An evaluation platform for regional vocational education system

Abstract

This invention discloses a regional vocational education system evaluation platform, relating to the field of education evaluation technology. The platform introduces a three-dimensional dynamic adaptation mechanism of regional policy, industrial clusters, and resource endowment. The platform includes: a data acquisition module, a regional knowledge graph construction module, an evaluation indicator decomposition module, an indicator weight dynamic adjustment module, a specialized evaluation module, and a result output module. By introducing this three-dimensional dynamic adaptation mechanism and combining data acquisition, knowledge graph construction, indicator decomposition, dynamic weight adjustment, and the collaborative operation of specialized evaluation modules, this invention constructs a region-specific evaluation logic, achieving real-time binding of the evaluation system with the dynamic development of the region. This solves the problems of existing technologies that only address industry needs, have rigid indicator systems, and lack region-specific evaluation logic, ensuring that evaluation results accurately align with the characteristics and development needs of regional vocational education.

Description

Technical Field

[0001] This invention relates to the field of educational evaluation technology, specifically to an evaluation platform for a regional vocational education system. Background Technology

[0002] Vocational education is a type of education designed to meet the needs of economic development and cultivate application-oriented and skilled personnel with professional knowledge and vocational skills. It is an important component of the education system and human resource development. Its core value lies in building bridges for talent growth, promoting industrial upgrading, alleviating structural employment contradictions, and providing solid skilled talent support for the sustained and healthy development of the regional economy. The evaluation of the vocational education system is a systematic activity that comprehensively assesses various aspects of vocational education, including its school-running positioning, resource allocation, training quality, and industry adaptability. Through scientific evaluation, the strengths and weaknesses of the vocational education system can be accurately identified, providing an important basis for optimizing the allocation of vocational education resources, adjusting school-running models, and improving policy formulation. It is of key significance for improving the overall quality of vocational education and enhancing the service capacity of vocational education.

[0003] However, existing technologies for evaluating vocational education systems still have certain shortcomings. Most existing evaluation platforms focus solely on aligning with industry needs, failing to fully consider core characteristics such as regional policy guidance and resource differences. They lack consideration for the personalized needs of regional development, have rigid evaluation indicator systems, lack dynamic adjustment mechanisms for weight settings, and cannot adapt to the dynamic changes in regional industrial structure and policy environment. They also fail to construct regionally specific evaluation logic, resulting in evaluation results that are highly generalized but lack specificity. This makes it difficult to truly reflect the current development status and core needs of regional vocational education, and consequently, it cannot provide effective support for the precise optimization of regional vocational education. This restricts the deep integration of vocational education and regional development. Therefore, developing a regional vocational education system evaluation platform is of great significance. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a regional vocational education system evaluation platform. It can construct a region-specific evaluation logic by introducing a three-dimensional dynamic adaptation mechanism of regional policies, industrial clusters, and resource endowments, combined with data collection, knowledge graph construction, indicator decomposition, dynamic weight adjustment, and the collaborative operation of special evaluation modules. This enables the evaluation system to be linked to the dynamic development of the region in real time, so that the evaluation results accurately match the characteristics and development needs of regional vocational education, and provide a scientific basis for the optimal allocation of regional vocational education resources, policy adjustment, and improvement of school operation models.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a regional vocational education system evaluation platform, which introduces a three-dimensional dynamic adaptation mechanism of regional policy-industrial cluster-resource endowment. The platform includes: a data acquisition module, a regional knowledge graph construction module, an evaluation indicator decomposition module, an indicator weight dynamic adjustment module, a special evaluation module, and a result output module.

[0006] The data acquisition module automatically captures relevant data on regional industrial cluster planning, local vocational education support policies, and the distribution of urban and rural vocational education resources, and transmits the data to the regional knowledge graph construction module.

[0007] The regional knowledge graph construction module constructs a regional vocational education knowledge graph based on the received data, and transmits the knowledge graph to the evaluation indicator decomposition module, the indicator weight dynamic adjustment module, and the special evaluation module respectively.

[0008] The evaluation index decomposition module decomposes the evaluation index into three major modules based on the received knowledge graph: industry adaptability, policy responsiveness, and resource balance. The decomposed index system is then transmitted to the index weight dynamic adjustment module and the special evaluation module.

[0009] The indicator weight dynamic adjustment module, based on the received knowledge graph and indicator system, automatically adjusts the corresponding evaluation indicator weights according to the regional industrial positioning and development changes through a preset industry association algorithm, and transmits the adjusted indicator system to the special evaluation module.

[0010] The special evaluation module, based on the received knowledge graph, indicator system and adjusted weights, conducts evaluations on areas with resource allocation gaps within the region using the special evaluation dimension of resource supplementation efficiency, and transmits the evaluation data to the result output module.

[0011] The result output module integrates the processing results received from each module and outputs an evaluation report.

[0012] Furthermore, the data acquisition module performs the following operations when collecting core regional data:

[0013] The core categories of data collection should be clearly defined, including the latest industrial cluster planning documents released in the region, vocational education support policy documents issued by governments at all levels, and resource-related data on the allocation of teachers, training equipment, enrollment scale, and operating funds of vocational schools in urban and rural areas.

[0014] For different types of data, corresponding real-time capture channels are built. Policy and planning documents released by government public platforms are obtained through interface docking or web crawling technology, and resource data of vocational colleges are collected through the college's dedicated data reporting port.

[0015] The captured raw data is formatted and standardized to remove duplicate and invalid data.

[0016] Furthermore, the regional knowledge graph construction module performs the following operations when constructing a regionally specific vocational education knowledge graph:

[0017] The standardized data transmitted by the data acquisition module is classified and processed into four major data subsets: policy, industry, resources, and vocational education.

