CN111507874A - Intelligent campus AIOT big data visualization analysis method - Google Patents
Intelligent campus AIOT big data visualization analysis method Download PDFInfo
- Publication number
- CN111507874A CN111507874A CN202010305806.7A CN202010305806A CN111507874A CN 111507874 A CN111507874 A CN 111507874A CN 202010305806 A CN202010305806 A CN 202010305806A CN 111507874 A CN111507874 A CN 111507874A
- Authority
- CN
- China
- Prior art keywords
- data
- campus
- student
- classroom
- aiot
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 95
- 238000013079 data visualisation Methods 0.000 title claims description 10
- 230000000007 visual effect Effects 0.000 claims abstract description 56
- 230000014509 gene expression Effects 0.000 claims description 31
- 230000006399 behavior Effects 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 25
- 238000007781 pre-processing Methods 0.000 claims description 22
- 230000004927 fusion Effects 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 15
- 230000003993 interaction Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000005236 sound signal Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 230000007935 neutral effect Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000001815 facial effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000007726 management method Methods 0.000 abstract description 21
- 238000011161 development Methods 0.000 abstract description 8
- 238000007405 data analysis Methods 0.000 abstract description 5
- 230000006872 improvement Effects 0.000 abstract description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000002776 aggregation Effects 0.000 description 4
- 238000004220 aggregation Methods 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000013501 data transformation Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 4
- 238000012800 visualization Methods 0.000 description 4
- 238000007794 visualization technique Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012482 interaction analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Images
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—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
-
- 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
- G06F16/24—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
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- 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
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- 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
- G06F16/258—Data format conversion from or to a database
-
- 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
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
Abstract
The invention provides a visual analysis method for big data of an intelligent campus AIOT, which has the following advantages compared with the current campus management method: (1) various intelligent hardware products are connected through the AIOT platform, and face data of students and teachers are managed and analyzed in a centralized mode; (2) objective data analysis is provided for classroom management, so that data support is provided for decision and improvement of classroom management; (3) the database is built based on the AIOT platform, and the continuous development and construction of the smart campus can be supported.
Description
Technical Field
The invention relates to the technical field of smart campuses, in particular to a visual analysis method for big data of an AIOT (automated optical inspection) of a smart campus.
Background
With the continuous development of modern education, teachers, students and managers accumulate massive data in the teaching, living and management processes, and also grow at a faster speed, and the data become increasingly important intangible assets of schools. How to show, analyze and mine the data becomes a favorable power and basis for the rapid development of schools. The campus big data visual analysis is used as a basic platform for deep fusion of a smart campus and the Internet plus, and emphasizes acquisition, understanding and intelligent processing of various data such as teaching, scientific research, campus life and management and the like by using the Internet of things and cloud computing. The problems that the data analysis efficiency is low, the information and service connection is not tight enough, the management decision can not be supported systematically, and a good man-machine interaction analysis means is lacked in the modern education management can be solved.
The campus big data is not a concept which depicts huge data quantity, and can show diversification of data sources, diversification of data types and intellectualization of data processing and analysis. More importantly, based on the implicit relationship and value of deep mining and scientific analysis of a large amount of data, the research on the education big data is essentially converted into a new thinking mode, a new technology and a new problem solving mode. How to promote and support the application of big data in education evaluation of each layer, three problems are solved in a key way: firstly, the 'from which big data comes' how to collect campus big data by means of a high-quality modern education network; secondly, the reason why the big data is used is to explore the destination of the big data applied in the education management; and thirdly, how the big data are used, and how to analyze the data literacy of the educator from elaborately designing evaluation indexes, selecting proper big data processing technology and improving the data literacy of the educator. Education is advancing to the big data era, and is good at discovering data and winning survival space, and is good at mining data and winning development space, and is good at utilizing data and winning future competition.
With the development of the IOT technology (sensor, mobile network, communication standard, technology platform) and the AI (chip, algorithm), the smart device is more and more popular, and with the support of the AIOT, the smart device also has more intelligent functions, so that the building of an intelligent campus big data platform by means of the AIOT platform is an inevitable trend of development.
At present, the problems of campus management are mainly class attendance: laggard, inefficient, no data to look up, classroom interaction: not concentrate on, the effect is poor, course resource: unclear, difficult to use, low value, classroom analysis: subjective evaluation, no data support, and opacity.
Disclosure of Invention
In view of the above problems, the invention aims to provide a visual analysis method for big data of an intelligent campus AIOT, and aims to provide objective data analysis for classroom management through an AIOT platform, so as to provide data support for decision and improvement of classroom management.
