Comprehensive school condition data analysis visualization method and related device

Abstract

The invention discloses a comprehensive school condition data analysis visualization method and a related device, and relates to the technical field of data processing, and the method comprises the steps: extracting target data in a data warehouse through semantic embedding; performing student learning condition analysis by using the target data based on the decision tree, and performing subject comprehensive development analysis based on the target data; performing comprehensive school condition analysis based on the student learning condition analysis data and the subject comprehensive development analysis data; based on the student learning condition analysis data, the subject comprehensive development analysis data and the comprehensive school condition analysis data, determining a corresponding visual area by using an object relationship; performing rendering layout analysis on each visual area; and visually displaying the student learning condition analysis data, the subject comprehensive development analysis data and the comprehensive school condition analysis data in corresponding visual areas based on the rendering layout analysis data. According to the method, related personnel can intuitively and clearly know the analysis data of the comprehensive school condition.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data analysis visualization method and related devices for comprehensive school conditions. Background Art

[0002] The analysis of comprehensive school conditions is a necessary step to understand the current situation of the school and the learning situation of students. The visualization of the analysis data can enable relevant personnel to directly and clearly understand the overall situation of the school. Among them, the analysis of student learning conditions and the analysis of subject development are important links in the comprehensive school situation analysis. At present, it is mainly through managers to screen and analyze data to issue analysis reports, but this method is inefficient and prone to errors. Moreover, when the number of personnel to be analyzed is too large, it cannot cover all personnel, resulting in the analyzed comprehensive school situation information being unable to fully and accurately reflect the overall situation of the school. After obtaining the analysis data, it is currently usually configured and laid out visually through the template tool library. However, the use of the template tool library for visual layout will result in the mismatch between the size of the components and the visual interface and the unreasonable visual layout, resulting in the final data visualization layout being not beautiful enough, and it is difficult for relevant personnel to clearly observe the analysis data, thus affecting their understanding of the comprehensive school situation. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a data analysis visualization method and related devices for comprehensive school conditions, which improves the rationality and aesthetics of the visualization arrangement and enables relevant personnel to understand the analysis data of the comprehensive school conditions intuitively and clearly.

[0004] In order to solve the above technical problems, the present invention provides a data analysis and visualization method for comprehensive school conditions, which is applied to a data middle station, wherein the data middle station includes a public dimension model layer and an application data layer; the method includes: The common dimensional model layer uses semantic embedding to extract target data in the data warehouse; The application data layer uses the target data to perform student learning situation analysis based on the decision tree to obtain student learning situation analysis data, and performs subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data; Performing a comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data; Determine the corresponding visualization area by using object relationship based on the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Perform rendering layout analysis on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data to obtain corresponding rendering layout analysis data; Based on the rendering layout analysis data, the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data are visualized in the corresponding visualization area.

[0005] Optionally, the extracting target data in the data warehouse by using semantic embedding includes: Parse the query statement in the query request to obtain query task information; Perform semantic embedding based on the query task information to obtain a first semantic embedding vector, and match the first semantic embedding vector with a plurality of second semantic embedding vectors in the index database to obtain a matching result; The corresponding operation engine is determined based on the operator in the query statement, and the target data is extracted from the data warehouse using the operation engine based on the matching result.

[0006] Optionally, performing student learning situation analysis based on the decision tree and using the target data to obtain student learning situation analysis data, and performing subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data, includes: Extracting student data from the target data, and dividing the student data into objective evaluation data and subjective evaluation data; Based on a random forest model composed of a plurality of decision trees, the objective evaluation data and the subjective evaluation data are used to analyze the student's learning situation, thereby obtaining student's learning situation analysis data; Based on the target data, analyze the school conditions, teacher team construction, talent training, scientific research and academic degree status to obtain data on school conditions, teacher team construction, talent training, scientific research and academic degree status; Generate comprehensive discipline development analysis data based on school conditions data, faculty team construction data, talent training data, scientific research data and discipline degree data.

[0007] Optionally, performing a comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data includes: Determine the evaluation dimensions and evaluation indicators, and use the student learning situation analysis data and the subject comprehensive development analysis data to perform school situation profile analysis based on the evaluation dimensions and evaluation indicators to obtain school situation profile information; Classify the student learning situation analysis data based on support vector machine to obtain classification results; Generate comprehensive school situation analysis data based on classification results and school profile information.

