Industrial design talent demand quantitative analysis method and system based on cloud computing

Abstract

The invention discloses an industrial design talent demand quantitative analysis method and system based on cloud computing, and relates to the technical field of talent demand analysis, and the method comprises the steps: collecting talent demand data of the industrial design field from a plurality of data sources in real time through an AP I and a data flow service of a cloud computing platform; performing data classification on the talent demand data to obtain industrial design industry demand data and industrial design post demand data; determining a support association relationship between the industrial design industry demand data and the industrial design post demand data; the industrial design industry feature data, the industrial design post feature data and the support association feature data are stored and analyzed by using the distributed computing capability of the cloud computing platform so as to output a quantitative analysis result of the future demand trend of industrial design talents; and generating a talent demand prediction report based on the output quantitative analysis result of the future demand trend of the industrial design talents.

Description

Technical Field

[0001] This application relates to the technical field of talent demand analysis. Specifically, it relates to a method and system for quantitative analysis of industrial design talent demand based on cloud computing. Background Art

[0002] With the rapid development of the global economy and industrial upgrading, industrial design, as an important force driven by innovation, plays a crucial role in enhancing product competitiveness and promoting industrial transformation. Industrial design not only involves the combination of aesthetics and practicality, but also involves multiple fields such as user experience, materials science, and manufacturing processes. Therefore, the demand for industrial design talents is also increasing continuously, which poses higher requirements for the cultivation and allocation of talents.

[0003] However, there are many deficiencies in traditional industrial design talent demand analysis methods, including the lack of effective quantitative analysis tools, resulting in inaccurate prediction and evaluation of talent demand.

[0004] For the above problems, no effective solutions have been proposed yet. Summary of the Invention

[0005] Embodiments of this application provide a method and system for quantitative analysis of industrial design talent demand based on cloud computing to solve the above technical problems.

[0006] This application provides a method for quantitative analysis of industrial design talent demand based on cloud computing, including:

[0007] Using the API and data stream services of the cloud computing platform to collect talent demand data in the industrial design field in real time from multiple data sources;

[0008] Classifying the talent demand data to obtain industrial design industry demand data and industrial design position demand data;

[0009] Determining the support correlation relationship between the industrial design industry demand data and the industrial design position demand data; and extracting industrial design industry characteristic data, industrial design position characteristic data, and support correlation characteristic data according to the support correlation relationship;

[0010] Using the distributed computing power of the cloud computing platform to store and analyze the industrial design industry characteristic data, the industrial design position characteristic data, and the support correlation characteristic data to output a quantitative analysis result of the future demand trend of industrial design talents;

[0011] Generating a talent demand prediction report based on the output quantitative analysis result of the future demand trend of industrial design talents.

[0012] Specifically, it has the following beneficial effects: By using the APIs and data stream services of the cloud computing platform, it realizes the real-time collection of talent demand data in the field of industrial design from multiple data sources. This real-time nature ensures the timeliness and accuracy of the analysis results, enabling educational institutions, enterprises, and policymakers to respond promptly to market changes; deeply classifying the collected talent demand data to distinguish between industry demand data and job demand data in the industrial design industry; this refined classification method improves the pertinence and effectiveness of data analysis, providing a high-quality data basis for subsequent analysis; determining the supporting correlation relationship between industry demand data and job demand data in the industrial design industry, which helps to reveal how industry demand affects job demand; extracting industrial design industry feature data, industrial design job feature data, and supporting correlation feature data based on the determined supporting correlation relationship. These feature data are the key to understanding the dynamics of talent demand and provide rich information for in-depth analysis; using the distributed computing power of the cloud computing platform to store and analyze a large amount of feature data. This distributed computing method improves the efficiency and stability of data processing, making large-scale data analysis possible; providing scientific decision-making support for educational institutions, enterprises, and policymakers. By deeply exploring the talent market and predicting future talent demand trends, this patent helps to optimize the allocation of educational resources, improve recruitment efficiency, and formulate relevant policies. Brief Description of the Drawings

[0013] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and the illustrative embodiments and descriptions thereof are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0014] Figure 1 It is a flowchart of an optional cloud computing-based method for quantitatively analyzing the talent demand in industrial design according to an embodiment of the present application;

[0015] Figure 2 It is a structural diagram of an optional cloud computing-based system for quantitatively analyzing the talent demand in industrial design according to an embodiment of the present application.

