Multi-dimensional data fused college music major student employment prospect analysis method

Abstract

The invention relates to the technical field of data analysis, and particularly discloses a college music major student employment foreground analysis method fusing multi-dimensional data, which comprises the following steps: collecting employment, practice experience and industry demand data of students from multiple platforms, performing text analysis on the collected data by using Pandaas and NLP libraries, and automatically extracting key information; according to student personal information, utilizing a Feature Tools tool to automatically generate multi-dimensional features related to employment, and adopting a graph neural network to analyze a relationship between the multi-dimensional features and the collected data; according to the method, multi-dimensional features related to employment are automatically generated by using a Feature Tools tool, complex relationships between the features and actual employment data are analyzed in combination with a graph neural network, the collected data are deeply analyzed and accurately predicted by constructing and applying a prediction model, and finally personalized employment suggestions are generated. And students are guided to make decisions in occupational planning.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and in particular relates to a method for analyzing employment prospects of college music majors by integrating multi-dimensional data. Background Art

[0002] With the continuous popularization of education, more and more families have realized the importance of knowledge. As a result, colleges and universities continue to expand their enrollment, and there are more and more college students. However, after graduation, students face difficult choices. Most college students are confused about how to apply the professional knowledge they have learned, how to choose a job, what the employment prospects are, whether to consider postgraduate entrance examinations or applying for public institutions, etc.

[0003] At present, the employment prospect analysis is simply to collect data from the Internet, use the collected network data as a reference, and determine the degree of professional ability of students based on their academic performance, and provide employment prospect suggestions for music majors. However, since the employment prospect analysis must not only consider the current professional matching and salary situation, but also the future development of employment, it is a very complex analysis and matching process. This method of only providing employment prospect suggestions and references based on network data and student grades cannot meet the practical application of employment prospect analysis for music majors. If a student's academic performance in school is very poor, but the student is very capable in interpersonal communication, but the student's employment prospects are not good according to the analysis, the student will be confused about his or her employment prospects even though he or she has a skill.

[0004] Therefore, it is necessary to propose a method for analyzing the employment prospects of college music majors that integrates multi-dimensional data to solve the problem of inaccurate analysis and prediction of the employment prospects of music majors in the existing technology.

[0005] The above information disclosed in this background technology is only used to increase the understanding of the background technology of the present invention and therefore, it may include information that does not constitute the prior art known to ordinary technicians in this field. Summary of the invention

[0006] The purpose of the present invention is to provide a method for analyzing the employment prospects of college music majors by integrating multi-dimensional data to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for analyzing employment prospects of college music majors by integrating multi-dimensional data, including:

[0009] Collect data on students’ employment, internship experience, and industry needs from multiple platforms, use Pandas and NLP libraries to perform text analysis on the collected data, and automatically extract key information;

[0010] Automatically generate employment-related multidimensional features using Feature Tools according to the student personal information, and use a graph neural network to analyze the relationship between the multidimensional features and the collected data;

[0011] Introducing reinforcement learning algorithms to simulate the learning and employment performance of the students in different educational environments, and revealing the impact of different variables on the employment performance of the students through comparative analysis;

[0012] Analyzing and predicting the collected data through a prepared prediction model based on the multi-dimensional features to generate a prediction result;

[0013] Providing personalized employment advice to the student using an artificial intelligence algorithm based on the prediction results combined with the student's personal information and interests;

[0014] Establish a continuous learning mechanism to utilize the collected interaction information between students, enterprises, and industry experts to continuously optimize the data collection, processing, and analysis processes.

[0015] Preferably, the data sources from multiple platforms are automatically integrated through the API interface to collect data on the students' employment, internship experience and industry needs, and obtain industry employment reports issued by the government; the collected data are processed and cleaned using Pandas and NLP libraries to identify key words and key information of job requirements; the numerical data in the collected data are standardized and normalized, and the collected data are stored in a database.

