Method, device and equipment for balanced configuration of regional education resources and medium

Abstract

The application relates to a regional education resource balanced allocation method, device, equipment and medium. The method comprises the following steps: firstly, obtaining shared resource use time length data of each education institution to form an original log sequence; then, carrying out time sequence analysis on the original log sequence to generate an occupation rate distribution mode of the shared resource in different time periods; based on the occupation rate distribution mode, determining the idle state of the shared resource through a preset idle threshold, adopting a clustering algorithm to perform grouping processing on the resource supply and demand relationship to obtain a demand difference classification result; analyzing and planning a shared resource cross-institution flow path according to the demand difference classification result, and then generating a preliminary flow plan; finally, taking the preliminary flow plan as input, constructing a resource flow simulation model, adopting an iterative optimization algorithm to adjust and optimize the model parameters, and finally outputting a shared resource balanced flow allocation scheme covering cross-institution and cross-time period. The method can realize efficient activation and balanced allocation of regional education shared resources.

Description

Technical Field

[0001] This invention belongs to the field of educational resource allocation technology, and in particular relates to methods, devices, equipment and media for the balanced allocation of regional educational resources. Background Technology

[0002] Currently, the balanced allocation of regional educational resources largely relies on administrative coordination or experience-based allocation models based on static data. While some technical solutions incorporate statistical methods for resource usage data, they generally suffer from three core flaws: First, the monitoring of the usage status of shared resources in educational institutions lacks in-depth analysis along a time-series dimension, failing to accurately capture the dynamic changes in resource occupancy rates at different times, resulting in low accuracy in identifying idle resources and poor utilization efficiency. Second, in the resource supply and demand matching stage, single-dimensional indicators such as demand gaps or idle rates are often used to determine the flow direction, ignoring the differences in resource stock and demand fluctuations among different schools within the region, leading to a low degree of alignment between resource flow paths and actual needs. Third, the lack of a dynamic iterative optimization mechanism after the allocation plan is generated makes it difficult to cope with changes in resource demand across institutions and time periods, ultimately resulting in an imbalance where high-quality resources are concentrated in a few schools while weaker schools suffer from insufficient resource supply, severely hindering the achievement of the goal of high-quality and balanced regional educational development. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, device, equipment, and medium for the balanced allocation of regional educational resources that can effectively avoid the shortcomings of traditional configuration models, such as fixed solutions and difficulty in responding to changes in demand, and achieve efficient activation and balanced distribution of shared educational resources within the region.

[0004] Firstly, this application provides a method for the balanced allocation of regional educational resources, including:

[0005] Data on the usage time of shared resources from various educational institutions was obtained to produce the raw log sequence.

[0006] By performing time-series analysis on the original log sequences and integrating time-dimensional feature information, the occupancy distribution pattern of shared resources in different time periods can be obtained.

[0007] Based on the occupancy rate distribution pattern, the idle status of shared resources is determined, and clustering is performed using data from adjacent educational institutions to obtain the classification results of demand differences.

[0008] Demand fluctuation characteristics are extracted from the demand difference classification results, and the cross-institutional flow paths of shared resources are analyzed by correlating regional difference information to generate preliminary flow plans.

[0009] The initial flow plan was simulated and optimized using an iterative optimization algorithm to obtain a balanced flow allocation scheme for shared resources across institutions and time periods.

[0010] In one embodiment, time-series analysis is performed on the original log sequence and time-dimensional feature information is integrated to obtain the occupancy distribution pattern of shared resources in different time periods, including:

[0011] Extract time dimension information from the original log sequence to obtain the resource access time point sequence.

[0012] The resource access time sequence is divided into preset time intervals to obtain the access event set corresponding to each time interval.

[0013] The time period occupancy data is obtained by statistically analyzing the number of access events and the cumulative duration of each access event set corresponding to each time period.

[0014] Based on the time period occupancy data, the resource occupancy rate of each time period is calculated and the occupancy rate distribution relationship is constructed to obtain the shared resource occupancy rate pattern.

[0015] Based on the shared resource occupancy rate pattern recognition, the periodic fluctuation characteristics of resource occupancy are identified, and the resource occupancy periodic attribute is obtained.