The invention is realized in such a way, and the technical scheme adopted by the visual analysis method for big data of the intelligent campus AIOT is as follows: the intelligent campus AIOT big data visualization analysis method is used for classroom management and is connected with intelligent hardware equipment through an AIOT platform; the intelligent campus AIOT big data visualization analysis method comprises the following steps:
s1: the classroom data source acquired by the intelligent hardware equipment and the campus data source acquired by the campus original information system are divided into structured data, semi-structured data and unstructured data according to data structures, data transmission is carried out according to different functions and different structural classifications of the classroom data source and the campus data source, the data are stored in a new distributed database with Hadoop as a basic framework, and a heterogeneous integrated smart campus big data basic platform is constructed;
s2: carrying out data preprocessing on the classroom data source and the campus data source to clean data which do not meet requirements, constructing new attributes and expression modes, storing the preprocessed data, and reconstructing the preprocessed data into a big data base platform of the smart campus;
s3: extracting data required by classroom management analysis from the smart campus big data base platform, designing a data feature fusion algorithm according to data features, and performing visual analysis on the places;
s4: the smart campus big data base platform receives interaction information of a user and outputs a visual analysis result to the user according to indication of human-computer interaction of the user.
Furthermore, the intelligent hardware equipment comprises a teacher camera, a student camera, a sound pickup and an intelligent recording and playing host; the intelligent recording and broadcasting host is used for receiving data collected by the teacher camera, the student cameras and the sound pick-up and transmitting the data to the heterogeneous integrated intelligent campus big data base platform; the sound pick-up is used for collecting classroom field sound, converting the classroom field sound into an audio signal and sending the audio signal to the intelligent recording and broadcasting host; the intelligent recorded broadcast host supports the teaching book camera and the student camera to supply power in a POE mode, and the intelligent recorded broadcast host supplies power to the sound pick-up through an audio line.
Further, the teacher camera comprises a blackboard writing detection dome camera, a teacher detection panoramic ball machine, a teacher tracking ball machine and a blackboard writing tracking ball machine; the blackboard-writing detection hemisphere camera is used for detecting and collecting blackboard-writing contents of a blackboard, the teacher detection hemisphere camera is used for collecting images of a teacher in a platform area, the teacher detection panorama ball machine is used for collecting images of the teacher in the whole classroom range, the teacher tracking ball machine is used for collecting images of real-time actions of the teacher, and the blackboard-writing tracking ball machine is used for collecting images of real-time blackboard-writing of the teacher.
Further, the student video cameras comprise a 4K student focusing camera and a student tracking camera, wherein the 4K student focusing camera is used for collecting facial close-up images of students, and the student tracking camera is used for collecting images of real-time actions of students.
Further, the classroom data source comprises seven student behaviors and seven student expressions; the seven student behaviors include reading, writing, listening, raising hands, standing up, lying down on a table, and playing a mobile phone, and the seven student expressions include neutral, happy, surprised, hated, disgusted, bored, angry, and fear.
Further, the campus data sources include student names, teacher names, class names, student scores, classroom locations, class headcount, and schedule information.
Further, the data preprocessing in step S2 includes the following steps:
s21: removing irrelevant fields in the classification data of the classroom data source and the campus data source, filtering invalid records in the classification data of the classroom data source and the campus data source, discretizing numerical fields in the classification data of the classroom data source and the campus data source, and synchronously processing time in the classification data of the classroom data source and the campus data source;
s22: converting the data cleaned in the step S21 into a form suitable for visual representation, finding a spatial feature representation method of the data, and constructing a new attribute or normalizing and normalizing the data as required;
s23: and performing mode definition conversion on the data transformed in the step S22, and removing redundant and inconsistent data, so that heterogeneous data in the heterogeneous integrated smart campus big data base platform is converted into standard and uniform data.
Further, the data feature fusion algorithm in step S3 includes a weighted average algorithm, a bayesian estimation algorithm, a statistical decision algorithm, an evidence theory algorithm, a neural network algorithm, and an information entropy algorithm.
Further, the design technology of the heterogeneous integrated intelligent campus big data base platform in step S1 is a distributed file system HDFS, a data warehouse tool Hive, a distributed database Hbase, and a MapReduce data processing method.
Further, the result of the visual analysis in the step S4 includes visual analysis graphs of classroom analysis files, class concentration contrast analysis, student concentration contrast analysis, and student concentration and score collision analysis.
