verification is passed, the visitor is allowed to access the query data, and if the verification is not passed, the visitor is not allowed to access the query data.
5. The on-line examination system based on the deep learning technology according to claim 1, wherein the discriminant design unit (2) comprises an examinee classification module (201), an examination design module (202), an examinee recording module (203) and an examination execution module (204);
the test taker classifying module (201) is connected with the test design module (202), the test design module (202) is connected with the test taker recording module (203), and the test taker recording module (203) is connected with the test execution module (204);
the examinee classification module (201) is used for classifying the examinees into normal examinees and special examinees according to personal information conditions of the examinees;
the examination design module (202) is used for establishing examination modes of different types based on genetic algorithm and task parameters;
the examinee recording module (203) is used for recording and tracking the whole examination process of the examinee;
the examination execution module (204) is used for managing and coordinating the actual operation process of the examination.
6. The system of claim 5, wherein the classifying the test taker into a normal test taker and a special test taker according to personal information of the test taker comprises:
selecting vision and hearing information data in the information data, and respectively quantizing and converting the vision and hearing information data of the examinee into signal data by utilizing digital optics and digital audio technology;
windowing is carried out on the vision and hearing signal data by adopting short-time Fourier transform;
extracting vision degree in vision signal data, carrying out probability analysis on the vision degree, and classifying vision types through the probability analysis to obtain two groups of normal vision and impaired vision;
and mapping the hearing data to a high-dimensional feature space by using a support vector machine, constructing an optimal classification hyperplane, and classifying to obtain two groups of normal hearing and impaired hearing.
7. The system of claim 6, wherein the establishing test patterns of different types based on genetic algorithm and task parameters comprises:
based on task parameters and teaching modes, comprehensively considering examination duration, examination difficulty and examination plans to establish a multi-machine collaborative operation function;
constructing a multi-variant grouping genetic algorithm according to a multi-machine collaborative operation function, designing a two-section code, wherein the two-section code comprises a normal mode code and a special mode code, and designing an examination mode under the normal mode;
analyzing the influence of different items in a multi-machine collaborative operation function on the hearing and eyesight of a test taker aiming at the coded content in a special mode, and determining the weight coefficient of the eyesight and the hearing;
and selecting a limit selection method and a weight coefficient to design an examination mode in a special mode, and performing simulation aiming at the examination mode.
8. The system of claim 7, wherein the expression of the multi-machine collaborative work function is:
；
in the method, in the process of the invention,frepresenting multi-machine collaboration;
、/>and->Respectively representing the examination duration, the examination difficulty and the weight of the examination plan;
represent the firstiLoad parameters of the field test application device;
represent the firstiThe upper limit of the field test taker load;
mindicating the number of fields of the examination.
9. The online examination system based on the deep learning technology according to claim 1, wherein the examination reminding unit (3) comprises an examination planning module (301), a reminding planning module (302), a reminding sending module (303) and a reminding tracking module (304);
the examination planning module (301) is connected with the reminding planning module (302), the reminding planning module (302) is connected with the reminding sending module (303), and the reminding sending module (303) is connected with the reminding tracking module (304);
the examination planning module (301) is used for storing and managing various types of information of examination, wherein the information comprises examination places, dates, examination duration and examination subjects;
the reminding plan module (302) is used for making different reminding plans according to the examination plans and categories of the examinees;
the reminding sending module (303) is used for sending examination reminding to the examinee according to the reminding plan at the appointed time;
the reminding tracking module (304) is used for tracking the sending state of the reminding and confirming whether the examinee receives the reminding.