[0016] The realization of the objectives, functional features, and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0017] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application.

[0018] Optionally, as Figure 1 shown, this application provides a cloud computing-based method for quantitatively analyzing the talent demand in industrial design, including:

[0019] S101, use the API and data stream service of the cloud computing platform to collect the talent demand data in the industrial design field in real time from multiple data sources;

[0020] S102, classify the talent demand data to obtain the industrial design industry demand data and the industrial design position demand data;

[0021] S103, determine the support correlation relationship between the industrial design industry demand data and the industrial design position demand data; and extract the industrial design industry feature data, the industrial design position feature data and the support correlation feature data according to the support correlation relationship;

[0022] S104, use the distributed computing power of the cloud computing platform to store and analyze the industrial design industry feature data, the industrial design position feature data and the support correlation feature data, so as to output the quantitative analysis result of the future demand trend of industrial design talents;

[0023] S105, generate a talent demand prediction report based on the output quantitative analysis result of the future demand trend of industrial design talents.

[0024] Based on the embodiments provided in this application, use the API and data stream service of the cloud computing platform to collect the talent demand data in the industrial design field in real time from multiple data sources; classify the talent demand data to obtain the industrial design industry demand data and the industrial design position demand data; determine the support correlation relationship between the industrial design industry demand data and the industrial design position demand data; and extract the industrial design industry feature data, the industrial design position feature data and the support correlation feature data according to the support correlation relationship; use the distributed computing power of the cloud computing platform to store and analyze the industrial design industry feature data, the industrial design position feature data and the support correlation feature data, so as to output the quantitative analysis result of the future demand trend of industrial design talents; generate a talent demand prediction report based on the output quantitative analysis result of the future demand trend of industrial design talents. Thus, through cloud computing technology, the real-time, dynamic and quantitative analysis of the talent demand in the industrial design field is realized; the talent market can be deeply explored, the future talent demand trend can be predicted, and scientific decision-making support can be provided for educational institutions, enterprises and policy makers.

[0025] Specifically, it has the following beneficial effects: By using the APIs and data stream services of the cloud computing platform, the real-time collection of talent demand data in the field of industrial design from multiple data sources is realized. This real-time nature ensures the timeliness and accuracy of the analysis results, enabling educational institutions, enterprises, and policymakers to respond promptly to market changes; deeply classifying the collected talent demand data to distinguish between industrial design industry demand data and industrial design job demand data; this refined classification method improves the pertinence and effectiveness of data analysis, providing a high-quality data basis for subsequent analysis; determining the supporting correlation relationship between industrial design industry demand data and industrial design job demand data, which helps to reveal how industry demand affects job demand; according to the determined supporting correlation relationship, extracting industrial design industry characteristic data, industrial design job characteristic data, and supporting correlation characteristic data. These characteristic data are the key to understanding the dynamics of talent demand and provide rich information for in-depth analysis; using the distributed computing power of the cloud computing platform to store and analyze a large amount of characteristic data. This distributed computing method improves the efficiency and stability of data processing, making large-scale data analysis possible; providing scientific decision-making support for educational institutions, enterprises, and policymakers. By deeply exploring the talent market and predicting future talent demand trends, this patent helps to optimize the allocation of educational resources, improve recruitment efficiency, and formulate relevant policies.