Compared with the prior art, the intelligent campus AIOT big data visualization analysis method provided by the invention has the following advantages compared with the current campus management method:
(1) various intelligent hardware products are connected through the AIOT platform, and face data of students and teachers are managed and analyzed in a centralized mode;
(2) objective data analysis is provided for classroom management, so that data support is provided for decision and improvement of classroom management;
(3) the database is built based on the AIOT platform, and the continuous development and construction of the smart campus can be supported.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used 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 it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for visually analyzing big data of a smart campus AIOT according to an embodiment of the present invention.
Fig. 2 is a visual analysis diagram of a classroom analysis file of the visual analysis method for big data of the smart campus AIOT according to the embodiment of the present invention.
Fig. 3 is a visual analysis diagram of class concentration contrast analysis of the visual analysis method for big data of the smart campus AIOT according to the embodiment of the present invention.
Fig. 4 is a visual analysis diagram of student concentration contrast analysis of the visual analysis method for big data of the smart campus AIOT according to the embodiment of the present invention.
Fig. 5 is a visual analysis diagram of student concentration and achievement collision analysis of the method for visual analysis of big data of the smart campus AIOT according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The same or similar reference numerals in the drawings of the present embodiment correspond to the same or similar components; in the description of the present invention, it should be noted that when an element is referred to as being "fixed" to another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may be present, it is to be understood that the terms "upper", "lower", "left", "right", and the like, if any, refer to an orientation or positional relationship based on that shown in the drawings, that is for convenience in describing and simplifying the description, and that no indication or suggestion that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, is therefore depicted in the drawings by the use of positional relationship descriptive terms only for purposes of illustration and not for purposes of limitation, the particular meaning of such terms being interpreted as broadly as will be understood by those skilled in the art based on the particular circumstances.
The technical solution of the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1 to 5, a preferred embodiment of the present invention is shown.
Referring to fig. 1, the visual analysis method for big data of the smart campus AIOT is used for classroom management and is connected with intelligent hardware equipment through an AIOT platform;
the intelligent campus AIOT big data visualization analysis method comprises the following steps:
s1: the method comprises the steps that a classroom data source acquired by intelligent hardware equipment and a campus data source acquired by a campus original information system are divided into structured data, semi-structured data and unstructured data according to data structures, data are transmitted according to different functions and different structural classifications of the classroom data source and the campus data source, the data are stored in a new distributed database with Hadoop as a basic framework, and a heterogeneous integrated smart campus big data basic platform is constructed;
s2: carrying out data preprocessing on the classroom data source and the campus data source to clear data which do not meet requirements, constructing new attributes and expression modes, storing the preprocessed data, and reconstructing the preprocessed data into an intelligent campus big data base platform;
s3: extracting data required by classroom management analysis from a big data base platform of the smart campus, designing a data feature fusion algorithm according to data features, and performing visual analysis on the spot;
s4: the smart campus big data base platform receives interaction information of a user and outputs a visual analysis result to the user according to indication of human-computer interaction of the user.
Compared with the current campus management method, the intelligent campus AIOT big data visualization analysis method has the following advantages:
(1) various intelligent hardware products are connected through the AIOT platform, and face data of students and teachers are managed and analyzed in a centralized mode;
(2) objective data analysis is provided for classroom management, so that data support is provided for decision and improvement of classroom management;
(3) the database is built based on the AIOT platform, and the continuous development and construction of the smart campus can be supported.
Specifically, structured data such as Oracle, SQ L Server, MySQ L, ACCESS, etc., semi-structured data such as XM L, JSON, etc., unstructured data such as documents, web pages, pictures, audio, video, etc.
As an implementation mode of the invention, the intelligent hardware equipment comprises a teacher camera, a student camera, a sound pick-up and an intelligent recording and playing host; the intelligent recording and broadcasting host is used for receiving data collected by the teacher camera, the student cameras and the sound pick-up and transmitting the data to the heterogeneous integrated intelligent campus big data base platform; the sound pick-up is used for collecting classroom field sound, converting the classroom field sound into an audio signal and sending the audio signal to the intelligent recording and broadcasting host; the intelligent recorded broadcast host supports the power supply for the textbook camera and the student camera in a POE mode, and the intelligent recorded broadcast host supplies power for the sound pick-up through an audio line.
Specifically, the teacher camera comprises a blackboard writing detection hemisphere camera, a teacher detection panorama ball machine, a teacher tracking ball machine and a blackboard writing tracking ball machine; the blackboard-writing detection hemisphere camera is used for detecting and collecting blackboard-writing contents of a blackboard, the teacher detection hemisphere camera is used for collecting images of a teacher in a platform area, the teacher detection panorama ball machine is used for collecting images of the teacher in the whole classroom range, the teacher tracking ball machine is used for collecting images of real-time actions of the teacher, and the blackboard-writing tracking ball machine is used for collecting images of real-time blackboard-writing of the teacher.