[0018] Define the association rules between various data subsets, and clarify the matching association between policy data and vocational education data, the demand association between industry data and vocational education data, and the support association between resource data and vocational education data;

[0019] Based on classification data and association rules, graph database technology is used to construct an initial knowledge graph containing nodes, edges and attribute information. Nodes correspond to the core entities of various types of data, edges correspond to the association relationships between entities, and attribute information is the specific feature parameters of the entities.

[0020] Based on the real-time data updated and transmitted by the data acquisition module, the node information and edge association strength in the knowledge graph are dynamically updated.

[0021] Furthermore, the dynamic adjustment module for indicator weights performs the following operations when adjusting the weights of evaluation indicators:

[0022] The knowledge graph transmitted by the regional knowledge graph construction module is used to extract the current industrial positioning characteristics and industrial development dynamic data of the region, and to clarify the types and scale changes of the region's leading industries and key development industries.

[0023] Based on the preset industry association algorithm, the corresponding mapping relationship between industry type and each indicator in the indicator system transmitted by the evaluation indicator decomposition module is established, and the core evaluation indicators corresponding to different industries are clarified.

[0024] Set trigger conditions for weight adjustments and initiate the weight adjustment process based on key changes in regional industrial development.

[0025] Based on the pre-set weighting calculation model and combined with data on industry scale proportion and industry development growth rate, adjustment coefficients for each core evaluation indicator are calculated. The original indicator weights are then dynamically updated according to these adjustment coefficients. The formula for calculating the adjustment coefficients is as follows: The adjusted weights will be synchronized to the indicator system and transmitted to the special evaluation module. For the first The first category of industries The weights of the evaluation indicators after adjustment As the initial weight for this indicator, This is the industry scale weighting coefficient. The industrial growth rate weighting coefficient is determined based on data on the region's industrial contribution to the economy over the past three years, combined with consensus among industry experts. For the first The regional scale of similar industries For the first Annual growth rate of similar industries For the first Category of industries and the first The correlation strength coefficient of the evaluation indicators is extracted from the correlation edge attribute information of policy-industry-vocational education in the regional knowledge graph.

[0026] Furthermore, the industry fit module, which is part of the evaluation index decomposition module, includes multiple sub-evaluation indicators, specifically including the matching degree between vocational education majors and regional industry types, the fit between graduates' employment directions and regional industry needs, the conformity between vocational education curriculum content and industry technical standards, and the fit between school-enterprise cooperation projects and regional industrial development. The comprehensive score for industry fit is calculated using the following formula: ,in, The overall score is based on industry adaptability. The correlation strength coefficients for each sub-indicator are extracted from the weighted correlation relationships between industry-related data and vocational education-related data in the regional knowledge graph. Quantitative scoring for each sub-indicator, The compliance correction coefficient for indicators is determined based on the update frequency of regional industrial technology standards. The policy responsiveness module includes sub-evaluation indicators such as the degree of implementation of policy requirements by vocational schools, the compliance of the use of policy subsidies, the progress of vocational education reform measures under policy guidance, and the degree of alignment between policy objectives and the effectiveness of vocational education development. The resource balance module includes sub-evaluation indicators such as the balance coefficient of teacher allocation in urban and rural vocational schools, the balance coefficient of practical training equipment allocation, the balance coefficient of investment in school operating funds, and the coverage rate of sharing high-quality course resources.

[0027] Furthermore, the resource supplementation efficiency evaluation dimension set by the special evaluation module includes specific evaluation parameters, including the accuracy of resource gap identification, the timeliness of resource supplementation plan formulation, the efficiency of resource supplementation funding arrival, the utilization and conversion rate of newly added resources, and the improvement in vocational education service capabilities after resource supplementation. The special evaluation module receives the knowledge graph transmitted by the regional knowledge graph construction module, the indicator system transmitted by the evaluation indicator decomposition module, and the adjusted weights transmitted by the indicator weight dynamic adjustment module. Through the knowledge graph, it monitors the resource allocation status of each vocational education institution in the region in real time, automatically identifies gap areas where resource allocation is below the regional average, and initiates a targeted special evaluation process for the gap areas. It continuously tracks the entire process data of resource supplementation and conducts quantitative evaluation. The formula for calculating the comprehensive evaluation parameters of resource supplementation efficiency is as follows: The quantitative evaluation data is transmitted to the result output module, whereby... As a comprehensive evaluation parameter for resource replenishment efficiency, The importance coefficients for each evaluation parameter are determined based on the priority of regional resource gap types and through historical data on the correlation between resource supplementation and the improvement of vocational education service capabilities, obtained from regional knowledge graph statistics. These are the quantified values ​​for each evaluation parameter. The parameter timeliness correction factor is determined based on the matching degree between the resource replenishment cycle and the regional industrial development cycle.

[0028] Furthermore, the data acquisition module also has data encryption transmission and storage functions. It uses a symmetric encryption algorithm to encrypt the data transmission channel to the regional knowledge graph construction module after acquisition, uses distributed storage technology to store the processed standardized data, sets up a data access permission management mechanism, and only authorizes users to access the corresponding category of data according to preset permissions. At the same time, it establishes a data backup mechanism to regularly back up the stored data off-site.

[0029] Furthermore, the result output module receives the indicator system transmitted by the evaluation indicator decomposition module, the adjusted weights transmitted by the indicator weight dynamic adjustment module, and the quantitative evaluation data transmitted by the special evaluation module. The output evaluation report contains multi-dimensional content, specifically including the comprehensive evaluation score of the regional vocational education system, the sub-scores of the three major modules of industry adaptability, policy responsiveness, and resource balance, the specific scores of each sub-evaluation indicator, the development advantages and existing shortcomings of the regional vocational education system derived from the evaluation score analysis, and the suggestions for optimization directions for the shortcomings, clarifying the implementation focus and key steps of each optimization direction. The evaluation report supports export in multiple formats, including PDF, Excel, and Word formats.