[0026] Further, determining the supporting correlation relationship between industrial design industry demand data and industrial design job demand data is configured as follows:

[0027] Construct a binary tree, including: constructing the child nodes of the binary tree based on industrial design job demand data; constructing the root node of the binary tree based on industrial design industry demand data; constructing the edges of the binary tree based on the relationship between industrial design industry demand data and industrial design job demand data;

[0028] Among them, the child nodes represent job demands, and the attributes of the child nodes include skill demand distribution attributes, job demand growth rate attributes, educational background demand attributes, work experience demand attributes, and salary level demand attributes; the root node represents industry demand, and the attributes of the root node include business demand scale attributes, industry social attention index attributes, industry development trend attributes, and regional recruitment demand difference attributes; the edges represent the relationship between job demand and industry demand, and the weight of the edge represents the support degree, and the support degree is used to characterize the degree of influence of industry demand on job demand;

[0029] Randomly initialize the population; among them, each individual in the population is a path from the root node to the leaf node, used to represent the matching pattern between job demand and industry demand, and the matching pattern includes hierarchical relationship and dependency relationship;

[0030] Define a fitness function; wherein, the fitness function is used to characterize the matching degree and support degree between the job requirements and the industry requirements;

[0031] Take each individual in the population as a path in a binary tree, and the fitness of the path is determined by the support degree of the nodes on the path; generate new paths through genetic operators, evaluate the effectiveness of the new paths through the fitness function, and select the path with the highest fitness as the basis for the next generation of the population;

[0032] Repeatedly apply genetic operators and selection mechanisms, and update the structure of the binary tree at the same time until the fitness function meets the fitness threshold; wherein, the genetic operators include a crossover operator and a mutation operator; the crossover operator is used to combine the characteristics of two individuals in the population to form a new path; the mutation operator is used to randomly select a node in the path and replace it with any other node;

[0033] Determine the support correlation relationship between the industrial design industry demand data and the industrial design job demand data according to the updated structure of the binary tree.

[0034] Furthermore, the industrial design industry demand data includes the industry business demand scale, the industry social attention index, the industry development trend, and the regional recruitment demand difference;

[0035] The industrial design job demand data includes the skill demand distribution, the job demand growth rate, the educational background demand, the work experience demand, and the salary level demand.

[0036] Optionally, as Figure 2 shown, this application provides a cloud computing-based quantitative analysis system for industrial design talent demand, including:

[0037] A talent demand data acquisition module 201, which is used to use the API and data stream services of the cloud computing platform to collect the talent demand data in the industrial design field from multiple data sources in real time;

[0038] A talent demand data classification module 202, which is used to classify the talent demand data to obtain the industrial design industry demand data and the industrial design job demand data;

[0039] A feature data extraction unit 203, which is used to determine the support correlation relationship between the industrial design industry demand data and the industrial design job demand data; and extract the industrial design industry feature data, the industrial design job feature data, and the support correlation feature data according to the support correlation relationship;

[0040] The requirement quantification analysis module 204 is configured to store and analyze industrial design industry characteristic data, industrial design position characteristic data, and supporting correlation characteristic data by using the distributed computing power of the cloud computing platform, so as to output a quantification analysis result of the future demand trend of industrial design talents;

[0041] The talent demand prediction report generation unit 205 is configured to generate a talent demand prediction report based on the output quantification analysis result of the future demand trend of industrial design talents.

[0042] Further, the characteristic data extraction unit determines the supporting correlation relationship between the industrial design industry demand data and the industrial design position demand data, and is configured as follows:

[0043] Construct a binary tree, including: constructing the child nodes of the binary tree based on the industrial design position demand data; constructing the root node of the binary tree based on the industrial design industry demand data; constructing the edges of the binary tree based on the relationship between the industrial design industry demand data and the industrial design position demand data;

[0044] Among them, the child nodes represent position demands, and the attributes of the child nodes include skill demand distribution attributes, position demand growth rate attributes, educational background demand attributes, work experience demand attributes, and salary level demand attributes; the root node represents industry demands, and the attributes of the root node include business demand scale attributes, industry social attention index attributes, industry development trend attributes, and regional recruitment demand difference attributes; the edges represent the relationship between position demands and industry demands, and the weight of the edges represents the support degree, and the support degree is used to characterize the influence degree of industry demands on position demands;

[0045] Randomly initialize the population; among them, each individual in the population is a path from the root node to the leaf node, which is used to characterize the matching mode between position demands and industry demands, and the matching mode includes a hierarchical relationship and a dependency relationship;

[0046] Define a fitness function; among them, the fitness function is used to characterize the matching degree and support degree between position demands and industry demands;