[0016] By associating the resource occupancy cycle attribute with the educational institution type identifier, we can obtain the institution's differentiated resource occupancy pattern.

[0017] By integrating the shared resource occupancy rate pattern and the institutional differentiated resource occupancy pattern in multiple dimensions, an occupancy rate distribution pattern is obtained.

[0018] In one embodiment, the idle status of shared resources is determined based on the occupancy distribution pattern, and clustering is performed using data from adjacent educational institutions to obtain a classification result of demand differences, including:

[0019] Based on the occupancy distribution pattern of shared resources, statistical characteristic parameters of occupancy rates in different time periods are extracted. Combined with the occupancy rate intervals corresponding to historical idle states, the resource idle threshold is determined through statistical fitting analysis.

[0020] By comparing the real-time occupancy rate of the target shared resource with the resource idle threshold, if the real-time occupancy rate is lower than the resource idle threshold, the shared resource is determined to be in an idle state.

[0021] Obtain a dataset of shared resource occupancy rates from neighboring educational institutions; the dataset includes dynamic demand metrics.

[0022] For shared resources that are idle, the demand difference value is calculated by combining dynamic demand indicators and shared resource occupancy data to obtain potential demand difference characteristics.

[0023] Clustering algorithms are used to group and cluster the potential demand difference characteristics to obtain the demand difference classification results.

[0024] In one embodiment, the demand difference value is calculated using the following formula:

[0025]

[0026] in, Indicates the demand difference value. This represents the resource idle threshold, obtained through statistical fitting of historical occupancy rate distribution. This indicates the real-time occupancy rate of the target institution. This represents the dynamic demand indicator of adjacent institutions, calibrated based on their teaching plans and resource application data. This indicates the real-time occupancy rate of adjacent institutions. This represents the weighting coefficient, which is determined based on the regional resource allocation policy objectives. This represents a regional disparity correction factor, a correction coefficient adapted to urban-rural and inter-school development disparities, with values ​​ranging from [value missing]. .

[0027] In one embodiment, demand fluctuation characteristics are extracted from the demand difference classification results, and the cross-institutional flow paths of shared resources are analyzed by correlating regional difference information to generate a preliminary flow plan, including:

[0028] Demand fluctuation characteristics are extracted from the demand difference classification results; the demand fluctuation characteristics include fluctuation cycle and fluctuation amplitude.

[0029] By matching and associating the extracted demand fluctuation characteristics with regional difference information in multiple dimensions, priority flow paths of shared resources across institutions are obtained; the regional difference information includes the resource stock data and the quantitative value of resource demand gap of each educational institution.

[0030] Clustering algorithms are used to group and cluster demand fluctuation characteristics to obtain a set of demand fluctuation patterns.

[0031] Based on the set of demand fluctuation patterns and regional differences, the path weight matrix of shared resource flow across institutions is calculated.

[0032] The priority flow paths are iteratively updated using the path weight matrix to obtain optimized cross-organizational flow paths for shared resources, generating a preliminary flow plan. The preliminary flow plan includes the resource scheduling amount for each path and the corresponding resource flow time nodes.

[0033] In one embodiment, the path weight matrix for cross-agency flow of shared resources is calculated using the following formula:

[0034]

[0035] in, This represents the elements in the path weight matrix. The dimensional balance weights are determined based on the regional education resource allocation policy objectives. Indicating the organization and The similarity of demand fluctuation patterns is calculated using a dynamic time warping algorithm. These represent the demand fluctuation characteristics of the two institutions, Indicating the organization The gap value for the target shared resources, Indicating the organization The idle stock value of the target shared resources. Indicates the fairness correction factor. It adapts to the differences in development between urban and rural areas and between schools.

[0036] In one embodiment, the initial flow plan is simulated and optimized using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods, including:

[0037] Obtain the quantitative data input corresponding to the preliminary flow plan; the quantitative data input includes the cross-institutional flow direction of shared resources, the amount of resources allocated across time periods, and the timeliness requirements for resource scheduling.