10. An online examination system based on a deep learning technique as claimed in claim 9, wherein the developing a different reminder plan according to the category of the examination plan and the examinee includes:
after the test taker logs in the platform to finish the test registration operation, the test platform sends a message prompt to the test taker;
identifying the category of the examinee of the category of the examinee at the examination platform according to login information of the examinee, generating a link for a normal examinee by the examination platform, and setting corresponding selection data in the link;
normal examinees click into the links, fill in service requests in the links, determine the sending frequency and time of the reminding, formulate the content when the reminding is sent according to the reminding frequency and time selected by the examinees, and select corresponding reminding modes in the links, wherein the reminding modes comprise telephone reminding, alarm reminding and short message reminding;
after the examination platform identifies a special examinee, the frequency and time of transmission are determined through the voice reminding service if the examination platform is the visually impaired examinee, and the frequency and time of transmission are determined through the short message reminding service if the examination platform is the hearing impaired examinee.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311555933.2A CN117291773A (en) | 2023-11-21 | 2023-11-21 | Online examination system based on deep learning technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311555933.2A CN117291773A (en) | 2023-11-21 | 2023-11-21 | Online examination system based on deep learning technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117291773A true CN117291773A (en) | 2023-12-26 |
Family
ID=89253775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311555933.2A Pending CN117291773A (en) | 2023-11-21 | 2023-11-21 | Online examination system based on deep learning technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117291773A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170263142A1 (en) * | 2016-03-08 | 2017-09-14 | Gholam Hossein Zereshkian | Anti-cheating device for online examination |
| CN108574777A (en) * | 2018-03-28 | 2018-09-25 | 北京小米移动软件有限公司 | Information prompting method and device |
| CN111311455A (en) * | 2020-01-17 | 2020-06-19 | 广东德诚科教有限公司 | Examination information matching method and device, computer equipment and storage medium |
| CN113706348A (en) * | 2021-08-31 | 2021-11-26 | 贵州东冠科技有限公司 | Online automatic invigilation system and method based on face recognition |
-
2023
- 2023-11-21 CN CN202311555933.2A patent/CN117291773A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170263142A1 (en) * | 2016-03-08 | 2017-09-14 | Gholam Hossein Zereshkian | Anti-cheating device for online examination |
| CN108574777A (en) * | 2018-03-28 | 2018-09-25 | 北京小米移动软件有限公司 | Information prompting method and device |
| CN111311455A (en) * | 2020-01-17 | 2020-06-19 | 广东德诚科教有限公司 | Examination information matching method and device, computer equipment and storage medium |
| CN113706348A (en) * | 2021-08-31 | 2021-11-26 | 贵州东冠科技有限公司 | Online automatic invigilation system and method based on face recognition |
Non-Patent Citations (1)
| Title |
|---|
| 王猛 等: "基于多变异分组遗传算法的多机协同作业静态任务分配", 《农业机械学报》, vol. 52, no. 7, pages 19 - 28 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105243910B (en) | Battle and exercise system of making a breakthrough based on Mobile solution | |
| CN107251033A (en) | System and method for carrying out active user checking in online education | |
| CN108389147A (en) | Item difficulty hierarchical processing method and system | |
| CN109492595A (en) | Behavior prediction method and system suitable for fixed group | |
| WO2021042842A1 (en) | Interview method and apparatus based on ai interview system, and computer device | |
| CN109871673A (en) | Based on the lasting identity identifying method and system in different context environmentals | |
| US11657295B2 (en) | Cognitive automation platform for dynamic unauthorized event detection and processing | |
| CN111461636A (en) | Virtual robot-based government affair service platform and application | |
| KR20100060555A (en) | Virtual university using rfid technology and artificial intelligence | |
| CN113873088A (en) | Voice call interaction method and device, computer equipment and storage medium | |
| CN113761217A (en) | Artificial intelligence-based question set data processing method and device and computer equipment | |
| CN117291773A (en) | Online examination system based on deep learning technology | |
| CN114971425B (en) | Database information monitoring method, device, equipment and storage medium | |
| Pavlenko et al. | Collection and analysis of digital footprints in LMS | |
| EP3973525A1 (en) | Method of delivering webinars with certified participation | |
| CN114971658B (en) | Anti-fraud propaganda method, system, electronic equipment and storage medium | |
| CN116777690A (en) | College student party continuous education tracking evaluation system and method based on multi-mode data analysis | |
| KR101802377B1 (en) | Cloud sourcing service system for knowledge acquisition based on quiz type | |
| CN111612659B (en) | Automatic scoring system and scoring method for online financial examination | |
| Qi et al. | Temporal models for personalized grade prediction in massive open online courses | |
| Zhou et al. | Design of the intelligent internship management platform for vocational colleges | |
| Deodhar et al. | Prediction of Online Academic dishonesty Using the Voting Ensemble Machine Learning Method | |
| WO2019156590A1 (en) | Method and system for calculating an illegal activity risk index of job applicants and current employees | |
| CN117972645B (en) | Fire-fighting facility operator real-operation online examination system and method | |
| CN111538982B (en) | Multistage multi-element serial authentication method and system for smart education cloud platform |
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 |