[0030] Furthermore, the preset industry association algorithm includes an industry feature extraction sub-algorithm, an indicator mapping sub-algorithm, and a weight calculation sub-algorithm. The industry feature extraction sub-algorithm uses a machine learning model to extract features from regional industry data and accurately identify core industry needs. The indicator mapping sub-algorithm uses a mapping rule library built based on the experience of industry experts to achieve accurate matching between industry features and evaluation indicators. The weight calculation sub-algorithm uses a combined weighting method that combines the analytic hierarchy process (AHP) and the entropy weighting method, incorporating expert subjective judgment while fully considering the objective characteristics of the data.

[0031] Compared with existing technologies, this regional vocational education system evaluation platform has the following beneficial effects:

[0032] This invention introduces a three-dimensional dynamic adaptation mechanism of regional policy, industrial clusters, and resource endowment. By combining data collection, knowledge graph construction, indicator decomposition, dynamic weight adjustment, and the collaborative operation of specialized evaluation modules, it constructs a region-specific evaluation logic. This enables the evaluation system to be linked to the dynamic development of the region in real time, solving the problems of existing technologies that only address industry needs, have rigid indicator systems, and lack region-specific evaluation logic. This ensures that the evaluation results accurately match the characteristics and development needs of regional vocational education, providing a scientific basis for the optimal allocation of regional vocational education resources, policy adjustments, and the improvement of school operation models. It enhances the support capacity of regional vocational education for industrial development and the efficiency of resource allocation, and promotes the deep integration of vocational education and regional economic development.

[0033] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0035] Figure 1 This is a schematic diagram of the structure of a regional vocational education system evaluation platform;

[0036] Figure 2 A flowchart illustrating the workflow of a regional vocational education system evaluation platform;

[0037] Figure 3 This is a flowchart of the process of constructing a regional knowledge graph for vocational education, which is part of the regional knowledge graph construction module. Detailed Implementation

[0038] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0039] This invention provides a regional vocational education system evaluation platform, aiming to solve the problems of existing evaluation platforms that only address industry needs, have rigid indicator systems, and lack region-specific evaluation logic. (See also...) Figure 1 and Figure 2 The specific technical solution is as follows:

[0040] The platform's core is the introduction of a three-dimensional dynamic adaptation mechanism encompassing regional policies, industrial clusters, and resource endowments, comprising a complete technical solution through the collaborative efforts of six modules. The data acquisition module clearly defines core data categories such as industrial planning, vocational education policies, and institutional resources. It captures data in real-time through interface integration, web crawling, and institutional reporting, and then removes invalid information after standardization processing. The regional knowledge graph construction module categorizes standardized data into four main types, defines the association rules between each type of data and vocational education data, and uses graph database technology to construct an initial knowledge graph containing nodes, edges, and attributes, dynamically updating it based on real-time data.

[0041] The evaluation indicator decomposition module, based on a knowledge graph, breaks down the evaluation indicators into three main modules: industry adaptability, policy responsiveness, and resource balance. Each module contains multiple sub-indicators. The indicator weight dynamic adjustment module extracts regional industry positioning and development data, establishes a mapping relationship between industries and indicators through a preset industry association algorithm, and initiates weight adjustments based on key industry change nodes to dynamically update indicator weights.

[0042] The special evaluation module targets areas with resource allocation gaps, initiating a special evaluation of resource replenishment efficiency, tracking data throughout the entire process, and quantifying the assessment. The results output module integrates data from all modules, outputting an evaluation report that includes a comprehensive score, sub-scores, development advantages, shortcomings, and optimization suggestions, and supports export in multiple formats.

[0043] Furthermore, the data acquisition module features encrypted transmission, distributed storage, access control, and off-site backup to ensure data security. The pre-defined industry-related algorithm integrates multiple sub-algorithms, balancing expert subjective judgment with objective data characteristics. This ensures that the evaluation logic aligns with regional dynamic development, accurately matching evaluation results to regional vocational education characteristics and needs, and providing a scientific basis for resource optimization and policy adjustments.

[0044] Example 1

[0045] This embodiment is applied to the evaluation scenario of a regional vocational education system in a prefecture-level city. In recent years, this city has focused on two core industrial clusters: advanced manufacturing and modern services, and has introduced a number of vocational education support policies. However, problems such as the uneven distribution of urban and rural vocational education resources and the disconnect between some vocational education majors and industry needs have gradually become prominent. To accurately assess the operational effectiveness of the regional vocational education system and adapt to the needs of regional industrial structure upgrading, policy guidance adjustment, and resource optimization, the regional vocational education system evaluation platform described in this invention is introduced. Through a three-dimensional dynamic adaptation mechanism and the collaborative operation of six modules, a unique evaluation logic tailored to the region's development characteristics is constructed, providing data support and decision-making reference for the high-quality development of regional vocational education. (See also...) Figure 1 and Figure 2 The specific implementation process of this embodiment is as follows:

[0046] In the specific implementation process, the data collection module was first activated to comprehensively collect core regional data. The core categories of data to be collected included the latest advanced manufacturing and modern service industry cluster planning documents released by the prefecture-level city, vocational education support policy documents issued by provincial and municipal governments, and resource-related data such as faculty allocation, training equipment configuration, enrollment scale, and operating funds of more than 20 vocational colleges in urban and rural areas. Dedicated real-time capture channels were established for different categories of data. For industry plans and policy documents published on the municipal government's public information platform and the official website of the National Development and Reform Commission, a combination of interface docking and web crawling technology was used to obtain the data, ensuring the timeliness of policy and planning data. For resource data of each vocational college, a dedicated data reporting port was established, with designated personnel from each college uploading the data regularly to ensure its accuracy.