[0038] Based on quantitative data input, a resource flow equilibrium optimization model is constructed. With the goal of maximizing resource utilization and achieving optimal allocation balance, an iterative optimization algorithm is used to adjust the parameters of the equilibrium optimization model in multiple rounds to obtain a preliminary equilibrium scheme for the flow of shared resources.

[0039] The rationality of resource allocation in the preliminary equilibrium scheme is verified, and quantitative data on flow bottlenecks are extracted. The quantitative data on flow bottlenecks includes the scale of resource gaps, timeliness deviation values, and imbalance coefficients corresponding to areas with insufficient resource supply, areas with lagging flow timeliness, and areas with imbalanced allocation.

[0040] Based on quantitative data of flow bottlenecks, secondary optimization constraints are constructed, and the priority sequence of cross-institutional resource allocation is determined according to the constraints and the real-time matching degree of resource supply and demand. The constraints include resource replenishment priority constraints, timeliness guarantee constraints, and balanced allocation threshold constraints.

[0041] Verify whether the resource allocation scheme corresponding to the priority sequence meets the preset balance threshold. If it does, generate a shared resource balance flow configuration scheme. The configuration scheme covers the resource allocation amount, flow path and timeliness requirements of multiple time periods.

[0042] Secondly, this application also provides a device for the balanced allocation of regional educational resources, the device comprising:

[0043] The data time series analysis module is used to obtain the usage time data of shared resources of various educational institutions to obtain the raw log sequence; it is also used to perform time series analysis on the raw log sequence and integrate time dimension feature information to obtain the occupancy distribution pattern of shared resources in different time periods.

[0044] The resource idleness determination module is used to determine the idle status of shared resources based on the occupancy rate distribution pattern, and to obtain the demand difference classification results by clustering and grouping data from adjacent educational institutions.

[0045] The fluctuation path planning module is used to extract demand fluctuation characteristics from the demand difference classification results, analyze the cross-institutional flow path of shared resources by associating regional difference information, and generate a preliminary flow plan.

[0046] The scheme balance optimization module is used to simulate and optimize the preliminary flow plan using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods.

[0047] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0048] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned method.

[0049] The aforementioned method, apparatus, computer equipment, and storage media for balanced allocation of regional educational resources first acquire data on the usage duration of shared resources from various educational institutions, forming a raw log sequence. Then, time-series analysis is performed on the raw log sequence to extract and integrate time-dimensional feature information, thereby generating a distribution pattern of shared resource occupancy rates at different times. Based on this occupancy distribution pattern, the idle status of shared resources is determined by a preset idle threshold. Simultaneously, resource occupancy and demand data from adjacent educational institutions are introduced, and a clustering algorithm is used to group the resource supply and demand relationship, obtaining a demand difference classification result. Demand fluctuation characteristics are further extracted from the demand difference classification result and matched with regional difference information in multiple dimensions to analyze and plan the cross-institutional flow path of shared resources, thereby generating a preliminary flow plan. Finally, using the preliminary flow plan as input, a resource flow simulation model is constructed, and an iterative optimization algorithm is used to adjust and optimize the model parameters, ultimately outputting a balanced allocation scheme for shared resources covering cross-institutional and cross-time periods. This method achieves dynamic monitoring of the occupancy status of shared resources through time-series analysis, solving the problem of low accuracy in identifying idle resources in traditional models. Based on clustering and feature matching, it establishes a precise quantitative model of supply and demand, breaking the limitations of single-dimensional indicators in determining resource flow direction and improving the adaptability of resource flow paths to actual needs. By using iterative optimization algorithms to simulate and optimize the initial plan, a dynamically adjustable resource allocation scheme is formed, effectively avoiding the shortcomings of traditional allocation models where schemes are fixed and difficult to adapt to changing needs. Ultimately, it achieves efficient activation and balanced allocation of shared educational resources within the region, providing practical technical support for the high-quality and balanced development of regional education. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart of a method for balanced allocation of regional educational resources provided in an embodiment of the present invention;

[0052] Figure 2 This is a structural block diagram of a regional educational resource equalization allocation device provided in an embodiment of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] In one embodiment, such as Figure 1 As shown, this application provides a method for balanced allocation of regional educational resources, which may include the following steps:

[0055] Step S101: Obtain the usage time data of shared resources from various educational institutions to obtain the original log sequence.