[0008] Optionally, the determining a corresponding visualization area based on the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data by using object relationships includes: Match corresponding visualization components to the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Analyze the object information of student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Perform display resolution analysis based on the data volume of student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data to obtain the corresponding display resolution; Determine the horizontal spacing and the vertical spacing between the visualization components based on the width and height of the view area and the width and height of each visualization component using the object information; The three-dimensional space position is determined based on the visualization components and display resolution corresponding to the comprehensive subject development analysis data, and the corresponding regional coordinate position is determined based on the three-dimensional space position and the horizontal and vertical spacing between each visualization component, and the corresponding visualization area is determined based on the regional coordinate position.

[0009] Optionally, performing rendering layout analysis on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data to obtain corresponding rendering layout analysis data includes: Determine the rendering information of each visualization component in the corresponding visualization area of ​​the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data; Determine a layout mode of the view area based on rendering information of each visualization component, and perform a visualization preview based on the rendering information and the layout mode to obtain a visualization preview effect; Performing color distribution analysis based on the visual preview effect to obtain color distribution information, and performing a color mixing test based on the color distribution information to obtain a color mixing test result; The rendering information of each visualization component is adjusted based on the color mixing test result to obtain the adjusted rendering information of each visualization component, and the corresponding rendering layout analysis data is determined based on the adjusted rendering information and the layout mode of each visualization component.

[0010] Optionally, visually displaying the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data in a corresponding visualization area based on the rendering layout analysis data includes: Based on the rendering layout analysis data, the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data are visually drawn in the corresponding visualization area, and a monitoring component is deployed in the corresponding visualization area.

[0011] In addition, the present invention also provides a data analysis and visualization device for comprehensive school conditions, which is applied to a data middle platform, wherein the data middle platform includes a public dimension model layer and an application data layer; the device includes: Data extraction module: used for extracting target data from the data warehouse using semantic embedding in the common dimensional model layer; The learning situation and subject analysis module is used to apply the data layer to analyze the student learning situation using the target data based on the decision tree to obtain the student learning situation analysis data, and to perform subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data; School situation analysis module: used to perform comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data; Region determination module: used to determine the corresponding visualization region by using object relationship based on the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Layout analysis module: used to perform rendering layout analysis on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data, and obtain the corresponding rendering layout analysis data; Visualization display module: used to visualize the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data in the corresponding visualization area based on the rendering layout analysis data.

[0012] In addition, the present invention also provides an electronic device, which includes a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the above-mentioned comprehensive school situation data analysis visualization method.

[0013] In addition, the present invention also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned comprehensive school situation data analysis and visualization method.

[0014] In an embodiment of the present invention, the public dimension model layer of the data center uses semantic embedding to extract target data in the data warehouse, and can quickly and accurately extract target data from large data sets. Using target data based on decision trees to analyze student learning conditions, and using target data to analyze subject comprehensive development, can improve the efficiency and accuracy of student learning conditions analysis and subject comprehensive development analysis, so that the comprehensive school situation analysis data obtained can more comprehensively and accurately reflect the overall situation of the school. Based on the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, the corresponding visualization area is determined using object relationships, and rendering layout analysis is performed on each visualization area to visualize the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, so as to avoid the mismatch between the visualization component and the interface size, improve the rationality and aesthetics of the visualization layout, and enable relevant personnel to intuitively and clearly understand the comprehensive school situation analysis data. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 is a flow chart of a method for visualizing data analysis of comprehensive school conditions in an embodiment of the present invention; Figure 2 is a flow chart of a method for visualizing data analysis of comprehensive school conditions in another embodiment of the present invention; Figure 3 Schematic diagram of the structure of the comprehensive school situation data analysis and visualization device in an embodiment of the present invention; Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1 See also Figure 1 , Figure 1: is a flow chart of a data analysis visualization method for comprehensive school conditions in an embodiment of the present invention, the method is applied to a data middle station, the data middle station includes a public dimension model layer and an application data layer, and the method includes: S11: The common dimensional model layer uses semantic embedding to extract target data in the data warehouse; In the specific implementation process of the present invention, the use of semantic embedding to extract target data in the data warehouse includes: parsing the query statement in the query request to obtain query task information; performing semantic embedding based on the query task information to obtain a first semantic embedding vector, and matching the first semantic embedding vector with a plurality of second semantic embedding vectors in the index database to obtain a matching result; determining the corresponding operation engine based on the operator in the query statement, and extracting the target data in the data warehouse using the operation engine based on the matching result.