Specifically, student's camera includes student 4K camera of looking deeply and student tracking camera, and student 4K camera of looking deeply is used for gathering student's facial close-up image, and student tracking camera is used for gathering the image of student's real-time action.
As an embodiment of the present invention, the classroom data source includes seven student behaviors and seven student expressions; seven student behaviors include reading, writing, listening, raising hands, standing up, lying down on a table, and playing mobile phones, and seven student expressions include neutral, happy, surprised, hated, disgusted, angry, and fear.
As an embodiment of the present invention, the campus data sources include student names, teacher names, class names, course names, student scores, classroom location, number of classes, and schedule information.
As an embodiment of the present invention, the data preprocessing in step S2 includes the following steps:
s21: removing irrelevant fields in the classification data of the classroom data source and the campus data source, filtering invalid records in the classification data of the classroom data source and the campus data source, discretizing numerical fields in the classification data of the classroom data source and the campus data source, and synchronously processing time in the classification data of the classroom data source and the campus data source;
s22: converting the data cleaned in the step S21 into a form suitable for visual representation, finding a spatial feature representation method of the data, and constructing new attributes or normalizing and normalizing the data according to needs;
s23: and performing mode definition conversion on the data converted in the step S22, and removing redundant and inconsistent data, so that heterogeneous data in the heterogeneous integrated smart campus big data base platform is converted into standard and uniform data.
As an embodiment of the present invention, the data feature fusion algorithm in step S3 includes a weighted average algorithm, a bayesian estimation algorithm, a statistical decision algorithm, an evidence theory algorithm, a neural network algorithm, and an information entropy algorithm.
Preferably, the weighted average algorithm is used for low-level data fusion of original numerical values, the Bayesian estimation algorithm is used for low-level data fusion of probability distribution, the statistical decision algorithm is used for high-level information fusion of probability distribution, the evidence theory algorithm is used for high-level information fusion of logical reasoning, the neuron network algorithm is used for high-level information fusion of a neuron network, and the information entropy algorithm is used for high-level information fusion of information redundancy. All the algorithms adopted are the existing mature published algorithms.
As an embodiment of the present invention, the design technology of the heterogeneous integrated smart campus big data base platform in step S1 is a distributed file system HDFS, a data warehouse tool Hive, a distributed database Hbase, and a MapReduce data processing method.
As an embodiment of the present invention, the result of the visual analysis in step S4 includes a visual analysis chart of the classroom analysis file, the class concentration contrast analysis, the student concentration contrast analysis, and the student concentration and score collision analysis.
The first embodiment is as follows:
fig. 2 is a visual analysis diagram of a classroom analysis file according to an embodiment of the present invention, which is analyzed by using the visual analysis method for big data of an intelligent campus AIOT, and the steps are specifically as follows:
s01: dividing data such as seven student behaviors, seven student expressions, snap-shot face pictures and blackboard writing pictures collected from intelligent hardware equipment, class names, teacher names, classroom positions, student names, course names, attendance rates, class arrival rates and the like collected from a campus original information system into structured data, semi-structured data and unstructured data according to a data structure, and transmitting and storing the classified data into a new distributed database with Hadoop as a basic framework;
s02: extracting classified data from a database, and performing data preprocessing on the classified data, wherein the preprocessing comprises data cleaning, data transformation and data integration, the preprocessing comprises unifying time format, clearing invalid time, clearing redundant data and the like (the preprocessing process is the prior art), and a data set is reconstructed to be analyzed and synthesized according to a preset criterion;
s03: corresponding data such as a timestamp, seven student behaviors, seven student expressions, a class name, a teacher name, a student name, a classroom position, a course name, an attendance rate, a class arrival rate, an examination, a score and the like are quickly read from the set, a data fusion algorithm is selected, and the class behaviors and the class expressions are determined by counting the student behaviors and the student expressions by adopting a statistical decision algorithm according to the behaviors and the expressions of students;
s04: designing a visual graph method, wherein the school assignment statistics, the behavior statistics and the expression statistics are the key points of visualization, the visualization method is to represent data in a specific time window by a column graph, a sector graph and a ring graph, and the aggregation mode in the data is disclosed by adopting the change of colors and the proportion of objects so as to show the attendance index, the school assignment index, the class behavior data and the class expression data;
s05: the visual analysis graph of the class analysis archive output to the user includes a class name, a class owner name, the number of classes, a teacher position, an attendance index (a ring graph shows an average class rate), basic cumulative data, a class rate index (a histogram display), class behavior data (yesterday class behavior data is shown by a histogram), and class expression data (yesterday class expression data is shown by a fan graph).