[0056] Specifically, the data acquisition targets all educational institutions participating in resource sharing within the region. The acquired data includes core fields such as the type identifier of the shared resource, the institution to which the user belongs, the start and end time of resource use, and the duration of a single use. The above data is collected from the resource management systems of each educational institution through a unified data interface, and the collected data is structured and organized according to the timestamp order to form a raw log sequence with time as the axis.

[0057] Step S102: Perform time-series analysis on the original log sequence and integrate time-dimensional feature information to obtain the occupancy distribution pattern of shared resources in different time periods.

[0058] Specifically, the time series analysis involves dividing the original log sequence into multiple analysis periods according to a preset time granularity, calculating the total usage time and total available time of each type of shared resource within each period, and calculating the resource occupancy rate for each period. Simultaneously, it extracts time-dimensional feature information, including the changing trend of occupancy rates in different periods and the time intervals between peaks and troughs. By integrating the above analysis results and feature information, the final output is a shared resource occupancy rate distribution pattern with "period-resource type-occupancy rate" as the core dimension.

[0059] Step S103: Determine the idle status of shared resources based on the occupancy rate distribution pattern, and combine the data of adjacent educational institutions to perform clustering and grouping to obtain the demand difference classification results.

[0060] Furthermore, the determination of the idle status of shared resources is based on a preset idle threshold. By comparing the resource occupancy rate of each time period with the idle threshold, if the resource occupancy rate is lower than the idle threshold in a certain time period, the resource is determined to be idle in the corresponding time period. At the same time, resource stock data and resource demand index data of neighboring educational institutions are collected. The resource idle potential data of the target institution is integrated with the demand data of neighboring institutions. Idle potential and demand gap are selected as core feature dimensions. Clustering algorithms are used to group all educational institutions in the region, and finally, the demand difference classification results reflecting different supply and demand matching degrees are obtained.

[0061] Step S104: Extract demand fluctuation characteristics from the demand difference classification results, analyze the cross-institutional flow path of shared resources by associating regional difference information, and generate a preliminary flow plan.

[0062] Specifically, the extraction of demand fluctuation characteristics involves the resource demand data of each institutional group in the demand difference classification results. The extracted characteristics include core indicators such as demand fluctuation cycle and fluctuation amplitude. Regional difference information includes data such as the quantitative value of resource stock, quantitative value of demand gap, and school scale of each educational institution. By matching and associating demand fluctuation characteristics with regional difference information in multiple dimensions, and using the resource supply and demand matching degree as the criterion, the cross-institutional flow path of shared resources from idle institutions to demand institutions is analyzed and planned. Based on the planned flow path, the resource allocation amount and resource flow time nodes of each path are further clarified, and finally a preliminary flow plan covering all shared resources in the region is generated.

[0063] Step S105: The preliminary flow plan is simulated and optimized using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods.

[0064] Using the initial flow plan as input, a resource flow simulation model is constructed with the objective functions of maximizing resource utilization and optimizing the regional resource allocation balance. Constraints such as resource flow timeliness and institutional demand priority are also set. Subsequently, an iterative optimization algorithm is used to perform multiple rounds of parameter adjustment and calculation on the model. In each iteration, the resource flow bottleneck data output by the model is extracted and used as the basis for adjustment in the next iteration. After multiple rounds of iterative optimization, when the model output meets the preset balance threshold, the iteration stops and the final solution is output. This solution covers the direction of resource flow across institutions and the amount of resource scheduling across time periods.