[0019] Specifically, the data center serves as a support platform for data collection, data asset storage, management, and data development. Data collection includes heterogeneous networks, heterogeneous data sources, offline access, real-time access, and visual configuration. Data asset management includes data assets in various subject domains shared by various data layers and school affairs. Data asset management includes metadata management, data standard management, data model management, and data quality management. Data development includes offline development, real-time development, algorithm development, and label development. Among them, the data center includes a public dimension model layer and an application data layer. The public dimension model layer summarizes relevant data tables, such as student management information, school information, teaching information, and faculty information, and can extract corresponding data according to needs. The application data layer is used to perform relevant analysis based on the data extracted from the public dimension model layer.

[0020] Receive the query request sent by the client, parse the query statement in the query request, match the syntax parser of the query statement in the query request, different query statements have different syntax parsers, such as PostgreSQL syntax parser and SQL syntax parser, etc. Parse the query statement into an abstract syntax tree according to the syntax parser. The abstract syntax tree is a tree representation method used to describe the syntax structure of program code. Each node of the syntax tree represents a syntax structure in the program code, which better avoids the restriction on the database language, analyzes the nested relationship in the query statement, determines the hierarchical relationship between several branches related to the query statement in the abstract syntax tree according to the nested relationship, determines the hierarchical relationship of the statement block according to the syntax node in each branch and the hierarchical relationship between them, determines the statement type, execution intention and goal according to the hierarchical relationship of the statement block and the nested relationship of the query statement, that is, obtains the query task information. Based on the query task information, semantic embedding is performed, and a query task statement is generated according to the query task information. The query task statement is semantically embedded using an embedding model, that is, the query task statement is embedded with demand words to obtain a number of corresponding demand word embedding vectors, that is, a first semantic embedding vector is obtained, and the first semantic embedding vector is matched with a number of second semantic embedding vectors in the index database. The first semantic embedding vector and the second semantic embedding vector can be matched for similarity. The higher the similarity, the stronger the semantic relationship between the vectors, and a matching result is obtained. Based on the operator in the query statement, the corresponding operation engine is determined, and the target data is extracted from the data warehouse using the operation engine based on the matching result. The required second semantic embedding vector is determined according to the matching result. Each second semantic embedding vector corresponds to the index of the data. According to the index of the data, the target data is extracted from the data warehouse using the operation engine. The target data includes teacher information, student information, scientific research information, subject and degree point information, etc.

[0021] S12: the application data layer uses the target data to perform student learning situation analysis based on the decision tree to obtain student learning situation analysis data, and performs subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data; In the specific implementation process of the present invention, the decision tree-based method uses the target data to perform student learning situation analysis to obtain student learning situation analysis data, and based on the target data, performs discipline comprehensive development analysis to obtain discipline comprehensive development analysis data, including: extracting student data from the target data, and dividing the student data into objective evaluation data and subjective evaluation data; based on a random forest model composed of several decision trees, uses the objective evaluation data and the subjective evaluation data to perform student learning situation analysis to obtain student learning situation analysis data; based on the target data, performs school running conditions analysis, faculty team construction analysis, talent training analysis, scientific research situation analysis and discipline degree point situation analysis to obtain school running conditions data, faculty team construction data, talent training data, scientific research situation data and discipline degree point situation data; generates discipline comprehensive development analysis data based on school running conditions data, faculty team construction data, talent training data, scientific research situation data and discipline degree point situation data.

[0022] Specifically, student data is extracted from the target data, and the student data includes each student's grades in various subjects, self-evaluation and teacher evaluation, etc., and the student data is divided into objective evaluation data and subjective evaluation data. The objective evaluation data is information that is not affected by the subjective will of relevant personnel, such as grades in various subjects, and the subjective evaluation data is information that is affected by the subjective will of relevant personnel, such as teacher evaluation. Based on a random forest model composed of several decision trees, the objective evaluation data and the subjective evaluation data are used to analyze the student learning situation. During training, each decision tree is trained in a cycle, and the training samples of each decision tree are obtained by Bootstrap sampling from the original training set. The features used when training each node of the decision tree are also randomly sampled from the new feature space. Each decision tree is recursively split according to the judgment criterion. The recursive splitting step includes forming a root node with the extracted sample set, splitting the sample set into a first sample set and a second sample set according to a preset splitting criterion, recursively establishing a left subtree with the first sample set, and establishing a right subtree with the second sample set. When the splitting can no longer be performed, the node is marked as a leaf node. However, after the training of each decision tree is completed, the trained decision trees are used to form a random forest model, and the objective evaluation data and the subjective evaluation data are input into the random forest model to analyze the student learning situation, so as to obtain the student's learning effect of each course and the overall learning effect, that is, to obtain the student learning situation analysis data. Based on the target data, the school conditions analysis, faculty team construction analysis, talent training analysis, scientific research situation analysis and discipline degree situation analysis are carried out. The school conditions analysis includes the analysis of school indicators, campus area and layout, campus student distribution and discipline distribution. The faculty team construction analysis includes the overall profile of teachers in each discipline. The talent training analysis includes the number and category analysis of students in each discipline and the analysis of student majors. The scientific research situation analysis includes the scientific research funding analysis, scientific research project analysis and scientific research institution analysis of each discipline. The discipline degree analysis includes the discipline coverage, degree point construction situation and discipline evaluation and ranking. The school conditions data, faculty team construction data, talent training data, scientific research situation data and discipline degree situation data are obtained. Based on the school conditions data, faculty team construction data, talent training data, scientific research situation data and discipline degree situation data, the discipline comprehensive development analysis data is generated, that is, the above data constitute the discipline comprehensive development analysis data.