[0016] Preferably, each node is defined based on the multidimensional features, the edges of each node are determined in combination with the collected data, and a feature graph structure is formed with all the nodes and their edges; according to the feature graph structure, the multidimensional features and the upstream and downstream relationships of the collected data are propagated and aggregated in the feature graph structure through iteration of a multi-layer graph convolutional network, and an analysis result is generated through an output layer;

[0017] Statistical methods are used to explore the collected data to identify the nonlinear correlation between the impact of different influencing factors on employment; all the generated multidimensional features and the nonlinear correlations are displayed in the form of a collinear time scale diagram, and the analysis results are displayed in the form of a heat map.

[0018] Preferably, Unity is used to build a virtual simulation environment, and by giving different educational environments and practice opportunities, the employment performance of the students in different educational environments is simulated; the employment decision is trained using a reinforcement learning algorithm, and combined with the given different educational environments and practice opportunities, the impact of different employment decisions on the employment success rate is simulated to generate simulation results; based on the simulation results, a comparative analysis is performed to reveal the impact of different variables of the students on their employment performance, and an analysis report is generated.

[0019] Preferably, the prepared prediction model is retrained based on the collected data using the multidimensional features as input, and cross-validation is used to optimize model parameters; the prediction performance of the retrained prediction model is evaluated through a confusion matrix to generate an evaluation result, and the model is tuned according to the evaluation result to remove redundant features; the collected data is analyzed and predicted using the optimized prediction model to generate the prediction result.

[0020] Preferably, the matching degree between the student and different positions and industries is analyzed based on the prediction results and the student personal information; job suggestions and development paths are generated using a recommendation algorithm based on the prediction results and the student's interests; and career planning suggestions and skill improvement directions are provided to students using an artificial intelligence algorithm based on the job suggestions and development paths.

[0021] Preferably, the employment status of the students is collected, and industry dynamics and new job requirements are obtained in real time by establishing cooperation with the enterprises and the industry experts; the employment status of the students, the industry dynamics and the new job requirements are used as input to update and adjust the training data of the graph neural network and the multidimensional features; an employment trend report based on the real-time industry dynamics is provided, and the employment guidance strategy is adjusted regularly.

[0022] Preferably, the method further comprises using Power BI or Tableau tools to establish a real-time updated analytical dashboard for displaying the collected data; using VR / AR technology to present the real-time industry dynamics as three-dimensional graphics and integrating them into the analytical dashboard.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The present invention collects student employment, internship experience and industry demand data from different platforms, and uses Pandas and NLP technology for text analysis, which can efficiently extract key information, and use the Feature Tools tool to automatically generate multidimensional features related to employment. It combines graph neural networks to analyze the complex relationship between these features and actual employment data, helping to reveal potential influencing factors, and introduces reinforcement learning algorithms to simulate students' learning and employment performance in different educational environments, so as to identify the specific impact of each variable on employment outcomes. It also constructs and applies prediction models to conduct in-depth analysis and accurate prediction of the collected data, and finally generates personalized employment suggestions to guide students' decision-making in career planning.

[0025] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of the method for analyzing employment prospects of college music majors by integrating multi-dimensional data of the present invention. DETAILED DESCRIPTION

[0027] 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.

[0028] Embodiment 1:

[0029] See also Figure 1 As shown in the figure, a method for analyzing the employment prospects of college music students integrating multi-dimensional data includes:

[0030] Collect data on students’ employment, internship experience, and industry needs from multiple platforms, use Pandas and NLP libraries to perform text analysis on the collected data, and automatically extract key information;

[0031] Based on students’ personal information, Feature Tools is used to automatically generate employment-related multidimensional features, and graph neural networks are used to analyze the relationship between multidimensional features and collected data.

[0032] Introducing reinforcement learning algorithms to simulate students’ learning and employment performance in different educational environments, and revealing the impact of different variables on students’ employment performance through comparative analysis;

[0033] Analyze and predict the collected data through the prepared prediction model based on multi-dimensional features to generate prediction results;

[0034] Based on the prediction results and combined with students’ personal information and interests, AI algorithms are used to provide students with personalized career advice;

[0035] Establish a continuous learning mechanism to utilize the collected interactive information between students, enterprises, and industry experts to continuously optimize the data collection, processing, and analysis processes.