The visual analysis chart of the classroom analysis archive obtained by the method can show that the highest class rate index is 98 percent and the lowest mathematics index is obtained; the most popular in class behavior is listening and speaking; the greatest proportion of class expressions is neutral and happy.
Example two:
fig. 3 is a visual analysis diagram of class concentration contrast analysis according to the second embodiment of the present invention, which is analyzed by using the visual analysis method for big data of the smart campus AIOT, and the steps are specifically as follows:
s01: dividing seven data such as student behaviors, seven student expressions, snap-shot face pictures and blackboard writing pictures collected from intelligent hardware equipment and class names collected from a campus original information system into structured data, semi-structured data and unstructured data according to a data structure, and transmitting and storing the classified data into a new distributed database taking Hadoop as a basic framework;
s02: extracting classified data from a database, and performing data preprocessing on the classified data, wherein the preprocessing comprises data cleaning, data transformation and data integration, the preprocessing comprises unifying time format, clearing invalid time, clearing redundant data and the like (the preprocessing process is the prior art), and a data set is reconstructed to be analyzed and synthesized according to a preset criterion;
s03: quickly reading corresponding data such as timestamps, seven student behaviors, seven student expressions, class names and the like from the set, selecting a data fusion algorithm, and counting the student behaviors and the student expressions to determine class concentration degree by adopting a statistical decision algorithm according to the behaviors and the expressions of students;
s04: designing a visual graph method, wherein the class concentration index is the key point of visualization, and the visualization method is to adopt the area size of points in a specific time window to disclose an aggregation mode in data so as to show the class concentration;
s05: the visual analysis graph of the class concentration contrast analysis output to the user includes the name of the outlier class and the distance of the outlier class from the median.
The median is the average concentration degree of each class calculated by counting the concentration degrees of the individual students of each class by adopting the existing weighted average algorithm and is used as a reference for judging the concentration degree of each class.
As can be seen from the visual analysis chart of the class concentration contrast analysis obtained by the method, the median is 6.3, the average concentration of the class is within the range of 6.3 ± 1 and belongs to the normal class, and the class exceeding the range belongs to the outlier class; the higher the class concentration than the normal class is one (21) higher and one (9) higher, the lower the class concentration than the normal class is one (15) higher, the highest the class concentration is one (21) higher, and the lowest the class concentration is one (15) higher.
Example three:
fig. 4 is a visual analysis diagram of student concentration contrast analysis provided in the third embodiment of the present invention, and the analysis is performed by using the visual analysis method for big data of the smart campus AIOT, the steps are specifically described as follows:
s01: dividing seven data such as student behaviors, seven student expressions, snap-shot face pictures and blackboard writing pictures collected from intelligent hardware equipment and data such as student names collected from a campus original information system into structured data, semi-structured data and unstructured data according to data structures, and transmitting and storing the classified data into a new distributed database taking Hadoop as a basic framework;
s02: extracting classified data from a database, and performing data preprocessing on the classified data, wherein the preprocessing comprises data cleaning, data transformation and data integration, the preprocessing comprises unifying time format, clearing invalid time, clearing redundant data and the like (the preprocessing process is the prior art), and a data set is reconstructed to be analyzed and synthesized according to a preset criterion;
s03: quickly reading corresponding data such as timestamps, seven student behaviors, seven student expressions, student names and the like from the set, selecting a data fusion algorithm, and counting the student behaviors and the student expressions to determine the concentration degree of the students by adopting a statistical decision algorithm according to the behaviors and the expressions of the students;
s04: designing a visual graph method, wherein the student concentration index is the key point of visualization, and the visualization method is to adopt the area size of points in a specific time window to disclose an aggregation mode in data so as to show the student concentration;
s05: the visual analysis map of the student concentration contrast analysis output to the user includes the names of the outlier students and the distances of the outlier students from the median.
The median is the average concentration degree of the students obtained by adopting the existing weighted average algorithm and carrying out accumulation calculation by counting the concentration degrees of all the students and is used as a reference for judging the concentration degree of the students.
The visual analysis chart of the student concentration degree contrast analysis obtained by the method shows that the median is 6.3, the average concentration degree of the students belongs to the normal class within the range of 6.3 +/-1, and the students belonging to the outlier beyond the range belong to the normal class; the higher concentration degree of the students than that of the normal students is Yang Xin and Li Da quan, the lower concentration degree of the students than that of the normal students is Jinxin, the highest concentration degree of the students is Yang Xin, and the lowest concentration degree of the students is Jinxin.