[0023] S13: Performing comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data; In the specific implementation process of the present invention, the comprehensive school situation analysis is performed based on the student learning situation analysis data and the comprehensive subject development analysis data to obtain the comprehensive school situation analysis data, including: determining the evaluation dimensions and evaluation indicators, and performing the school situation profile analysis based on the evaluation dimensions and evaluation indicators using the student learning situation analysis data and the comprehensive subject development analysis data to obtain the school situation profile information; classifying the student learning situation analysis data based on a support vector machine to obtain the classification results; and generating the comprehensive school situation analysis data based on the classification results and the school situation profile information.

[0024] Specifically, the evaluation dimensions and evaluation indicators are determined, such as academic quality, the effect of scientific research investment, etc., and the evaluation indicators are such as the evaluation standards of academic quality, the evaluation standards of scientific research investment, etc., and based on the evaluation dimensions and evaluation indicators, the student learning situation analysis data and the subject comprehensive development analysis data are used to perform school situation overview analysis, that is, analyze the overview of each data contained in the student learning situation analysis data and the subject comprehensive development analysis data, such as analyzing the proportion and number of each academic quality level and subject development level based on the student learning situation analysis data and the subject comprehensive development analysis data, such as the proportion and number of students whose overall academic quality reaches the excellent level, and obtain school situation overview information. The student learning situation analysis data is classified based on the support vector machine, that is, the student learning situation analysis data is classified into different grades and different subjects, the support vector machine is trained by the sequence minimum optimization algorithm, and the student learning situation analysis data is input into the trained support vector machine to obtain the student learning situation analysis data of different grades and different subjects, that is, to obtain the classification result. Comprehensive school situation analysis data is generated based on the classification results and school profile information. The specific student subject learning situation and the overall learning situation of different grades are analyzed based on the student learning situation analysis data of different grades and subjects. Comprehensive school situation analysis data is generated in combination with the school profile information.

[0025] S14: Determine a corresponding visualization area using object relationships based on the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data; In the specific implementation process of the present invention, the corresponding visualization area is determined based on the student learning situation analysis data, the comprehensive subject development analysis data and the comprehensive school situation analysis data using object relationships, including: matching the student learning situation analysis data, the comprehensive subject development analysis data and the comprehensive school situation analysis data with corresponding visualization components; analyzing the object information of the student learning situation analysis data, the comprehensive subject development analysis data and the comprehensive school situation analysis data; performing display resolution analysis based on the data volume of the student learning situation analysis data, the comprehensive subject development analysis data and the comprehensive school situation analysis data to obtain the corresponding display resolution; determining the horizontal spacing and vertical spacing between each visualization component based on the width and height of the view area and the width and height of each visualization component using the object information; determining the three-dimensional space position based on the visualization component and the display resolution corresponding to the comprehensive subject development analysis data, and determining the corresponding regional coordinate position based on the three-dimensional space position and the horizontal spacing and vertical spacing between each visualization component, and determining the corresponding visualization area based on the regional coordinate position.