[0047] After data collection, the raw data undergoes format standardization, unifying data storage format and field definitions. Simultaneously, data validation algorithms are used to eliminate duplicate submissions and invalid data that does not meet specifications, providing a high-quality data foundation for subsequent module operations. Furthermore, the data acquisition module employs a symmetric encryption algorithm to encrypt the transmission channel, stores the processed standardized data using distributed storage technology, and implements a tiered data access permission management mechanism. Only authorized educational management departments and school administrators can access the corresponding data according to their permissions. A weekly off-site backup mechanism is also established to ensure the security of data transmission and storage.

[0048] After the data acquisition module completes data processing, it transmits standardized data to the regional knowledge graph construction module. The process for initiating the construction of a regionally specific vocational education knowledge graph in this module is detailed below. Figure 3 First, the received standardized data was categorized into four subsets: policy-related, industry-related, resource-related, and vocational education-related. Policy-related data includes policy documents and implementation details for vocational education support at all levels. Industry-related data covers the planning goals, industry scale, and technical standards of the two core industrial clusters. Resource-related data details the resource allocation of various institutions, including faculty, equipment, and funding. Vocational education-related data includes information on institution majors, curriculum systems, and industry-university cooperation projects. Next, the association rules between these subsets were defined. Specifically, the compatibility relationship between policy-related and vocational education-related data (i.e., the direction and implementation path of vocational schools in implementing policy requirements); the demand relationship between industry-related and vocational education-related data (i.e., the specific needs of industrial development for vocational education majors and skills training); and the support relationship between resource-related and vocational education-related data (i.e., the supporting role of various resources in vocational education teaching and practical training) were clarified.

[0049] Based on categorized data and association rules, an initial knowledge graph is constructed using graph database technology. Nodes in the graph correspond to core entities such as policy names, industry types, university names, and major names. Edges correspond to the relationships between entities, and attribute information represents the specific characteristic parameters of each entity. For example, attributes of industry nodes include industry scale and growth rate, while attributes of university nodes include the number of faculty members and the number of sets of training equipment. During subsequent operation, the node information and edge association strength in the knowledge graph are dynamically updated based on data transmitted in real time from the data acquisition module, ensuring that the knowledge graph accurately reflects regional development dynamics.

[0050] After the regional knowledge graph is constructed, it is transmitted to the evaluation indicator decomposition module, the indicator weight dynamic adjustment module, and the special evaluation module. Upon receiving the knowledge graph, the evaluation indicator decomposition module decomposes the evaluation indicators into three modules based on the relationships between various data types in the graph: industry adaptability, policy responsiveness, and resource balance. The industry adaptability module includes four sub-indicators: the matching degree between vocational education majors and regional industry types, the alignment between graduate employment directions and regional industry needs, the conformity between vocational education curriculum content and industry technical standards, and the adaptability between school-enterprise cooperation projects and regional industrial development. The policy responsiveness module includes four sub-indicators: the degree to which vocational schools implement policy requirements, the compliance of policy subsidy funds, the progress of vocational education reform measures under policy guidance, and the alignment between policy objectives and vocational education development achievements. The resource balance module includes four sub-indicators: the balance coefficient of teacher allocation in urban and rural vocational schools, the balance coefficient of practical training equipment allocation, the balance coefficient of operating funds investment, and the coverage rate of high-quality course resource sharing.

[0051] In the specific implementation of this embodiment, the comprehensive score of industry adaptability is calculated using the formula, which is as follows: ,in The overall score is based on industry adaptability. The correlation strength coefficient for each sub-indicator is extracted from the correlation weights between industry data and vocational education data in the regional knowledge graph, reflecting the degree of influence of each sub-indicator on industry suitability. The quantitative scores for each sub-indicator are determined by evaluators who combine the actual situation with the evaluation criteria. The compliance correction coefficient for the indicators is determined based on the update frequency of regional industrial technical standards. For sectors with frequently updated industrial technical standards, the correction coefficient is higher to ensure the evaluation adapts to technological developments. The evaluation indicator decomposition module transmits the decomposed complete indicator system to the indicator weight dynamic adjustment module and the special evaluation module.

[0052] After receiving the knowledge graph and indicator system, the dynamic adjustment module for indicator weights initiates the weight adjustment process. First, it extracts the current industrial positioning characteristics and dynamic data of industrial development for the prefecture-level city through the knowledge graph, clarifying the types and scale changes of the two leading industries (advanced manufacturing and modern services) and key development industries. Based on a pre-defined industry association algorithm, this algorithm includes an industry feature extraction sub-algorithm, an indicator mapping sub-algorithm, and a weight calculation sub-algorithm. The industry feature extraction sub-algorithm uses a machine learning model to extract features from regional industrial data, accurately identifying core industry needs. The indicator mapping sub-algorithm uses a mapping rule library built based on industry expert experience to achieve accurate matching between industry characteristics and evaluation indicators. The weight calculation sub-algorithm uses a combined weighting method combining the analytic hierarchy process (AHP) and entropy weighting, incorporating expert subjective judgment and objective data characteristics to establish a corresponding mapping relationship between industry types and indicators in the indicator system, clarifying the core evaluation indicators for different industries. For example, the core evaluation indicators for advanced manufacturing include the conformity of course content with industry technical standards and the suitability of school-enterprise cooperation projects.

[0053] Subsequently, weight adjustment trigger conditions are set. The weight adjustment process is automatically initiated when changes in the regional industry scale share reach a set threshold, when there are significant fluctuations in industry development growth, or when major industrial policies are introduced. In the specific implementation of this embodiment, according to the preset weight calculation model, combined with data on industry scale share and industry development growth, the adjustment coefficients of each core evaluation indicator are calculated using the following formula: ,in For the first The first category of industries The weights of the evaluation indicators after adjustment The initial weight of this indicator was determined by industry experts in conjunction with the initial stage of regional development. This is the industry scale weighting coefficient. The industry growth rate weighting coefficient is determined based on the city's industry contribution to the economy over the past three years, combined with industry expert consensus, and reflects the impact of industry size and growth rate on weight adjustments. For the first The regional scale of a particular industry reflects the importance of that industry to the regional economy; For the first The annual growth rate of a particular industry reflects its development potential; For the first Category of industries and the first The correlation strength coefficient of each evaluation indicator is extracted from the policy-industry-vocational education correlation edge attribute information in the regional knowledge graph. The original indicator weights are dynamically updated based on the calculated adjustment coefficients, and the adjusted indicator system is then transmitted to the specialized evaluation module.

[0054] After receiving the knowledge graph, indicator system, and adjusted weights, the specialized evaluation module first monitors the resource allocation status of vocational colleges in the prefecture-level city in real time through the knowledge graph. By comparing this to the regional average resource allocation level, it automatically identifies areas with resource gaps below the average, such as insufficient practical training equipment and a lack of high-quality course resources in some rural vocational colleges. For these areas with gaps, a targeted evaluation process for resource supplementation efficiency is initiated. This evaluation dimension includes five specific evaluation parameters: the accuracy of resource gap identification, the timeliness of resource supplementation plan formulation, the efficiency of resource supplementation funding arrival, the utilization and conversion rate of newly added resources, and the extent to which vocational education service capabilities are improved after resource supplementation.

[0055] In the specific implementation of this embodiment, the comprehensive evaluation parameter of resource replenishment efficiency is calculated using the formula, which is: ,in As a comprehensive evaluation parameter for resource replenishment efficiency, The importance coefficients of each evaluation parameter are determined based on the priority of regional resource gap types and through historical data on the correlation between resource supplementation and the improvement of vocational education service capabilities, as statistically analyzed using regional knowledge graphs. For example, the importance coefficient of training equipment gap is higher than that of curriculum resource gap. The quantitative values ​​for each evaluation parameter are obtained by tracking resources and supplementing the entire process of data acquisition; The parameter timeliness correction factor is determined based on the matching degree between the resource replenishment cycle and the regional industrial development cycle. The higher the matching degree between the resource replenishment cycle and the industrial development cycle, the higher the correction factor value. The special evaluation module continuously tracks the entire process data of resource replenishment and performs quantitative evaluation, transmitting the evaluation data to the results output module.

[0056] The results output module receives the indicator system transmitted by the evaluation indicator decomposition module, the adjusted weights transmitted by the indicator weight dynamic adjustment module, and the quantitative evaluation data transmitted by the special evaluation module. After integrating and processing these data, it outputs an evaluation report. The evaluation report contains multi-dimensional content, specifically including the comprehensive evaluation score of the vocational education system in the prefecture-level city, the sub-scores for three modules: industry adaptability, policy responsiveness, and resource balance, and the specific scores for each sub-evaluation indicator. Based on the evaluation scores, it analyzes the development advantages of the regional vocational education system, such as the high degree of industry adaptability of some institutions' advanced manufacturing-related majors and the good compliance of policy subsidy funds. It also identifies existing shortcomings, such as the uneven distribution of resources in rural vocational schools and the disconnect between some professional courses and industry technical standards. Furthermore, it includes optimization suggestions for addressing these shortcomings, clarifying the implementation focus and key steps for each optimization direction. For example, regarding the issue of resource imbalance, it recommends increasing financial investment in rural vocational schools and establishing a resource-sharing mechanism between urban and rural schools. The evaluation report supports export in PDF, Excel, and Word formats, facilitating use by different users such as education management departments and school administrators according to their needs.

[0057] In summary, this embodiment, by fully utilizing the six modules of the regional vocational education system evaluation platform, leverages the dynamic three-dimensional adaptation mechanism of regional policies, industrial clusters, and resource endowments to construct a unique evaluation logic tailored to the development characteristics of the prefecture-level city. The platform achieves real-time binding of the evaluation system with the dynamic changes in regional industrial structure, policy environment, and resource distribution, solving the problems of traditional evaluation methods that only address industry needs, have rigid indicator systems, and lack regional specificity.

[0058] Example 2

[0059] This embodiment applies to the evaluation scenario of a regional vocational education system in a county. This county, relying on its local natural resource advantages, focuses on developing two pillar industries: specialty agriculture and rural tourism. In recent years, it has introduced numerous vocational education support policies in line with the rural revitalization strategy, vigorously promoting the construction of vocational education centers in townships. However, problems exist, such as insufficient alignment between vocational education majors and the county's specialty industries, untimely replenishment of township vocational education resources, and significant regional differences in the effectiveness of policy implementation. To accurately assess the county's vocational education system's support capacity for the development of specialty industries and optimize the allocation of urban and rural vocational education resources, this embodiment, based on the aforementioned Embodiment 1, specifically adjusts the platform's data collection scope and evaluation focus. Through a three-dimensional dynamic adaptation mechanism and the collaborative operation of six modules, it constructs an evaluation system adapted to the county's development characteristics, providing decision-making support for county-level vocational education to empower rural revitalization. See [link to previous document]. Figure 1 and Figure 2 The specific implementation process of this embodiment is as follows:

[0060] In the specific implementation process, the data collection module was first activated to carry out the collection of core county-level data. Based on the data collection categories in the aforementioned Example 1, new characteristic data categories were added, including county-level characteristic agricultural industry development plans, rural tourism industry layout documents, the allocation of mobile teachers at township vocational education centers, the provision of portable training equipment, and the number of people receiving short-term skills training. Differentiated collection channels were established for different data categories. For industry plans and policy documents published on the county government website, the Agriculture and Rural Affairs Bureau, and the Culture and Tourism Bureau, interface technology was used to capture them in real time. Resource data from the three secondary vocational schools and eight township vocational education centers within the county were collected through dedicated data reporting ports for the schools and centers, and some verification data was simultaneously obtained by connecting to the county-level government data sharing platform. Data related to market demand and technical standards for characteristic industries were collected through targeted collection from industry associations.

[0061] After data collection, the raw data is standardized according to unified standards. Duplicate data is removed using a data deduplication algorithm, and invalid data is filtered out using validity verification rules to ensure that the data quality meets the requirements of subsequent module operation. Simultaneously, the data encryption transmission and storage scheme described in Implementation Example 1 is adopted, using a symmetric encryption algorithm to ensure transmission security, distributed storage technology to store standardized data, setting three levels of data access permissions, and establishing a regular off-site backup mechanism to ensure the security and controllability of county-level vocational education data.

[0062] After the data acquisition module completes data processing, it transmits standardized data to the regional knowledge graph construction module. The process for initiating the county-specific vocational education knowledge graph construction is described below. Figure 3 Building upon the data classification in Example 1, the industry-related data is further subdivided into specialty agriculture and rural tourism, while resource-related data includes a new subset of data specific to township vocational education centers. Association rules for each data subset are defined, clarifying the alignment between policy-related data and vocational education data regarding rural revitalization, the skill demand relationship between specialty agriculture and rural tourism data and vocational education data, and the grassroots support relationship between township vocational education center resource data and vocational education data.

[0063] Based on categorized data and association rules, an initial knowledge graph containing nodes, edges, and attribute information is constructed using graph database technology. Nodes encompass county-level characteristic entities such as specialty agricultural product planting bases, rural tourism scenic spots, and township vocational education centers. Edges correspond to the relationships between various entities, and attribute information includes specific parameters such as technical standards for characteristic industries and models of training equipment at township vocational education centers. During platform operation, the node information and edge association strength in the knowledge graph are dynamically updated based on real-time data from the data acquisition module, ensuring that the knowledge graph accurately reflects the dynamics of county-level industry and vocational education development.

[0064] After the regional knowledge graph is constructed, it is synchronously transmitted to the evaluation indicator decomposition module, the indicator weight dynamic adjustment module, and the special evaluation module. The evaluation indicator decomposition module, based on the knowledge graph, retains the framework of three main modules: industry adaptability, policy responsiveness, and resource balance, with targeted adjustments to the sub-indicators. The adjusted industry adaptability module includes four sub-indicators: the matching degree between vocational education majors and county-level characteristic industries; the employment rate of graduates serving county-level characteristic industries; the conformity of vocational skills training content with characteristic industry technical standards; and the adaptability of school-enterprise cooperation projects with county-level industrial development. The policy responsiveness module adds two new sub-indicators: the implementation degree of policy funding tilted towards township vocational education points and the coverage of characteristic industry skills training policies. The resource balance module is adjusted to include four sub-indicators: the balance coefficient of teacher allocation in urban and rural vocational education institutions; the balance coefficient of practical training equipment allocation; the balance coefficient of educational funding investment; and the coverage rate of characteristic industry curriculum resource sharing.

[0065] In the specific implementation of this embodiment, the comprehensive score of industry adaptability is calculated using the formula, which is as follows: The evaluation index decomposition module transmits the adjusted complete index system to the index weight dynamic adjustment module and the special evaluation module.

[0066] After receiving the knowledge graph and indicator system, the dynamic adjustment module for indicator weights initiates the weight adjustment process. It extracts current industrial positioning characteristics and development dynamics data from the knowledge graph, clarifying the types and scale changes of the two leading industries: specialty agriculture and rural tourism. Based on a pre-set industry association algorithm, it establishes a mapping relationship between the leading industries and each indicator in the indicator system. The core evaluation indicators for specialty agriculture are defined as the conformity of skills training content with industry technical standards and the balance coefficient of practical training equipment configuration; the core evaluation indicators for rural tourism are the matching degree between majors and industries and the suitability of school-local cooperation projects. Weight adjustment trigger conditions are set: when the scale of specialty industry planting or the number of tourist visits in the county reaches a preset threshold, or when a major support policy for township vocational education centers is introduced, the weight adjustment process is automatically initiated.

[0067] In the specific implementation of this embodiment, according to the preset weight calculation model, combined with the industry scale ratio and industry development growth rate data, the adjustment coefficient of each core evaluation indicator is calculated using the formula: The original indicator weights are dynamically updated based on the adjustment coefficients, and the adjusted indicator system is transmitted to the special evaluation module.

[0068] After receiving the knowledge graph, indicator system, and adjusted weights, the specialized evaluation module monitors the resource allocation status of vocational schools and township vocational education centers within the county in real time through the knowledge graph. It compares this to the county's average vocational education resource allocation level, automatically identifies areas with resource gaps, and focuses on issues such as shortages of specialized agricultural training equipment, shortages of rural tourism service skills training instructors, and insufficient portable training resources in township vocational education centers. For these gap areas, a targeted evaluation process for resource replenishment efficiency is initiated, using five evaluation parameters: accuracy of resource gap identification, timeliness of resource replenishment plan formulation, efficiency of resource replenishment funding arrival, utilization and conversion rate of newly added resources, and the extent to which vocational education service capabilities are improved after resource replenishment.

[0069] In the specific implementation of this embodiment, the comprehensive evaluation parameter of resource replenishment efficiency is calculated using the formula, which is: The special evaluation module continuously tracks data from the entire process, including the procurement and distribution of specialized agricultural training equipment, the allocation of mobile instructors, and the distribution of short-term skills training resources. After quantitative evaluation, the data is transmitted to the results output module.

[0070] The results output module integrates the indicator system from the evaluation indicator decomposition module, the adjusted weights from the indicator weight dynamic adjustment module, and the quantitative evaluation data from the special evaluation module to output a county-specific evaluation report. The evaluation report includes the comprehensive evaluation score of the county's vocational education system, the sub-scores for three modules—industry adaptability, policy responsiveness, and resource balance—and the specific scores for each sub-indicator. Based on the score analysis, it identifies the development advantages of the county's vocational education system, such as the broad coverage of characteristic industry skills training policies and the high degree of industry adaptability between county-level vocational schools and industries. It also identifies existing shortcomings, such as insufficient practical training equipment in township vocational education centers, a lack of characteristic industry-related course resources, and low efficiency in resource replenishment. Targeted optimization suggestions are included, such as developing school-based courses in characteristic agriculture and rural tourism, establishing a county-level vocational education resource coordination and allocation mechanism, and optimizing the resource replenishment process for township vocational education centers. The report also clarifies the implementing entities, implementation steps, and timelines for each optimization direction. The evaluation report supports export in PDF, Excel, and Word formats and includes a newly added visual display function of a county-level vocational education development heat map, allowing education management departments to intuitively understand the differences in urban and rural vocational education development.

[0071] In summary, this embodiment, through targeted adjustments to the platform's data collection scope and the detailed content of evaluation indicators, fully adapts to the small but specialized industrial structure and the dispersed resource distribution characteristics of urban and rural areas within counties. The platform achieves real-time binding of the evaluation system with the development of county-level characteristic industries, rural revitalization policy guidance, and resource endowment differences through a three-dimensional dynamic adaptation mechanism. This effectively solves the problems of insufficient relevance and inaccurate resource evaluation in traditional evaluation methods within county-level scenarios. The evaluation results accurately reflect the effectiveness and shortcomings of the county's vocational education system in serving the development of characteristic industries. The proposed optimization suggestions are highly practical and tailored to the actual situation in counties, providing a scientific basis for education management departments to coordinate urban and rural vocational education resources and adjust the direction of school operation.

[0072] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An evaluation platform for regional vocational education system, characterized in that, The platform introduces a three-dimensional dynamic adaptation mechanism of regional policies, industrial clusters, and resource endowments. The platform includes: a data acquisition module, a regional knowledge graph construction module, an evaluation indicator decomposition module, an indicator weight dynamic adjustment module, a special evaluation module, and a result output module. The data acquisition module automatically captures relevant data on regional industrial cluster planning, local vocational education support policies, and the distribution of urban and rural vocational education resources, and transmits the data to the regional knowledge graph construction module. The regional knowledge graph construction module constructs a regional vocational education knowledge graph based on the received data, and transmits the knowledge graph to the evaluation indicator decomposition module, the indicator weight dynamic adjustment module, and the special evaluation module respectively. The evaluation index decomposition module decomposes the evaluation index into three major modules based on the received knowledge graph: industry adaptability, policy responsiveness, and resource balance. The decomposed index system is then transmitted to the index weight dynamic adjustment module and the special evaluation module. The indicator weight dynamic adjustment module, based on the received knowledge graph and indicator system, automatically adjusts the corresponding evaluation indicator weights according to the regional industrial positioning and development changes through a preset industry association algorithm, and transmits the adjusted indicator system to the special evaluation module. The special evaluation module, based on the received knowledge graph, indicator system and adjusted weights, conducts evaluations on areas with resource allocation gaps within the region using the special evaluation dimension of resource supplementation efficiency, and transmits the evaluation data to the result output module. The result output module integrates the processing results received from each module and outputs an evaluation report.

2. The regional vocational education system evaluation platform according to claim 1, characterized in that, The data acquisition module performs the following operations when collecting core regional data: The core categories of data collection should be clearly defined, including the latest industrial cluster planning documents released in the region, vocational education support policy documents issued by governments at all levels, and resource-related data on the allocation of teachers, training equipment, enrollment scale, and operating funds of vocational schools in urban and rural areas. For different types of data, corresponding real-time capture channels are built. Policy and planning documents released by government public platforms are obtained through interface docking or web crawling technology, and resource data of vocational colleges are collected through the college's dedicated data reporting port. The captured raw data is formatted and standardized to remove duplicate and invalid data.

3. The regional vocational education system evaluation platform according to claim 1, characterized in that, The regional knowledge graph construction module performs the following operations when constructing a regionally specific vocational education knowledge graph: The standardized data transmitted by the data acquisition module is classified and processed into four major data subsets: policy, industry, resources, and vocational education. Define the association rules between various data subsets, and clarify the matching association between policy data and vocational education data, the demand association between industry data and vocational education data, and the support association between resource data and vocational education data; Based on classification data and association rules, graph database technology is used to construct an initial knowledge graph containing nodes, edges and attribute information. Nodes correspond to the core entities of various types of data, edges correspond to the association relationships between entities, and attribute information is the specific feature parameters of the entities. Based on the real-time data updated and transmitted by the data acquisition module, the node information and edge association strength in the knowledge graph are dynamically updated.

4. The regional vocational education system evaluation platform according to claim 1, characterized in that, The dynamic adjustment module for indicator weights performs the following operations when adjusting the weights of evaluation indicators: The knowledge graph transmitted by the regional knowledge graph construction module is used to extract the current industrial positioning characteristics and industrial development dynamic data of the region, and to clarify the types and scale changes of the region's leading industries and key development industries. Based on the preset industry association algorithm, the corresponding mapping relationship between industry type and each indicator in the indicator system transmitted by the evaluation indicator decomposition module is established, and the core evaluation indicators corresponding to different industries are clarified. Set trigger conditions for weight adjustments and initiate the weight adjustment process based on key changes in regional industrial development. Based on the pre-set weighting calculation model and combined with data on industry scale proportion and industry development growth rate, adjustment coefficients for each core evaluation indicator are calculated. The original indicator weights are then dynamically updated according to these adjustment coefficients. The formula for calculating the adjustment coefficients is as follows: The adjusted weights will be synchronized to the indicator system and transmitted to the special evaluation module. For the first The first category of industries The weights of the evaluation indicators after adjustment As the initial weight for this indicator, This is the industry scale weighting coefficient. The weighting coefficient for industry growth rate. For the first The regional scale of similar industries For the first Annual growth rate of similar industries For the first Category of industries and the first The correlation strength coefficient of the evaluation indicators.

5. The regional vocational education system evaluation platform according to claim 1, characterized in that, The industry fit module, which is part of the evaluation index decomposition module, includes multiple sub-evaluation indicators. These include the matching degree between vocational education majors and regional industry types, the alignment between graduate employment directions and regional industry needs, the conformity of vocational education curriculum content with industry technical standards, and the fit between school-enterprise cooperation projects and regional industrial development. The comprehensive score for industry fit is calculated using the following formula: ,in, The overall score is based on industry adaptability. The correlation strength coefficients for each sub-indicator are... Quantitative scoring for each sub-indicator, As a correction coefficient for indicator compliance, the policy responsiveness module includes subdivided evaluation indicators such as the degree of implementation of policy requirements by vocational schools, the compliance of the use of policy subsidy funds, the progress of vocational education reform measures under policy guidance, and the degree of alignment between policy objectives and the effectiveness of vocational education development. The resource balance module includes subdivided evaluation indicators such as the balance coefficient of teacher allocation in urban and rural vocational schools, the balance coefficient of practical training equipment allocation, the balance coefficient of investment in school operating funds, and the coverage rate of sharing high-quality course resources.

6. The regional vocational education system evaluation platform according to claim 1, characterized in that, The specialized evaluation module's resource replenishment efficiency evaluation dimension includes specific evaluation parameters, such as the accuracy of resource gap identification, the timeliness of resource replenishment plan formulation, the efficiency of resource replenishment funding arrival, the utilization and conversion rate of newly added resources, and the improvement in vocational education service capabilities after resource replenishment. The specialized evaluation module receives the knowledge graph transmitted by the regional knowledge graph construction module, the indicator system transmitted by the evaluation indicator decomposition module, and the adjusted weights transmitted by the indicator weight dynamic adjustment module. Through real-time monitoring of the resource allocation status of vocational schools within the region using the knowledge graph, it automatically identifies gap areas where resource allocation is below the regional average, initiates targeted specialized evaluation processes for these gap areas, continuously tracks and quantitatively evaluates the entire resource replenishment process data, and calculates the comprehensive evaluation parameters for resource replenishment efficiency using the following formula: The quantitative evaluation data is transmitted to the result output module, whereby... As a comprehensive evaluation parameter for resource replenishment efficiency, The importance coefficients for each evaluation parameter are: These are the quantified values ​​for each evaluation parameter. This is a parameter timeliness correction factor.

7. The regional vocational education system evaluation platform according to claim 1, characterized in that, The data acquisition module also has data encryption transmission and storage functions. It uses a symmetric encryption algorithm to encrypt the data transmission channel to the regional knowledge graph construction module after acquisition, uses distributed storage technology to store the processed standardized data, sets up a data access permission management mechanism, and only authorizes users to access the corresponding category of data according to preset permissions. At the same time, it establishes a data backup mechanism to regularly back up the stored data off-site.

8. The regional vocational education system evaluation platform according to claim 1, characterized in that, The result output module receives the indicator system transmitted by the evaluation indicator decomposition module, the adjusted weights transmitted by the indicator weight dynamic adjustment module, and the quantitative evaluation data transmitted by the special evaluation module. The output evaluation report contains multi-dimensional content, specifically including the comprehensive evaluation score of the regional vocational education system, the sub-scores of the three major modules of industry adaptability, policy responsiveness, and resource balance, the specific scores of each sub-evaluation indicator, the development advantages and existing shortcomings of the regional vocational education system based on the evaluation score analysis, and the suggestions for optimization directions for the shortcomings, clarifying the implementation focus and key steps of each optimization direction. The evaluation report supports export in multiple formats, including PDF, Excel, and Word formats.

9. The regional vocational education system evaluation platform according to claim 1, characterized in that, The preset industry association algorithm includes an industry feature extraction sub-algorithm, an indicator mapping sub-algorithm, and a weight calculation sub-algorithm. The industry feature extraction sub-algorithm uses a machine learning model to extract features from regional industry data and accurately identify core industry needs. The indicator mapping sub-algorithm is based on a mapping rule library built on the experience of industry experts. The weight calculation sub-algorithm uses a combined weighting method that combines the analytic hierarchy process (AHP) and the entropy weighting method, incorporating expert subjective judgment while fully considering the objective characteristics of the data.

Images