Example four:
fig. 5 is a visual analysis diagram of student concentration and achievement collision analysis provided in the fourth embodiment of the present invention, and the analysis is performed by using the visual analysis method for big data of the smart campus AIOT, the steps are specifically as follows:
s01: dividing seven data such as student behaviors, seven student expressions, snap face pictures and blackboard writing pictures collected from intelligent hardware equipment and data such as student names, examination scores and the like collected from a campus original information system into structured data, semi-structured data and unstructured data according to a data structure, and transmitting and storing the classified data into a new distributed database taking Hadoop as a basic framework;
s02: extracting classified data from a database, and performing data preprocessing on the classified data, wherein the preprocessing comprises data cleaning, data transformation and data integration, the preprocessing comprises unifying time format, clearing invalid time, clearing redundant data and the like (the preprocessing process is the prior art), and a data set is reconstructed to be analyzed and synthesized according to a preset criterion;
s03: quickly reading corresponding data such as timestamps, seven student behaviors, seven student expressions, student names, examination scores and the like from the set, selecting a data fusion algorithm, adopting a statistical decision algorithm aiming at the behaviors and the expressions of students, and counting the student behaviors and the student expressions to determine the concentration of the students, wherein the concentration of the students is combined with the examination scores of the students to form a concentration index and coordinates of the examination scores;
s04: designing a visual graph method, wherein the coordinates of concentration and examination achievements are the key points of visualization, and the visualization method is to adopt the area size of points in a specific time window to disclose an aggregation mode in data so as to show the distribution of the concentration and the examination achievements of students;
s05: and outputting a visual analysis chart of the student concentration degree contrast analysis to the user as a student concentration degree and score collision analysis result.
The visual analysis chart of the student concentration and score collision analysis obtained by the method shows that students are divided into four types:
type 1: concentration on the step type is high, the concentration degree index of the students is high, the examination score is high, and the students are informed seriously and have better scores;
type 2: the student is seriously listened, the concentration index of the student is high, the examination score is low, and the result shows that the student is seriously listened to and talk but not good;
type 3: the study slag type is characterized in that the concentration index of the students is low, the examination score is low, and the students are indicated to be uninterested in listening and speaking and have poor scores;
type 4: the student is of the super school type, the concentration degree index of the student is low, the examination score is high, and the student can hear and speak badly but the score is good.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. The intelligent campus AIOT big data visualization analysis method is characterized by being used for classroom management and being connected with intelligent hardware equipment through an AIOT platform;
the intelligent campus AIOT big data visualization analysis method comprises the following steps:
s1: the classroom data source acquired by the intelligent hardware equipment and the campus data source acquired by the campus original information system are divided into structured data, semi-structured data and unstructured data according to data structures, data transmission is carried out according to different functions and different structural classifications of the classroom data source and the campus data source, the data are stored in a new distributed database with Hadoop as a basic framework, and a heterogeneous integrated smart campus big data basic platform is constructed;
s2: carrying out data preprocessing on the classroom data source and the campus data source to clean data which do not meet requirements, constructing new attributes and expression modes, storing the preprocessed data, and reconstructing the preprocessed data into a big data base platform of the smart campus;
s3: extracting data required by classroom management analysis from the smart campus big data base platform, designing a data feature fusion algorithm according to data features, and performing visual analysis on the places;
s4: the smart campus big data base platform receives interaction information of a user and outputs a visual analysis result to the user according to indication of human-computer interaction of the user.
2. The visual analytic method of big data of wisdom campus AIOT of claim 1, characterized in that, the intelligent hardware equipment includes teacher's camera, student's camera, sound pickup and intelligent recording and broadcasting host computer; the intelligent recording and broadcasting host is used for receiving data collected by the teacher camera, the student cameras and the sound pick-up and transmitting the data to the heterogeneous integrated intelligent campus big data base platform; the sound pick-up is used for collecting classroom field sound, converting the classroom field sound into an audio signal and sending the audio signal to the intelligent recording and broadcasting host; the intelligent recorded broadcast host supports the teaching book camera and the student camera to supply power in a POE mode, and the intelligent recorded broadcast host supplies power to the sound pick-up through an audio line.