[0047] Take each individual in the population as a path in the binary tree, and the fitness of the path is determined by the support degree of the nodes on the path; generate new paths through genetic operators, evaluate the effectiveness of the new paths through the fitness function, and select the path with the highest fitness as the basis for the next generation of the population;

[0048] Repeatedly apply genetic operators and selection mechanisms while updating the structure of the binary tree until the fitness function meets the fitness threshold; among them, the genetic operators include a crossover operator and a mutation operator; the crossover operator is used to combine the characteristics of two individuals in the population to form a new path; the mutation operator is used to randomly select a node in the path and replace it with any other node;

[0049] Determine the support correlation relationship between the industrial design industry demand data and the industrial design position demand data according to the structure of the updated binary tree.

[0050] Based on the embodiments provided in the present application, by constructing a binary tree model based on position requirements and industry requirements, the talent requirements in the industrial design field can be analyzed in detail; this structured representation method makes the relationship between position requirements and industry requirements clearer, which helps to deeply understand the complexity of the talent market; the edge weights in the binary tree model intuitively represent the influence degree of industry requirements on position requirements; this quantitative representation method provides a clear measurement standard for analysis and prediction, making the changing trend of talent requirements more predictable; by randomly initializing the population and characterizing the matching pattern between position requirements and industry requirements, the present technology can identify the hierarchical relationship and dependency relationship between different position requirements and industry requirements; this helps to reveal the dynamic changes in talent requirements and provides guidance for talent recruitment and cultivation; by defining the fitness function and applying genetic operators, the optimal path in the binary tree, that is, the path that best matches the position requirements and industry requirements, can be found; this method improves the accuracy of talent requirement prediction and helps to discover more effective talent allocation strategies; by repeatedly applying genetic operators and selection mechanisms while updating the binary tree structure until the fitness function meets the preset threshold, the present technology realizes the adaptive update of the model; this iterative optimization process ensures that the model can continuously evolve with the addition of new data, maintaining the timeliness and accuracy of the prediction results; this automated report generation process improves the decision-making efficiency and provides intuitive decision-making support for decision-makers; by providing a quantitative and dynamic analysis framework, it enhances the scientific decision-making support of educational institutions, enterprises, and policymakers in talent requirement prediction. This helps these organizations better adapt to market changes, optimize resource allocation, and formulate forward-looking talent strategies.

[0051] Further, the process of updating the structure of the binary tree is as follows:

[0052] Traverse the binary tree, and for each child node, calculate the support degree between it and the root node; if the support degree between the child node and the root node is higher than the preset threshold, determine that the child node is a leaf node in the topology; otherwise, determine that the child node is an internal node in the topology and continue to traverse its subtree; where the subtree is a tree rooted at a certain internal node and contains all the descendant nodes of this internal node.

[0053] Further, f(x) = α × Match(x) + β × Support(x);

[0054] where f(x) is the fitness function; Match(x) is used to represent the similarity between the job requirements and the industry requirements; Support(x) is used to represent the correlation strength between the job requirements and the industry requirements; x represents an individual in the population; α and β are both weight coefficients;

[0055]

[0056] where f j is the value of the j-th attribute of the child node corresponding to the job requirements; i is the value of the corresponding attribute in the root node corresponding to the industry requirements; γ is an adjustment parameter used to control the sensitivity of the matching degree; n is the number of attributes of the child node corresponding to the job requirements.

[0057] Further, the demand quantification analysis module uses the distributed computing power of the cloud computing platform to store and analyze the industrial design industry feature data, industrial design job feature data, and support correlation feature data, so as to output the quantification analysis result of the future demand trend of industrial design talents, and is configured as:

[0058] Preprocess the industrial design industry feature data, industrial design job feature data, and support correlation feature data;

[0059] Design a deep neural network model; where the deep neural network model is used to learn the relationship between the feature data and the future talent demand trend; the deep neural network model includes an input layer, a hidden layer, and an output layer; the input layer is used to receive the preprocessed industrial design industry feature data, industrial design job feature data, and support correlation feature data; the hidden layer contains at least two layers, and each layer uses the ReLU activation function; the output layer contains multiple output nodes and uses the linear activation function to predict the future talent demand trend;