[0036] Automatically integrate data sources from multiple platforms through API interfaces, such as recruitment websites, industry forums, social media (such as LinkedIn, Weibo, Zhihu, etc.), etc., to collect data on students' employment, internship experience and industry needs, and obtain industry employment reports released by the government;

[0037] Use Pandas and NLP libraries (such as spaCy, BERT, etc.) to process and clean the collected data to identify key words and key information of job requirements;

[0038] Pandas is a powerful, open source Python data analysis library that is widely used for tasks such as data cleaning, data processing, and data analysis. It provides efficient and flexible data structures, especially suitable for processing structured data (such as tabular data).

[0039] The numerical data in the collected data (such as academic GPA, salary, industry growth rate, etc.) are standardized and normalized, and the collected data are stored in the database.

[0040] The extracted features cover multiple dimensions such as academic personal characteristics, educational background, industry needs, etc. The relationship between different characteristics and target variables such as employment rate, salary level, and job type is analyzed to find potential patterns and trends.

[0041] Feature Tools is an open source Python library for automated feature engineering, which is mainly used to automatically generate features with predictive capabilities from raw data. Feature engineering involves extracting useful information from raw data for modeling, and Feature Tools greatly reduces the complexity and manual workload of feature engineering through its automation capabilities.

[0042] Define each node based on multi-dimensional features, determine the edges of each node based on the collected data, and form a feature graph structure with all nodes and their edges;

[0043] According to the feature graph structure, through the iteration of the multi-layer graph convolutional network, the multi-dimensional features and the upstream and downstream relationships of the collected data are propagated and aggregated in the feature graph structure, and the analysis results are generated through the output layer;

[0044] In each layer of the graph neural network, each node exchanges information with its neighboring nodes. For example, the student node receives information from the position node, industry node, etc., and the position node receives information from the student node and industry trend node.

[0045] Aggregation functions (such as weighted average, maximum pooling, etc.) are used to merge information from neighboring nodes, which helps nodes capture the influence from their neighbors so that the representation of each node can reflect its upstream and downstream contextual information.

[0046] The output of each layer will serve as the input of the next layer, continuously updating the representation of the node. Through the iteration of multi-layer graph convolutional networks, the feature vector of the node gradually aggregates information from the global structure, and finally the representation of the node better reflects its position and relationship in the graph.

[0047] Use statistical methods to explore the collected data and identify the nonlinear relationship between different influencing factors (such as academic qualifications, on-campus activities, industry dynamics, etc.) and employment;

[0048] All generated multidimensional features and nonlinear associations are presented as collinear time-scale plots, and the analysis results are presented as heat maps.

[0049] The collinear time scale is similar to the hot search index, which is the appearance of a certain word in a certain period of time. Due to its high frequency of appearance, it becomes a keyword and also represents a research hotspot. The collinear time scale diagram can show the development and changes of employment content that has been focused on in different time periods.

[0050] Use Unity to build a virtual simulation environment to simulate students' employment performance in different educational environments by giving them different educational environments and practice opportunities;

[0051] Use reinforcement learning algorithms to train employment decisions, combine different educational environments and practice opportunities, simulate the impact of different employment decisions on employment success rates, and generate simulation results;

[0052] Based on the simulation results, comparative analysis is performed to reveal the impact of different variables of students (such as academic qualifications, on-campus activities, industry dynamics, etc.) on their employment performance, and an analysis report is generated.

[0053] Retrain the prepared prediction model based on the collected data using multi-dimensional features as input, and optimize the model parameters using cross-validation;

[0054] Evaluate the prediction performance of the retrained prediction model through the confusion matrix, generate evaluation results, and perform optimization based on the evaluation results to remove redundant features;

[0055] Use the optimized prediction model to analyze and predict the collected data to generate prediction results.

[0056] The confusion matrix is ​​used to record the prediction results of the model, as shown in the following table. For each category, there are four cases: if the actual situation is true and the prediction is true, it is recorded as TP (True Positive); if the actual situation is true and the prediction is false, it is recorded as FN (False Negative); if the actual situation is false and the prediction is true, it is recorded as FP (Falsepositive).

[0057]

[0058] Embodiment 2:

[0059] See also Figure 1 As shown, this embodiment is basically the same as the above embodiment, except that the matching degree between students and different positions and industries is analyzed based on the prediction results and student personal information;

[0060] Generate job recommendations and development paths based on prediction results and student interests using recommendation algorithms (such as collaborative filtering);

[0061] Based on job recommendations and development paths, AI algorithms are used to provide students with career planning advice and skill improvement directions. Real-time career guidance can be provided through chatbots, smart tutors, etc.

[0062] Collect students' employment information and obtain industry trends and new job requirements in real time by establishing cooperation with enterprises and industry experts;

[0063] Design a feedback mechanism to collect students’ employment feedback through questionnaires, online interviews and social platforms;

[0064] Taking students’ employment status, industry trends, and new job requirements as input, we update and adjust the training data and multi-dimensional features of the graph neural network.

[0065] Generate a personalized career outlook report detailing students' possible career paths, required skills, and recommended advancement areas.

[0066] Provide employment trend reports based on real-time industry dynamics and regularly adjust employment guidance strategies.

[0067] The method also includes using PowerBI or Tableau tools to build a real-time updated analytical dashboard to display the collected data. Users can select dimensions (such as student background, industry needs, etc.) to view data as needed;

[0068] VR / AR technology is used to present real-time industry dynamics as three-dimensional graphics and integrate them into analytical dashboards. Users can interact with data through a virtual environment to obtain more intuitive employment trend analysis.

[0069] By integrating real-time employment data (such as monthly industry demand, salary changes, etc.) into the analytical dashboard, users can view the latest employment trends in different dimensions.

[0070] From the above, it can be seen that the present invention can efficiently extract key information by collecting student employment, internship experience and industry demand data from different platforms and using Pandas and NLP technology for text analysis, and automatically generate multidimensional features related to employment using the Feature Tools tool. The complex relationship between these features and actual employment data is analyzed in combination with graph neural networks to help reveal potential influencing factors. Reinforcement learning algorithms are introduced to simulate students' learning and employment performance in different educational environments, so as to identify the specific impact of each variable on employment outcomes. In addition, by constructing and applying a predictive model, the collected data is deeply analyzed and accurately predicted, and ultimately personalized employment recommendations are generated to guide students' decision-making in career planning.

[0071] Embodiment 3:

[0072] The embodiment of the present invention also provides a computer-readable storage medium, on which is stored a program of a method for analyzing employment prospects of college music majors by integrating multi-dimensional data as described above, and when the program is executed by a processor, each process of the above-mentioned employment prospect analysis method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. Among them, the computer-readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0073] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0074] In the drawings of the embodiments disclosed in the present invention, only the structures involved in the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0075] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0076] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for analyzing employment prospects of college music majors by integrating multi-dimensional data, characterized in that: include: Collect data on students’ employment, internship experience, and industry needs from multiple platforms, use Pandas and NLP libraries to perform text analysis on the collected data, and automatically extract key information; Automatically generate employment-related multidimensional features using Feature Tools according to the student personal information, and use a graph neural network to analyze the relationship between the multidimensional features and the collected data; Introducing reinforcement learning algorithms to simulate the learning and employment performance of the students in different educational environments, and revealing the impact of different variables on the employment performance of the students through comparative analysis; Analyzing and predicting the collected data through a prepared prediction model based on the multi-dimensional features to generate a prediction result; Providing personalized employment advice to the student using an artificial intelligence algorithm based on the prediction results combined with the student's personal information and interests; Establish a continuous learning mechanism to utilize the collected interaction information between students, enterprises, and industry experts to continuously optimize the data collection, processing, and analysis processes.