3. The visual analysis method for big data of the smart campus AIOT according to claim 2, wherein the teacher camera includes a blackboard writing detection dome camera, a teacher detection panorama dome camera, a teacher tracking dome camera and a blackboard writing tracking dome camera; the blackboard-writing detection hemisphere camera is used for detecting and collecting blackboard-writing contents of a blackboard, the teacher detection hemisphere camera is used for collecting images of a teacher in a platform area, the teacher detection panorama ball machine is used for collecting images of the teacher in the whole classroom range, the teacher tracking ball machine is used for collecting images of real-time actions of the teacher, and the blackboard-writing tracking ball machine is used for collecting images of real-time blackboard-writing of the teacher.
4. The intelligent campus AIOT big data visualization analysis method according to claim 2, wherein said student cameras comprise student 4K deep-eye cameras and student tracking cameras, said student 4K deep-eye cameras are used for capturing student facial close-up images, said student tracking cameras are used for capturing images of student real-time actions.
5. The visual analytic method of big data of wisdom campus AIOT of claim 1, wherein said classroom data sources include seven student behaviors and seven student expressions; the seven student behaviors include reading, writing, listening, raising hands, standing up, lying down on a table, and playing a mobile phone, and the seven student expressions include neutral, happy, surprised, hated, disgusted, bored, angry, and fear.
6. The method for visual analytics of big data on a smart campus AIOT as claimed in claim 1, wherein said campus data sources include student name, teacher name, class name, student score, classroom location, number of classes, and schedule information.
7. The method for visual analysis of big data on smart campus AIOT according to claim 1, wherein the data preprocessing in step S2 includes the following steps:
s21: removing irrelevant fields in the classification data of the classroom data source and the campus data source, filtering invalid records in the classification data of the classroom data source and the campus data source, discretizing numerical fields in the classification data of the classroom data source and the campus data source, and synchronously processing time in the classification data of the classroom data source and the campus data source;
s22: converting the data cleaned in the step S21 into a form suitable for visual representation, finding a spatial feature representation method of the data, and constructing a new attribute or normalizing and normalizing the data as required;
s23: and performing mode definition conversion on the data transformed in the step S22, and removing redundant and inconsistent data, so that heterogeneous data in the heterogeneous integrated smart campus big data base platform is converted into standard and uniform data.
8. The method for visual analysis of big data in the smart campus AIOT according to claim 1, wherein the data feature fusion algorithm in step S3 includes a weighted average algorithm, a bayesian estimation algorithm, a statistical decision algorithm, an evidence theory algorithm, a neural network algorithm, and an information entropy algorithm.
9. The method for visual analysis of big data on smart campus AIOT according to claim 1, wherein the heterogeneous converged smart campus big data base platform design technique in step S1 is distributed file system HDFS, data warehouse tool Hive, distributed database Hbase and MapReduce data processing method.
10. The method as claimed in claim 1, wherein the results of the visual analysis in step S4 include classroom analysis files, class concentration contrast analysis, student concentration contrast analysis, and visual analysis charts of student concentration and score collision analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010305806.7A CN111507874B (en) | 2020-04-17 | 2020-04-17 | Intelligent campus AIOT big data visualization analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010305806.7A CN111507874B (en) | 2020-04-17 | 2020-04-17 | Intelligent campus AIOT big data visualization analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111507874A true CN111507874A (en) | 2020-08-07 |
| CN111507874B CN111507874B (en) | 2023-03-03 |
Family
ID=71869452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010305806.7A Active CN111507874B (en) | 2020-04-17 | 2020-04-17 | Intelligent campus AIOT big data visualization analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507874B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132009A (en) * | 2020-09-22 | 2020-12-25 | 湖南惟楚有才教育科技有限公司 | Classroom behavior analysis method and system and electronic equipment |
| WO2022095435A1 (en) * | 2020-11-06 | 2022-05-12 | 深圳市爱云信息科技有限公司 | Multilevel linkage management platform for aiot device accessing paas and saas |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446364A (en) * | 2018-03-14 | 2018-08-24 | 湖南商学院 | A kind of visual analysis method towards campus big data |
| CN108537516A (en) * | 2018-04-24 | 2018-09-14 | 温州市鹿城区中津先进科技研究院 | Intelligent campus educates big data convergence platform |