[0060] M = DNN(Feature′, {W 1 , b 1 , W 2 , b 2 , …, W L , b L});

[0061] where M is the deep neural network model; Feature′ is the preprocessed industrial design industry feature data, industrial design job feature data, and support correlation feature data; W L , b LThey are the weights and biases of the L-th layer neural network respectively; DNN is a multi-layer function complex, and each layer of DNN is a function. Each layer of DNN takes the output of the previous layer as the input;

[0062] Using the preprocessed industrial design industry feature data, industrial design position feature data, and supporting correlation feature data as inputs on the cloud computing platform, using the mean squared error as the loss function, and training and optimizing the deep neural network model through the stochastic gradient descent method;

[0063] Applying the trained and optimized deep neural network model to predict the future demand trend of industrial design talents;

[0064] Using the data analysis tool of the cloud computing platform to aggregate and analyze the predicted future demand trend of industrial design talents, and obtaining a quantitative analysis result of the future demand trend of industrial design talents.

[0065] Furthermore, based on the output quantitative analysis result of the future demand trend of industrial design talents, generating a talent demand prediction report, which is configured to:

[0066] Using the data visualization tool of the cloud computing platform to convert the quantitative analysis result into a talent demand prediction report including charts.

[0067] Furthermore, the industrial design industry demand data includes the industry business demand scale, industry social attention index, industry development trend, and regional recruitment demand differences;

[0068] The industrial design position demand data includes skill demand distribution, position demand growth rate, educational background demand, work experience demand, and salary level demand.

[0069] It should be noted that in this application, the embodiments implemented on the side of the cloud computing-based industrial design talent demand quantitative analysis system can be mutually referred to with the embodiments implemented on the side of the cloud computing-based industrial design talent demand quantitative analysis method, and this application will not elaborate one by one.

[0070] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present invention by the same token.

Claims

1. A method for quantitative analysis of industrial design talent demand based on cloud computing, characterized in that: include: Use the API and data streaming services of the cloud computing platform to collect talent demand data in the field of industrial design from multiple data sources in real time; Classifying the talent demand data to obtain industrial design industry demand data and industrial design job demand data; Determine the supporting correlation relationship between the industrial design industry demand data and the industrial design position demand data; And extracting industrial design industry characteristic data, industrial design position characteristic data and supporting correlation characteristic data according to the supporting correlation relationship; Using the distributed computing capability of the cloud computing platform, the industrial design industry characteristic data, the industrial design position characteristic data and the supporting associated characteristic data are stored and analyzed to output a quantitative analysis result of the future demand trend for industrial design talents; Based on the output of quantitative analysis results of future demand trends for industrial design talents, a talent demand forecast report is generated.

2. The method for quantitative analysis of industrial design talent demand based on cloud computing according to claim 1 is characterized in that: The determining of the supporting association relationship between the industrial design industry demand data and the industrial design position demand data is configured as follows: Constructing a binary tree, including: constructing child nodes of the binary tree based on the industrial design job demand data; constructing a root node of the binary tree based on the industrial design industry demand data; and constructing edges of the binary tree based on the relationship between the industrial design industry demand data and the industrial design job demand data.

3. The method for quantitative analysis of industrial design talent demand based on cloud computing according to claim 2 is characterized in that: The determining of the supporting association relationship between the industrial design industry demand data and the industrial design position demand data is configured as follows: A population is randomly initialized; wherein each individual in the population is a path from the root node to a leaf node, and is used to characterize a matching pattern between job requirements and industry requirements, wherein the matching pattern includes a hierarchical relationship and a dependency relationship.

4. The method for quantitative analysis of industrial design talent demand based on cloud computing according to claim 3 is characterized in that: The determining of the supporting association relationship between the industrial design industry demand data and the industrial design position demand data is configured as follows: Define a fitness function; wherein the fitness function is used to characterize the matching degree and support degree between job requirements and industry requirements; Each individual in the population is regarded as a path in the binary tree, and the fitness of the path is determined by the support of the nodes on the path; a new path is generated by a genetic operator, and the validity of the new path is evaluated by the fitness function, and the path with the highest fitness is selected as the basis of the next generation population.