2. According to the method for analyzing employment prospects of college music majors by integrating multi-dimensional data in claim 1, it is characterized by: The data on students’ employment, internship experience and industry needs are collected from multiple platforms, and Pandas and NLP libraries are used to perform text analysis on the collected data to automatically extract key information, including: Automatically integrate data sources from multiple platforms through API interfaces to collect data on the students’ employment, internship experience and industry needs, and obtain industry employment reports released by the government; Use Pandas and NLP libraries to process and clean the collected data to identify key words and key information of job requirements; The numerical data in the collected data are standardized and normalized, and the collected data are stored in a database.

3. The method for analyzing employment prospects of college music majors by integrating multi-dimensional data according to claim 2 is characterized by: The adopting of a graph neural network to analyze the relationship between the multidimensional features and the collected data includes: Defining each node based on the multi-dimensional features, determining the edges of each node in combination with the collected data, and forming a feature graph structure with all the nodes and their edges; According to the iteration of the feature graph structure through a multi-layer graph convolutional network, the multi-dimensional features and the upstream and downstream relationships of the collected data are propagated and aggregated in the feature graph structure, and an analysis result is generated through an output layer; Use statistical methods to explore the collected data and identify the nonlinear relationship between different influencing factors and employment effects; All the generated multidimensional features and the nonlinear associations are displayed in the form of a collinear time scale diagram, and the analysis results are displayed in the form of a heat map.

4. The method for analyzing employment prospects of college music majors by integrating multi-dimensional data according to claim 3 is characterized by: The reinforcement learning algorithm is introduced to simulate the learning and employment performance of the students in different educational environments, and the influence of different variables of the students on their employment performance is revealed through comparative analysis, including: Use Unity to build a virtual simulation environment to simulate the employment performance of the students in different educational environments by giving them different educational environments and practice opportunities; Using a reinforcement learning algorithm to train the employment decision, combining the given different educational environments and practice opportunities, simulating the impact of different employment decisions on the employment success rate, and generating simulation results; According to the simulation results, comparative analysis is performed to reveal the impact of different variables of the students on their employment performance, and an analysis report is generated.

5. The method for analyzing employment prospects of college music majors by integrating multi-dimensional data according to claim 4 is characterized by: The step of analyzing and predicting the collected data based on the multi-dimensional features through a prepared prediction model to generate a prediction result includes: Retraining the prepared prediction model based on the collected data using the multidimensional features as input, and optimizing model parameters using cross-validation; Evaluate the prediction performance of the retrained prediction model through a confusion matrix, generate an evaluation result, and perform optimization according to the evaluation result to remove redundant features; The optimized prediction model is used to analyze and predict the collected data to generate the prediction result.

6. The method for analyzing employment prospects of college music majors by integrating multi-dimensional data according to claim 5 is characterized by: The method of providing personalized employment advice to the student by using an artificial intelligence algorithm based on the prediction results combined with the student's personal information and interests includes: Analyzing the matching degree between the student and different positions and industries according to the prediction results and the student personal information; Generate job suggestions and development paths using a recommendation algorithm based on the prediction results and the student's interests; Based on the job recommendations and development paths, artificial intelligence algorithms are used to provide students with career planning advice and skill improvement directions.

7. The method for analyzing employment prospects of college music majors by integrating multi-dimensional data according to claim 6 is characterized by: The establishment of a continuous learning mechanism utilizes the collected interactive information of students, enterprises, and industry experts to continuously optimize the data collection, processing, and analysis processes, including: Collect the employment information of the students, and obtain industry trends and new job requirements in real time by establishing cooperation with the enterprises and industry experts; Taking the employment situation of the students, the industry dynamics and the new job requirements as input, updating and adjusting the training data of the graph neural network and the multi-dimensional features; Provide employment trend reports based on real-time industry dynamics and regularly adjust employment guidance strategies.

8. The method for analyzing employment prospects of college music majors by integrating multi-dimensional data according to claim 7 is characterized in that: The method further comprises: Use PowerBI or Tableau to build a real-time updated analytical dashboard to display the collected data; VR / AR technology is used to present the real-time industry dynamics as three-dimensional graphics and integrate them into the analysis dashboard.

Images