[0026] Specifically, the corresponding visualization components are matched to the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data. The visualization components are visualization graphics displayed in the interface of the application software, such as charts, edit boxes and dialog boxes. The visualization components also include interface controls with user interface functions and static components without interactive functions. Each analysis data is matched with the corresponding visualization components in the component database. The object information of the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data is analyzed, that is, the analysis objects corresponding to the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data are analyzed. For example, the analysis object corresponding to the student learning situation analysis data is students, and the analysis objects corresponding to each data in the subject comprehensive development analysis data include teachers, scientific research institutions and students, and the analysis objects corresponding to the comprehensive school situation analysis data include students, scientific research institutions, etc. The display resolution analysis is performed based on the data volume of the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data. The larger the data volume, the greater the display resolution required. From this, the display resolution of the visualization component corresponding to each analysis data can be known. The horizontal and vertical spacings between the visualization components are determined based on the width and height of the view area and the width and height of each visualization component using the object information. The view area is the display area of ​​the display canvas. The width and height of each visualization component are matched by the corresponding display resolution. In the data contained in the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data, the visualization components corresponding to the data with the same analysis object should be arranged in adjacent positions with a shorter spacing to avoid users spending too much time viewing the analysis data of the same analysis object. The initial horizontal and vertical spacings between the components are determined by the width and height of the view area and the width and height of each visualization component, as well as the number of visualization components. Then, the initial horizontal and vertical spacings are adjusted according to the analysis object of each data, that is, the spacing between the visualization components with the same analysis object is shortened, so as to obtain the final horizontal and vertical spacings.The three-dimensional spatial position is determined based on the visualization components and display resolution corresponding to the comprehensive discipline development analysis data. Since the comprehensive discipline development analysis data contains three-dimensional data such as campus layout and scientific research institution layout, the corresponding visualization components are three-dimensional visualization graphics. In order to make the visualization layout more reasonable and beautiful, the spatial position of the three-dimensional data must be determined first, and the spatial position loaded in the viewing area is determined according to its visualization components and display resolution using preset typesetting rules, that is, the three-dimensional spatial position, and the corresponding regional coordinate position is determined based on the three-dimensional spatial position and the horizontal and vertical spacing between each visualization component, and the coordinate position of each visualization component in the viewing area is determined based on the three-dimensional spatial position and the horizontal and vertical spacing between each visualization component, and the corresponding visualization area is determined based on the regional coordinate position, that is, the visualization area position of each visualization component in the display canvas is determined according to the coordinate position of each visualization component in the viewing area and its width and height.

[0027] S15: performing rendering layout analysis on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data, to obtain corresponding rendering layout analysis data; In the specific implementation process of the present invention, the rendering layout analysis is performed on the visualization area corresponding to the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data to obtain the corresponding rendering layout analysis data, including: determining the rendering information of each visualization component of the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data in the corresponding visualization area; determining the layout mode of the view area based on the rendering information of each visualization component, and performing a visualization preview based on the rendering information and the layout mode to obtain a visualization preview effect; performing a color distribution analysis based on the visualization preview effect to obtain color distribution information, and performing a color mixing test based on the color distribution information to obtain a color mixing test result; adjusting the rendering information of each visualization component based on the color mixing test result to obtain the adjusted rendering information of each visualization component, and determining the corresponding rendering layout analysis data based on the adjusted rendering information and the layout mode of each visualization component.

[0028] Specifically, the rendering information of each visualization component of the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data in the corresponding visualization area is determined, and the corresponding rendering information is matched according to each visualization component of each analysis data. Different visualization components correspond to different rendering information, and the rendering information includes color, shadow, and background, etc. The layout mode of the view area is determined based on the rendering information of each visualization component, and the overall layout of the view area is determined according to the rendering information of each visualization component, that is, the layout mode. The layout mode is the background color configuration and font color configuration of the view area, etc., and a visual preview is performed based on the rendering information and the layout mode, that is, the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data are previewed in the corresponding visualization area according to the rendering information and the layout mode to obtain a visual preview effect. Based on the visual preview effect, color distribution analysis is performed to obtain color distribution information, and the color distribution information includes the distribution of different colors in the view area, and a color mixing test is performed based on the color distribution information. The contrast between adjacent colors is analyzed according to the color distribution information, that is, the light and dark contrast difference between two colors is analyzed, and each contrast is projected into a preset human eye model for a color mixing test, and the manifestation of the color combination in the human eye is tested to obtain a color mixing test result. The rendering information of each visualization component is adjusted based on the color mixing test result. If the color contrast is too low, the human eye cannot distinguish different colors. If the color contrast is too high, the user will feel dizzy. Therefore, the rendering information of the visualization component needs to be adjusted according to how the color combination appears in the human eye, so that the rendering of the visualization component is more in line with the user's visual experience. The adjusted rendering information of each visualization component is obtained, and the corresponding rendering layout analysis data is determined based on the adjusted rendering information and layout mode of each visualization component. The overall layout color of the view area is adjusted according to the adjusted rendering information, and the rendering layout analysis data is generated from the adjusted rendering information of each visualization component and the adjusted layout mode.

[0029] S16: Visually displaying the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data in a corresponding visualization area based on the rendering layout analysis data.

[0030] In the specific implementation process of the present invention, the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data are visualized in the corresponding visualization area based on the rendering layout analysis data, including: drawing the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data in the corresponding visualization area based on the rendering layout analysis data, and deploying a listening component in the corresponding visualization area.

[0031] Specifically, based on the rendering layout analysis data, the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data are drawn in the corresponding visualization area, and the view drawing result is displayed in the display canvas. A monitoring component is deployed in the corresponding visualization area, and the monitoring component is used to monitor the change of the display canvas size. When the size of the display canvas is adjusted, the size of each visualization component is also adjusted accordingly to achieve adaptive layout of the components.

[0032] In an embodiment of the present invention, the public dimension model layer of the data center uses semantic embedding to extract target data in the data warehouse, and can quickly and accurately extract target data from large data sets. Using target data based on decision trees to analyze student learning conditions, and using target data to analyze subject comprehensive development, can improve the efficiency and accuracy of student learning conditions analysis and subject comprehensive development analysis, so that the comprehensive school situation analysis data obtained can more comprehensively and accurately reflect the overall situation of the school. Based on the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, the corresponding visualization area is determined using object relationships, and rendering layout analysis is performed on each visualization area to visualize the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, so as to avoid the mismatch between the visualization component and the interface size, improve the rationality and aesthetics of the visualization layout, and enable relevant personnel to intuitively and clearly understand the comprehensive school situation analysis data.

[0033] Embodiment 2 See also Figure 2 , Figure 2 It is a flow chart of a data analysis visualization method for comprehensive school conditions in another embodiment of the present invention, the method is applied to a data middle station, the data middle station includes a public dimension model layer and an application data layer, and the method includes: S201: The common dimension model layer uses semantic embedding to extract target data in the data warehouse; S202: the application data layer uses the target data to perform student learning situation analysis based on the decision tree to obtain student learning situation analysis data, and performs subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data; S203: Performing comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data; S204: Determine a corresponding visualization area using object relationships based on the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data; S205: Determine rendering information of each visualization component of the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data in the corresponding visualization area; S206: determining a layout mode of the view area based on rendering information of each visualization component, and performing a visualization preview based on the rendering information and the layout mode to obtain a visualization preview effect; S207: performing color distribution analysis based on the visual preview effect to obtain color distribution information, and performing a color mixing test based on the color distribution information to obtain a color mixing test result; S208: adjusting the rendering information of each visualization component based on the color mixing test result to obtain the adjusted rendering information of each visualization component, and determining corresponding rendering layout analysis data based on the adjusted rendering information and layout mode of each visualization component; S209: Visually displaying the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data in a corresponding visualization area based on the rendering layout analysis data.

[0034] In an embodiment of the present invention, the public dimension model layer of the data center uses semantic embedding to extract target data in the data warehouse, and can quickly and accurately extract target data from large data sets. Using target data based on decision trees to analyze student learning conditions, and using target data to analyze subject comprehensive development, can improve the efficiency and accuracy of student learning conditions analysis and subject comprehensive development analysis, so that the comprehensive school situation analysis data obtained can more comprehensively and accurately reflect the overall situation of the school. Based on the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, the corresponding visualization area is determined using object relationships, and rendering layout analysis is performed on each visualization area to visualize the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, so as to avoid the mismatch between the visualization component and the interface size, improve the rationality and aesthetics of the visualization layout, and enable relevant personnel to intuitively and clearly understand the comprehensive school situation analysis data.

[0035] Embodiment 3 See also Figure 3 , Figure 3 : is a schematic diagram of the structure of a data analysis and visualization device for comprehensive school conditions in an embodiment of the present invention. The device is applied to a data middle station, and the data middle station includes a public dimension model layer and an application data layer. The device includes: Data extraction module 31: used for extracting target data in the data warehouse by using semantic embedding in the common dimension model layer; The learning situation and subject analysis module 32 is used to apply the data layer to perform student learning situation analysis using the target data based on the decision tree to obtain student learning situation analysis data, and to perform subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data; School situation analysis module 33: used to perform comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data; The region determination module 34 is used to determine the corresponding visualization region by using object relationships based on the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data; Layout analysis module 35: used to perform rendering layout analysis on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data, and obtain corresponding rendering layout analysis data; Visualization display module 36: used for visually displaying the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data in the corresponding visualization area based on the rendering layout analysis data.

[0036] In the specific implementation process of the present invention, the specific implementation method of the device item can refer to the implementation method of the above-mentioned method item, which will not be repeated here.

[0037] In an embodiment of the present invention, the public dimension model layer of the data center uses semantic embedding to extract target data in the data warehouse, and can quickly and accurately extract target data from large data sets. Using target data based on decision trees to analyze student learning conditions, and using target data to analyze subject comprehensive development, can improve the efficiency and accuracy of student learning conditions analysis and subject comprehensive development analysis, so that the comprehensive school situation analysis data obtained can more comprehensively and accurately reflect the overall situation of the school. Based on the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, the corresponding visualization area is determined using object relationships, and rendering layout analysis is performed on each visualization area to visualize the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, so as to avoid the mismatch between the visualization component and the interface size, improve the rationality and aesthetics of the visualization layout, and enable relevant personnel to intuitively and clearly understand the comprehensive school situation analysis data.

[0038] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, a data analysis visualization method for comprehensive school conditions of any one of the above embodiments is implemented. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or optical card. That is, the storage device includes any medium that can store or transmit information in a readable form by a device (for example, a computer, a mobile phone), which can be a read-only memory, a disk or an optical disk, etc.

[0039] Embodiment 4 See also Figure 4 , Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention.

[0040] The embodiment of the present invention further provides an electronic device, such as Figure 4 As shown, the electronic device includes a memory 41, a processor 43, and a computer program 42 stored in the memory 41 and executable on the processor 43. Those skilled in the art will appreciate that Figure 3The electronic device shown does not constitute a limitation on all devices, and may include more or fewer components than shown, or combine certain components. The memory 41 can be used to store the computer program 42 and various functional modules, and the processor 43 runs the computer program 42 stored in the memory 41, thereby executing various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include both internal and external memories. The internal memory can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, or a random access memory. The external memory can include a hard disk, a floppy disk, a ZIP disk, a U disk, a magnetic tape, etc. The processor 43 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general processor may be a microprocessor, a single chip microcomputer or the processor 43 may also be any conventional processor, etc. The processor and memory disclosed in the present invention include but are not limited to these types of processors and memories. The processor and memory disclosed in the present invention are only examples and not limitations.

[0041] As an embodiment, the electronic device includes: one or more processors 43, a memory 41, and one or more computer programs 42, wherein the one or more computer programs 42 are stored in the memory 41 and are configured to be executed by the one or more processors 43, and the one or more computer programs 42 are configured to execute the comprehensive school situation data analysis visualization method in any of the above-mentioned embodiments. Please refer to the above-mentioned embodiments for the specific implementation process, which will not be repeated here.

[0042] In an embodiment of the present invention, the public dimension model layer of the data center uses semantic embedding to extract target data in the data warehouse, and can quickly and accurately extract target data from large data sets. Using target data based on decision trees to analyze student learning conditions, and using target data to analyze subject comprehensive development, can improve the efficiency and accuracy of student learning conditions analysis and subject comprehensive development analysis, so that the comprehensive school situation analysis data obtained can more comprehensively and accurately reflect the overall situation of the school. Based on the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, the corresponding visualization area is determined using object relationships, and rendering layout analysis is performed on each visualization area to visualize the student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data, so as to avoid the mismatch between the visualization component and the interface size, improve the rationality and aesthetics of the visualization layout, and enable relevant personnel to intuitively and clearly understand the comprehensive school situation analysis data.

[0043] In addition, the above is a detailed introduction to a comprehensive school data analysis visualization method and related devices provided by an embodiment of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A data analysis and visualization method for comprehensive school conditions, characterized in that: Applied to a data middle platform, the data middle platform includes a public dimension model layer and an application data layer; the method includes: The common dimensional model layer uses semantic embedding to extract target data in the data warehouse; The application data layer uses the target data to perform student learning situation analysis based on the decision tree to obtain student learning situation analysis data, and performs subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data; Performing a comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data; Determine the corresponding visualization area by using object relationship based on the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Perform rendering layout analysis on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data to obtain corresponding rendering layout analysis data; Based on the rendering layout analysis data, the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data are visualized in the corresponding visualization area.

2. The data analysis and visualization method of comprehensive school conditions according to claim 1 is characterized in that: The method of extracting target data from a data warehouse by using semantic embedding includes: Parse the query statement in the query request to obtain query task information; Perform semantic embedding based on the query task information to obtain a first semantic embedding vector, and match the first semantic embedding vector with a plurality of second semantic embedding vectors in the index database to obtain a matching result; The corresponding operation engine is determined based on the operator in the query statement, and the target data is extracted from the data warehouse using the operation engine based on the matching result.

3. The data analysis and visualization method of comprehensive school conditions according to claim 1 is characterized in that: The method of performing a student learning situation analysis based on the decision tree and using the target data to obtain student learning situation analysis data, and performing a subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data, includes: Extracting student data from the target data, and dividing the student data into objective evaluation data and subjective evaluation data; Based on a random forest model composed of a plurality of decision trees, the objective evaluation data and the subjective evaluation data are used to analyze the student's learning situation, thereby obtaining student's learning situation analysis data; Based on the target data, analyze the school conditions, teacher team construction, talent training, scientific research and academic degree status to obtain data on school conditions, teacher team construction, talent training, scientific research and academic degree status; Generate comprehensive discipline development analysis data based on school conditions data, faculty team construction data, talent training data, scientific research data and discipline degree data.

4. The data analysis and visualization method of comprehensive school conditions according to claim 1 is characterized in that: The comprehensive school situation analysis is performed based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain the comprehensive school situation analysis data, including: Determine the evaluation dimensions and evaluation indicators, and use the student learning situation analysis data and the subject comprehensive development analysis data to perform school situation profile analysis based on the evaluation dimensions and evaluation indicators to obtain school situation profile information; Classify the student learning situation analysis data based on support vector machine to obtain classification results; Generate comprehensive school situation analysis data based on classification results and school profile information.

5. The data analysis and visualization method of comprehensive school conditions according to claim 1 is characterized in that: The determining of the corresponding visualization area by using object relationships based on the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data includes: Match corresponding visualization components to the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Analyze the object information of student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Perform display resolution analysis based on the data volume of student learning situation analysis data, subject comprehensive development analysis data, and comprehensive school situation analysis data to obtain the corresponding display resolution; Determine the horizontal spacing and the vertical spacing between the visualization components based on the width and height of the view area and the width and height of each visualization component using the object information; The three-dimensional space position is determined based on the visualization components and display resolution corresponding to the comprehensive subject development analysis data, and the corresponding regional coordinate position is determined based on the three-dimensional space position and the horizontal and vertical spacing between each visualization component, and the corresponding visualization area is determined based on the regional coordinate position.

6. The data analysis and visualization method of comprehensive school conditions according to claim 1 is characterized in that: The rendering layout analysis is performed on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data, and the comprehensive school situation analysis data to obtain the corresponding rendering layout analysis data, including: Determine the rendering information of each visualization component in the corresponding visualization area of ​​the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data; Determine a layout mode of the view area based on rendering information of each visualization component, and perform a visualization preview based on the rendering information and the layout mode to obtain a visualization preview effect; Performing color distribution analysis based on the visual preview effect to obtain color distribution information, and performing a color mixing test based on the color distribution information to obtain a color mixing test result; The rendering information of each visualization component is adjusted based on the color mixing test result to obtain the adjusted rendering information of each visualization component, and the corresponding rendering layout analysis data is determined based on the adjusted rendering information and the layout mode of each visualization component.

7. The data analysis and visualization method of comprehensive school conditions according to claim 1 is characterized in that: The method of visually displaying the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data in the corresponding visualization area based on the rendering layout analysis data includes: Based on the rendering layout analysis data, the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data are visually drawn in the corresponding visualization area, and a monitoring component is deployed in the corresponding visualization area.

8. A data analysis and visualization device for comprehensive school conditions, characterized in that: Applied to a data middle platform, the data middle platform includes a public dimension model layer and an application data layer; the device includes: Data extraction module: used for extracting target data from the data warehouse using semantic embedding in the common dimensional model layer; The learning situation and subject analysis module is used to apply the data layer to analyze the student learning situation using the target data based on the decision tree to obtain the student learning situation analysis data, and to perform subject comprehensive development analysis based on the target data to obtain subject comprehensive development analysis data; School situation analysis module: used to perform comprehensive school situation analysis based on the student learning situation analysis data and the subject comprehensive development analysis data to obtain comprehensive school situation analysis data; Region determination module: used to determine the corresponding visualization region by using object relationship based on the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data; Layout analysis module: used to perform rendering layout analysis on the visualization areas corresponding to the student learning situation analysis data, the subject comprehensive development analysis data and the comprehensive school situation analysis data, and obtain the corresponding rendering layout analysis data; Visualization display module: used to visualize the student learning situation analysis data, subject comprehensive development analysis data and comprehensive school situation analysis data in the corresponding visualization area based on the rendering layout analysis data.

9. An electronic device, comprising a processor and a memory, characterized in that: The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the data analysis and visualization method for comprehensive school conditions as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the data analysis and visualization method for comprehensive school conditions as described in any one of claims 1 to 7.

Images