| CN108537517A (en) * | 2018-04-24 | 2018-09-14 | 温州市鹿城区中津先进科技研究院 | A kind of campus wisdom education cloud platform based on big data analysis |
| CN108961883A (en) * | 2018-09-17 | 2018-12-07 | 南京览众智能科技有限公司 | Wisdom classroom cloud platform |
| CN110245481A (en) * | 2019-05-08 | 2019-09-17 | 深圳法大大网络科技有限公司 | A kind of method, apparatus and terminal device of real-name authentication |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355350A (en) * | 2016-09-23 | 2017-01-25 | 重庆多创电子技术有限公司 | Intelligent campus system |
| CN106971359A (en) * | 2017-03-25 | 2017-07-21 | 广州市义加网络科技有限公司 | A kind of Intelligent campus tutoring system |
| CN108596802A (en) * | 2018-04-24 | 2018-09-28 | 温州市鹿城区中津先进科技研究院 | A kind of region wisdom education cloud platform based on big data analysis |
| CN108648114A (en) * | 2018-04-24 | 2018-10-12 | 温州市鹿城区中津先进科技研究院 | A kind of school education big data cloud platform based on artificial intelligence |
| CN109102242A (en) * | 2018-07-16 | 2018-12-28 | 周永平 | intelligent campus management and information analysis platform |
| CN110517169A (en) * | 2019-08-09 | 2019-11-29 | 福建路阳信息科技有限公司 | A kind of Intelligent campus integrated service system |
-
2020
- 2020-04-17 CN CN202010305806.7A patent/CN111507874B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446364A (en) * | 2018-03-14 | 2018-08-24 | 湖南商学院 | A kind of visual analysis method towards campus big data |
| CN108537516A (en) * | 2018-04-24 | 2018-09-14 | 温州市鹿城区中津先进科技研究院 | Intelligent campus educates big data convergence platform |
| CN108537517A (en) * | 2018-04-24 | 2018-09-14 | 温州市鹿城区中津先进科技研究院 | A kind of campus wisdom education cloud platform based on big data analysis |
| CN108961883A (en) * | 2018-09-17 | 2018-12-07 | 南京览众智能科技有限公司 | Wisdom classroom cloud platform |
| CN110245481A (en) * | 2019-05-08 | 2019-09-17 | 深圳法大大网络科技有限公司 | A kind of method, apparatus and terminal device of real-name authentication |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112132009A (en) * | 2020-09-22 | 2020-12-25 | 湖南惟楚有才教育科技有限公司 | Classroom behavior analysis method and system and electronic equipment |
| WO2022095435A1 (en) * | 2020-11-06 | 2022-05-12 | 深圳市爱云信息科技有限公司 | Multilevel linkage management platform for aiot device accessing paas and saas |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111507874B (en) | 2023-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107316257B (en) | Teaching quality assessment method and system based on classroom student behavior analysis | |
| AU2020101287A4 (en) | Method and device for constructing an educational cyber-physical space fusion learning environment | |
| CN108446364B (en) | Visual analysis method for campus big data | |
| CN111915148B (en) | Classroom teaching evaluation method and system based on information technology | |
| CN107004271A (en) | Display methods, device, electronic equipment, computer program product and non-transient computer readable storage medium storing program for executing | |
| CN105787837A (en) | Intelligent teaching system based on cloud computing and internet-of-thing technology | |
| CN109214664B (en) | Emotional behavior comprehensive analysis system based on artificial intelligence | |
| CN111507874B (en) | Intelligent campus AIOT big data visualization analysis method | |
| CN109902681B (en) | User group relation determining method, device, equipment and storage medium | |
| Gao | Research and implementation of intelligent evaluation system of teaching quality in universities based on artificial intelligence neural network model | |
| CN110737776A (en) | path learning planning system based on knowledge graph and target ontology | |
| CN112256755A (en) | Student abnormal behavior analysis method based on deep learning | |
| CN109359881A (en) | Visual comprehensive analysis system based on college big data | |
| Dai et al. | Spatio-temporal deep learning framework for traffic speed forecasting in IoT | |
| CN109062951A (en) | Based on conversation process abstracting method, equipment and the storage medium for being intended to analysis and dialogue cluster | |
| CN114898460A (en) | Teacher non-verbal behavior detection method based on graph convolution neural network | |
| Shams et al. | Towards distributed cyberinfrastructure for smart cities using big data and deep learning technologies | |
| Kramar et al. | Augmented Reality-assisted Cyber-Physical Systems of Smart University Campus | |
| CN114461853A (en) | Training sample generation method, device and equipment of video scene classification model | |
| CN109344325A (en) | The recommended method and device of information based on intelligent meeting plate | |
| Tavra et al. | Unpacking the role of volunteered geographic information in disaster management: focus on data quality | |
| Xie et al. | Deep learning on multi-view sequential data: a survey | |
| Cho | Designing smart cities: Security issues | |
| Zhou et al. | Abnormal Behavior Determination Model of Multimedia Classroom Students Based on Multi-task Deep Learning | |
| Li et al. | Dynamic Analysis of Deep Integration of Artificial Intelligence Based on High-Performance Computing for Ideological and Political Teaching Evaluation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |