CN112256755A - Student abnormal behavior analysis method based on deep learning - Google Patents
Student abnormal behavior analysis method based on deep learning Download PDFInfo
- Publication number
- CN112256755A CN112256755A CN202011123849.XA CN202011123849A CN112256755A CN 112256755 A CN112256755 A CN 112256755A CN 202011123849 A CN202011123849 A CN 202011123849A CN 112256755 A CN112256755 A CN 112256755A
- Authority
- CN
- China
- Prior art keywords
- data
- students
- student
- abnormal
- index
- 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
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 51
- 238000013135 deep learning Methods 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 32
- 230000006399 behavior Effects 0.000 claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 230000004927 fusion Effects 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 5
- 230000037213 diet Effects 0.000 claims description 3
- 235000005911 diet Nutrition 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000013501 data transformation Methods 0.000 claims 1
- 230000009466 transformation Effects 0.000 claims 1
- 230000002159 abnormal effect Effects 0.000 abstract description 8
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- 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 student abnormal behavior analysis method based on deep learning, which comprises the following steps: collecting relevant data of students in consumption, life and learning aspects of schools and preprocessing the data; secondly, analyzing the usability of data and evaluating the school behaviors of students, constructing a student portrait feature library, depicting the behavior features of the students through different indexes, and quantizing the indexes according to the acquired data; constructing an abnormal behavior prediction model based on the wide & deep neural network according to the behavior characteristics; and (4) combining an abnormal behavior prediction model to carry out prediction analysis on the abnormal behaviors of the students. The invention can efficiently process the fusion of different data, has high parallelization program and stable system; meanwhile, the prediction model can simultaneously learn low-order and high-order combination characteristics, a linear model and a Deep model are mixed, and therefore the method can be trained more quickly and accurately and can accurately predict abnormal students.
Description
Technical Field
The invention relates to a student abnormal behavior analysis method based on deep learning, and belongs to the technical field of data query.
Background
With the rapid development of modern information technology and the wide application of technologies such as internet of things, big data and artificial intelligence, the campus is continuously deep in digital construction, and a large amount of data related to students are accumulated in the campus, including data of all dimensions such as campus student card system data, student score data, student course selection system data, network use log data, dormitory attendance data and library borrowing record data, so that data support is provided for analyzing the daily behavior rules of the students and carrying out abnormal analysis and early warning.
At present, consumption habit clustering analysis is generally performed on campus card consumption behaviors of students by adopting a K-means clustering algorithm, abnormal student sample candidate sets are screened out through outliers in results, and abnormal behavior association degree analysis is performed on the student behaviors through an association rule algorithm. Besides the clustering algorithm, the classification algorithm can also be used for analyzing abnormal behaviors of students, researchers develop a set of big data system student portrait based on real-time behavior data of the students in the campus for learning and living by combining questionnaire survey, demographics and other related data, and realize abnormal behavior prediction and early warning of the students through analysis of daily behaviors.
However, in the actual operation process, the cross-correlation relationship among different dimensional data is not fully considered in the existing prediction method, and the accuracy of the abnormal prediction may be affected. Moreover, with the continuous enrichment of sample data, the training of a large number of sparse sample usage models becomes more complicated, and the training time becomes longer, affecting the stability of algorithm implementation.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a student abnormal behavior analysis method based on deep learning, which can efficiently process the fusion of different data, has high parallelization program and stable system; meanwhile, the prediction model can simultaneously learn low-order and high-order combination characteristics, a linear model and a Deep model are mixed, and therefore the method can be trained more quickly and accurately and can accurately predict abnormal students.
In order to achieve the purpose, the invention adopts the following technical scheme: a student abnormal behavior analysis method based on deep learning comprises the following steps:
step S1, data acquisition and preprocessing: collecting relevant data of students in the aspects of school consumption, life and learning, carrying out data cleaning, data conversion and data protocol preprocessing on the collected multi-source data, and storing the processed data to a data warehouse;
step S2, constructing a student portrait feature library: the method comprises the steps of establishing a student portrait feature library by analyzing the availability of data in a data warehouse and evaluating the school behaviors of students, describing the behavior features of the students through different indexes, and quantizing the indexes according to the acquired data;
step S3, creating an abnormal behavior prediction model: constructing an abnormal behavior prediction model based on the wide & deep neural network according to the behavior characteristics;
and step S4, combining the abnormal behavior prediction model to carry out prediction analysis on the abnormal behaviors of the students, and sequencing the prediction results from top to bottom to form an early warning information list.
In the method for analyzing abnormal behaviors of students based on deep learning, the data collected in the step S1 include campus card consumption, dormitory attendance, library borrowing, student educational administration information and student score data.
In the method for analyzing abnormal behaviors of students based on deep learning, the data cleaning in the step S1 is to perform data fusion on diversified data, convert the diversified data into a uniform data format, filter the personnel identity information data and clean irrelevant personnel record data; and simultaneously removing redundant data and partial missing data.
In the method for analyzing abnormal behaviors of students based on deep learning, the data conversion in the step S1 is conversion of compression, generalization and normalization of the cleaned data by using statistical, clustering and classification methods.
In the method for analyzing abnormal behaviors of students based on deep learning, the consumption rule indexes of the students in the step S2 include: monthly consumption, consumption frequency, monthly consumption interval, consumption place; the student life habit indexes comprise: diet index, daily life index, exercise index, activity area index; the student learning indexes comprise: library access index, score index, reading index, course index, and learning duration index.
In the deep learning-based student abnormal behavior analysis method, the step S3 of constructing the wide & deep neural network-based abnormal behavior prediction model specifically includes: the behavior characteristics are divided into continuous characteristics and classified characteristics, meanwhile, local intersection is carried out on some characteristics, a filtering threshold value is set for the classified characteristics, the characteristics are mapped to a 32-dimensional embedding layer and used as the input of a neural network together with the original continuous characteristics, then through back propagation of gradients, a mini-batch stochastic optimization training parameter is used, and an AdaGrad algorithm is used for the deep part.
Compared with the prior art, the method can efficiently process the fusion of different data, has high parallelization program and stable system; meanwhile, the prediction model can simultaneously learn low-order and high-order combination characteristics, a linear model and a Deep model are mixed, and therefore the method can be used for training more quickly and training and learning more accurately and can accurately predict abnormal students; the invention can be used in campus life, and can analyze student behaviors based on multi-source data such as student campus card consumption, dormitory attendance, library borrowing, student educational administration information, student scores and the like, and early warn students with possible abnormal behaviors to maintain campus safety.
Drawings
FIG. 1 is a schematic view of the present invention;
FIG. 2 is a schematic diagram of an abnormal behavior prediction model based on wide & deep neural network according to the present invention;
FIG. 3 is a diagram illustrating a translation corresponding to FIG. 2.
Detailed Description
The technical solutions in the implementation of the present invention will be made clear and fully described below with reference to the accompanying drawings, and the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1 and fig. 2, the method for analyzing abnormal behaviors of students based on deep learning provided by the invention comprises the following steps:
step S1, data acquisition and preprocessing: collecting relevant data of students in the aspects of school consumption, life and learning, carrying out data cleaning, data conversion and data protocol preprocessing on the collected multi-source data, and storing the processed data to a data warehouse;
step S2, constructing a student portrait feature library: the method comprises the steps of establishing a student portrait feature library by analyzing the availability of data in a data warehouse and evaluating the school behaviors of students, describing the behavior features of the students through different indexes, and quantizing the indexes according to the acquired data;
step S3, creating an abnormal behavior prediction model: according to the behavior characteristics, an abnormal behavior prediction model based on the wide & deep neural network is built, and the built prediction model is shown in figure 2;
and step S4, combining the abnormal behavior prediction model to carry out prediction analysis on the abnormal behaviors of the students, and sequencing the prediction results from top to bottom to form an early warning information list.
In the method for analyzing abnormal behaviors of students based on deep learning, the data collected in the step S1 include campus card consumption, dormitory attendance, library borrowing, student educational administration information and student score data.
In the method for analyzing abnormal behaviors of students based on deep learning, the data cleaning in the step S1 is to perform data fusion on diversified data, convert the diversified data into a uniform data format, filter the identity information data of the personnel, and clean the record data of irrelevant personnel such as teaching staff and the like; and simultaneously removing redundant data and partial missing data.
In the method for analyzing abnormal behaviors of students based on deep learning, the data conversion in the step S1 is conversion of compression, generalization and normalization of the cleaned data by using statistical, clustering and classification methods. And corresponding data conversion is carried out on different data, so that the data is more meaningful and more targeted.
In the method for analyzing abnormal behaviors of students based on deep learning, the consumption rule indexes of the students in the step S2 include: monthly consumption, consumption frequency, monthly consumption interval, consumption place; the student life habit indexes comprise: diet index, daily life index, exercise index, activity area index; the student learning indexes comprise: library access index, score index, reading index, course index, and learning duration index. The method comprehensively considers the relevant data of students in all aspects, and takes the data as basic parameters to construct the student portrait characteristic set, so as to construct an abnormal behavior prediction model, realize more accurate training and learning and predict abnormal students more accurately.
In the deep learning-based student abnormal behavior analysis method, the step S3 of constructing the wide & deep neural network-based abnormal behavior prediction model specifically includes: the behavior characteristics are divided into continuous characteristics and classified characteristics, meanwhile, local intersection is carried out on some characteristics, a filtering threshold value is set for the classified characteristics, the characteristics are mapped to a 32-dimensional embedding layer and used as the input of a neural network together with the original continuous characteristics, then through back propagation of gradients, a mini-batch stochastic optimization training parameter is used, and an AdaGrad algorithm is used for the deep part. Specifically, as shown in fig. 2, the corresponding Chinese meaning is as shown in fig. 3, and the left side is a continuous feature and is directly put into a neural network; and performing simple logistic regression and linear combination on the right side, and finally, taking the logistic regression and linear combination as the input of the neural network.
Example (b):
1. with the increasing importance of all colleges and universities on smart campuses, the construction of bedroom access control systems, classroom card punching systems, book borrowing systems, educational administration systems, dining room consumption systems and the like is complete. Through data analysis, data in the system are collected such as: and the access control time, the book borrowing, the internet surfing time, the score, the medical service, the student information and the like are cleaned and converted and stored in the data warehouse.
2. And taking out data corresponding to each student in the database, and forming a student portrait feature library such as a academic theme, a campus consumption theme, a book borrowing theme, a classroom check-in theme, a night-time theme, an internet surfing theme and the like by utilizing cluster analysis and correlation analysis.
3. And training abnormal behavior models of students. And taking the data obtained in the second step as model input, and generating sparse and dense features and labels.
1) The Wide part training data comprises student names and past abnormal behavior data.
2) For the Deep part of the model, the training data are data of various subject libraries and feature data obtained through statistics, and each class feature learns a 32-dimensional embedded vector. All the embeddings are then concatenated with the dense features, resulting in a dense vector of approximately 1200 dimensions. The concatenated vector is then fed into 3 ReLU layers and finally input into the logistic output unit.
4. And (4) according to the training model obtained in the step (3), predicting abnormal behaviors of the students, analyzing behaviors of the students such as excessive consumption, course escape, night lodging, couplet loss, academic abnormity, psychological abnormity and the like, and giving confidence of each behavior to form an early warning information list.
In conclusion, the invention can efficiently process the fusion of different data, has high parallelization program and stable system; meanwhile, the prediction model can simultaneously learn low-order and high-order combination characteristics, a linear model and a Deep model are mixed, and therefore the method can be used for training more quickly and training and learning more accurately and can accurately predict abnormal students; the invention can be used in campus life, and can analyze student behaviors based on multi-source data such as student campus card consumption, dormitory attendance, library borrowing, student educational administration information, student scores and the like, and early warn students with possible abnormal behaviors to maintain campus safety.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the embodiments may be appropriately combined to form other embodiments understood by those skilled in the art.
Claims (6)
1. A student abnormal behavior analysis method based on deep learning is characterized by comprising the following steps:
step S1, data acquisition and preprocessing: collecting relevant data of students in the aspects of school consumption, life and learning, carrying out data cleaning, data conversion and data protocol preprocessing on the collected multi-source data, and storing the processed data to a data warehouse;
step S2, constructing a student portrait feature library: the method comprises the steps of establishing a student portrait feature library by analyzing the availability of data in a data warehouse and evaluating the school behaviors of students, describing the behavior features of the students through different indexes, and quantizing the indexes according to the acquired data;
step S3, creating an abnormal behavior prediction model: constructing an abnormal behavior prediction model based on the wide & deep neural network according to the behavior characteristics;
and step S4, combining the abnormal behavior prediction model to carry out prediction analysis on the abnormal behaviors of the students, and sequencing the prediction results from top to bottom to form an early warning information list.
2. The method for analyzing abnormal behaviors of students based on deep learning of claim 1, wherein the data collected in step S1 includes campus card consumption, dormitory attendance, library borrowing, student educational administration information and student achievement data.
3. The method for analyzing abnormal behaviors of students based on deep learning of claim 1, wherein the data cleansing in step S1 is to perform data fusion on the multivariate data, convert the multivariate data into a uniform data format, filter the personnel identity information data, and cleanse the irrelevant personnel record data; and simultaneously removing redundant data and partial missing data.
4. The method for analyzing abnormal behaviors of students based on deep learning of claim 1, wherein the data transformation in the step S1 is a transformation of compressing, generalizing and standardizing the cleaned data by statistical, clustering and classification methods.
5. The method for analyzing abnormal behaviors of students based on deep learning as claimed in claim 1, wherein the consumption rule indexes of students in step S2 include: monthly consumption, consumption frequency, monthly consumption interval, consumption place; the student life habit indexes comprise: diet index, daily life index, exercise index, activity area index; the student learning indexes comprise: library access index, score index, reading index, course index, and learning duration index.
6. The method for analyzing abnormal behaviors of students based on deep learning as claimed in claim 1, wherein the step S3 of constructing the abnormal behavior prediction model based on wide & deep neural network specifically comprises: the behavior characteristics are divided into continuous characteristics and classified characteristics, meanwhile, local intersection is carried out on some characteristics, a filtering threshold value is set for the classified characteristics, the characteristics are mapped to a 32-dimensional embedding layer and used as the input of a neural network together with the original continuous characteristics, then through back propagation of gradients, a mini-batch stochastic optimization training parameter is used, and an AdaGrad algorithm is used for the deep part.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011123849.XA CN112256755A (en) | 2020-10-20 | 2020-10-20 | Student abnormal behavior analysis method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011123849.XA CN112256755A (en) | 2020-10-20 | 2020-10-20 | Student abnormal behavior analysis method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112256755A true CN112256755A (en) | 2021-01-22 |
Family
ID=74245151
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011123849.XA Pending CN112256755A (en) | 2020-10-20 | 2020-10-20 | Student abnormal behavior analysis method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112256755A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113626499A (en) * | 2021-08-09 | 2021-11-09 | 青软创新科技集团股份有限公司 | Student portrait mining implementation method based on big data warehouse technology |
CN113688170A (en) * | 2021-08-20 | 2021-11-23 | 中国联合网络通信集团有限公司 | Campus management method, device, equipment and storage medium |
CN114372090A (en) * | 2021-12-31 | 2022-04-19 | 北京工业大学 | User reading behavior analysis and prediction system under big data environment |
CN114707488A (en) * | 2022-02-25 | 2022-07-05 | 马上消费金融股份有限公司 | Data processing method and device, computer equipment and storage medium |
CN114926312A (en) * | 2022-06-21 | 2022-08-19 | 广州新烨数码科技股份有限公司 | Data acquisition and analysis method and system based on artificial intelligence |
CN113626499B (en) * | 2021-08-09 | 2024-05-10 | 青软创新科技集团股份有限公司 | Student portrait mining implementation method based on big data number bin technology |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180052898A1 (en) * | 2016-08-22 | 2018-02-22 | Oracle International Corporation | System and method for dynamic, incremental recommendations within real-time visual simulation |
CN109191338A (en) * | 2018-08-22 | 2019-01-11 | 西北工业大学 | Students ' behavior method for early warning based on all-in-one campus card consumption data |
CN110111894A (en) * | 2019-05-15 | 2019-08-09 | 杭州华网信息技术有限公司 | The mental health method for early warning of behavior is serialized based on deep learning student |
CN110751261A (en) * | 2018-07-23 | 2020-02-04 | 第四范式(北京)技术有限公司 | Training method and system and prediction method and system of neural network model |
CN111308355A (en) * | 2020-03-14 | 2020-06-19 | 智洋创新科技股份有限公司 | Transformer substation storage battery state detection and analysis method based on deep learning |
CN111652291A (en) * | 2020-05-18 | 2020-09-11 | 温州医科大学 | Method for establishing student growth portrait based on group sparse fusion hospital big data |
CN111695800A (en) * | 2020-06-03 | 2020-09-22 | 南京中电科能技术有限公司 | Method for positioning abnormal electricity consumption behavior user through cloud edge collaborative step-by-step analysis |
CN111709575A (en) * | 2020-06-16 | 2020-09-25 | 北京工业大学 | Academic achievement prediction method based on C-LSTM |
-
2020
- 2020-10-20 CN CN202011123849.XA patent/CN112256755A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180052898A1 (en) * | 2016-08-22 | 2018-02-22 | Oracle International Corporation | System and method for dynamic, incremental recommendations within real-time visual simulation |
CN110751261A (en) * | 2018-07-23 | 2020-02-04 | 第四范式(北京)技术有限公司 | Training method and system and prediction method and system of neural network model |
CN109191338A (en) * | 2018-08-22 | 2019-01-11 | 西北工业大学 | Students ' behavior method for early warning based on all-in-one campus card consumption data |
CN110111894A (en) * | 2019-05-15 | 2019-08-09 | 杭州华网信息技术有限公司 | The mental health method for early warning of behavior is serialized based on deep learning student |
CN111308355A (en) * | 2020-03-14 | 2020-06-19 | 智洋创新科技股份有限公司 | Transformer substation storage battery state detection and analysis method based on deep learning |
CN111652291A (en) * | 2020-05-18 | 2020-09-11 | 温州医科大学 | Method for establishing student growth portrait based on group sparse fusion hospital big data |
CN111695800A (en) * | 2020-06-03 | 2020-09-22 | 南京中电科能技术有限公司 | Method for positioning abnormal electricity consumption behavior user through cloud edge collaborative step-by-step analysis |
CN111709575A (en) * | 2020-06-16 | 2020-09-25 | 北京工业大学 | Academic achievement prediction method based on C-LSTM |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113626499A (en) * | 2021-08-09 | 2021-11-09 | 青软创新科技集团股份有限公司 | Student portrait mining implementation method based on big data warehouse technology |
CN113626499B (en) * | 2021-08-09 | 2024-05-10 | 青软创新科技集团股份有限公司 | Student portrait mining implementation method based on big data number bin technology |
CN113688170A (en) * | 2021-08-20 | 2021-11-23 | 中国联合网络通信集团有限公司 | Campus management method, device, equipment and storage medium |
CN114372090A (en) * | 2021-12-31 | 2022-04-19 | 北京工业大学 | User reading behavior analysis and prediction system under big data environment |
CN114707488A (en) * | 2022-02-25 | 2022-07-05 | 马上消费金融股份有限公司 | Data processing method and device, computer equipment and storage medium |
CN114707488B (en) * | 2022-02-25 | 2024-02-09 | 马上消费金融股份有限公司 | Data processing method, device, computer equipment and storage medium |
CN114926312A (en) * | 2022-06-21 | 2022-08-19 | 广州新烨数码科技股份有限公司 | Data acquisition and analysis method and system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112256755A (en) | Student abnormal behavior analysis method based on deep learning | |
Vohra | Using the multiple case study design to decipher contextual leadership behaviors in Indian organizations | |
CN109636688A (en) | A kind of students ' behavior analysis system based on big data | |
CN111652291A (en) | Method for establishing student growth portrait based on group sparse fusion hospital big data | |
Yu | Academic Performance Prediction Method of Online Education using Random Forest Algorithm and Artificial Intelligence Methods. | |
CN111950708B (en) | Neural network structure and method for finding daily life habits of college students | |
CN111709575A (en) | Academic achievement prediction method based on C-LSTM | |
Bowers | Grandmother cells and localist representations: a review of current thinking | |
CN110993102A (en) | Campus big data-based student behavior and psychological detection result accurate analysis method and system | |
Deepika et al. | Relief-F and Budget Tree Random Forest Based Feature Selection for Student Academic Performance Prediction. | |
CN106055875A (en) | Dermatoglyph analysis and processing apparatus based on big data | |
CN117036126A (en) | College student comprehensive quality management system and method based on data analysis | |
Alibasa et al. | Predicting Mood from Digital Footprints Using Frequent Sequential Context Patterns Features | |
CN105975792A (en) | Big-data-based dermatoglyph analysis and processing device and method | |
Yang | Research on strategies of promoting mental health of higher vocational college students based on data mining | |
CN106021927A (en) | Dermatoglyph analysis and processing method based on big data | |
Jianyun | Big data assisted online teaching platform for ideological and political theory course in universities | |
Nguyen | Temporal spike attribution: A local feature-based explanation for temporally coded spiking neural networks | |
Wang et al. | Research on Abnormal Behavior Prediction by Integrating Multiple Indexes of Student Behavior and Text Information in Big Data Environment | |
US11983156B2 (en) | System and method for indexing large volumes and durations of temporally-based sensor datasets | |
Victoire et al. | An Efficient Approach to Detect Autism in Child Using Machine Learning and Deep Learning | |
CN115204496B (en) | Campus interpersonal relationship data analysis method and device | |
Lin et al. | Student’s performance prediction based on an improved multi-view hypergraph neural network | |
Yang | FCM Clustering on interaction pattern analysis of Chinese Language learner behavior | |
HOSSAIN et al. | Preventing Student’s Mental Health Problems with the Help of Data Mining |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210122 |
|
RJ01 | Rejection of invention patent application after publication |