5. The method for quantitative analysis of industrial design talent demand based on cloud computing according to claim 1 is characterized in that: The determining of the supporting association relationship between the industrial design industry demand data and the industrial design position demand data is configured as follows: Repeatedly apply the genetic operator and the selection mechanism, and update the structure of the binary tree until the fitness function meets the fitness threshold; wherein the genetic operator includes a crossover operator and a mutation operator; the crossover operator is used to combine the characteristics of two individuals in the population to form a new path; the mutation operator is used to randomly select a node in the path and replace it with any other node; According to the structure of the updated binary tree, the supporting association relationship between the industrial design industry demand data and the industrial design position demand data is determined.

6. The method for quantitative analysis of industrial design talent demand based on cloud computing according to claim 1 is characterized in that: The industrial design industry demand data includes the scale of industry business demand, industry social attention index, industry development trends and regional recruitment demand differences; The industrial design job demand data includes skill requirement distribution, job demand growth rate, educational background requirements, work experience requirements and salary level requirements.

7. A cloud computing-based industrial design talent demand quantitative analysis system, the system implements the cloud computing-based industrial design talent demand quantitative analysis method as claimed in claim 1, characterized in that: include: The talent demand data collection module is used to collect talent demand data in the field of industrial design from multiple data sources in real time using the API and data stream services of the cloud computing platform; A talent demand data classification module is used to classify the talent demand data to obtain industrial design industry demand data and industrial design job demand data; A feature data extraction unit, used to determine the supporting association relationship between the industrial design industry demand data and the industrial design position demand data; And extracting industrial design industry characteristic data, industrial design position characteristic data and supporting correlation characteristic data according to the supporting correlation relationship; A demand quantification analysis module, used to utilize the distributed computing capability of the cloud computing platform to store and analyze the industrial design industry characteristic data, the industrial design position characteristic data, and the supporting association characteristic data, so as to output a quantitative analysis result of the future demand trend for industrial design talents; The talent demand forecast report generating unit is used to generate a talent demand forecast report based on the output quantitative analysis results of the future demand trend of industrial design talents.

8. The cloud computing-based industrial design talent demand quantitative analysis system according to claim 7 is characterized in that: The feature data extraction unit determines the supporting association relationship between the industrial design industry demand data and the industrial design position demand data, and is configured as follows: Constructing a binary tree, including: constructing child nodes of the binary tree based on the industrial design job demand data; constructing a root node of the binary tree based on the industrial design industry demand data; and constructing edges of the binary tree based on the relationship between the industrial design industry demand data and the industrial design job demand data.

9. The cloud computing-based industrial design talent demand quantitative analysis system according to claim 8, characterized in that: The process of updating the structure of the binary tree is as follows: Traverse the binary tree, and for each child node, calculate the support between it and the root node; if the support between the child node and the root node is higher than a preset threshold, determine that the child node is the leaf node in the topology; otherwise, determine that the child node is an internal node in the topology, and continue to traverse its subtree; wherein a subtree is a tree with a certain internal node as its root, which contains all descendant nodes of the internal node.

10. The cloud computing-based industrial design talent demand quantitative analysis system according to claim 8, characterized in that: The demand quantification analysis module utilizes the distributed computing capability of the cloud computing platform to store and analyze the industrial design industry characteristic data, the industrial design position characteristic data, and the supporting association characteristic data, so as to output a quantitative analysis result of the future demand trend of industrial design talents, and is configured as follows: Preprocessing the industrial design industry characteristic data, the industrial design position characteristic data, and the supporting associated characteristic data; Design a deep neural network model; wherein the deep neural network model is used to learn the relationship between feature data and future talent demand trends; the deep neural network model includes an input layer, a hidden layer and an output layer; the input layer is used to receive preprocessed industrial design industry feature data, industrial design job feature data and supporting related feature data; the hidden layer contains at least two layers, each layer uses a Re LU activation function; the output layer contains multiple output nodes, and uses a linear activation function to predict future talent demand trends.

Images