[0065] The aforementioned method for balanced allocation of regional educational resources first obtains data on the usage time of shared resources from various educational institutions, forming a raw log sequence. Then, time-series analysis is performed on the raw log sequence to extract and integrate time-dimensional feature information, thereby generating a distribution pattern of shared resource occupancy rates at different times. Based on this occupancy distribution pattern, the idle status of shared resources is determined by a preset idle threshold. Simultaneously, resource occupancy and demand data from adjacent educational institutions are introduced, and a clustering algorithm is used to group the resource supply and demand relationship, obtaining demand difference classification results. Demand fluctuation characteristics are further extracted from the demand difference classification results and matched with regional difference information in multiple dimensions to analyze and plan the cross-institutional flow path of shared resources, thereby generating a preliminary flow plan. Finally, using the preliminary flow plan as input, a resource flow simulation model is constructed, and an iterative optimization algorithm is used to adjust and optimize the model parameters, ultimately outputting a balanced allocation scheme for shared resources covering cross-institutional and cross-time periods. This method achieves dynamic monitoring of the occupancy status of shared resources through time series analysis, solving the problem of low accuracy in identifying idle resources in the traditional model. Relying on clustering and feature matching, it establishes a precise quantitative model of supply and demand relationship, breaking the limitation of judging the direction of resource flow by single-dimensional indicators and improving the adaptability of resource flow paths to actual needs. By using iterative optimization algorithms to simulate and optimize the preliminary plan, a dynamically adjustable resource allocation scheme is formed, effectively avoiding the defects of fixed schemes and difficulty in responding to changes in demand in the traditional allocation model, and realizing the efficient activation and balanced allocation of educational shared resources in the region.

[0066] In one embodiment, performing time-series analysis on the original log sequence and integrating time-dimensional feature information to obtain the occupancy distribution pattern of shared resources in different time periods may include the following steps:

[0067] Step S201: Extract time dimension information from the original log sequence to obtain the resource access time point sequence.

[0068] Step S202: Divide the resource access time sequence into preset time intervals to obtain the access event set corresponding to each time interval.

[0069] Step S203: Calculate the number of access events and the cumulative duration based on the access event set corresponding to each time period to obtain the time period occupancy data.

[0070] Step S204: Calculate the resource occupancy rate for each time period based on the time period occupancy duration data and construct the occupancy rate distribution relationship to obtain the shared resource occupancy rate pattern.

[0071] Step S205: Based on the shared resource occupancy rate pattern recognition, the periodic fluctuation characteristics of resource occupancy are identified to obtain the resource occupancy periodic attribute.

[0072] Step S206: Associate the resource occupancy cycle attribute with the educational institution type identifier to obtain the institution's differentiated resource occupancy pattern.

[0073] Step S207: The shared resource occupancy rate pattern and the institutional differentiated resource occupancy pattern are correlated and integrated in multiple dimensions to obtain the occupancy rate distribution pattern.

[0074] First, time-dimensional information is extracted from the original log sequence and organized into a resource access time point sequence with timestamps as the core. Then, the resource access time point sequence is divided according to preset time intervals to obtain the access event set corresponding to each time interval. Based on the access event set of each time interval, the number of access events and the cumulative value of resource usage time in each time interval are counted to form time interval occupancy data. On this basis, the resource occupancy rate of each time interval is calculated in combination with the total usable resource time, and the corresponding distribution relationship between time interval and occupancy rate is constructed to obtain the shared resource occupancy rate pattern. Further feature mining is performed on the shared resource occupancy rate pattern to identify the periodic fluctuation characteristics of resource occupancy and extract the resource occupancy periodic attribute. The resource occupancy periodic attribute is correlated with the type identifier of each educational institution, and the institution-differentiated resource occupancy pattern is generated by combining the resource usage characteristics of different types of institutions. Finally, the shared resource occupancy rate pattern and the institution-differentiated resource occupancy pattern are correlated and integrated in multiple dimensions to form a shared resource occupancy rate distribution pattern that can simultaneously reflect the time distribution pattern and the institutional differences.

[0075] This embodiment achieves a refined characterization of the occupancy status of shared resources, overcoming the shortcomings of traditional resource analysis methods that only focus on static data and ignore the fluctuation patterns over time and differences in institutional types. The generated occupancy rate distribution pattern simultaneously covers the distribution characteristics of different time periods and the differentiated characteristics of different institutions, providing accurate and comprehensive data support for subsequent determination of resource idle status and analysis of supply and demand differences. The entire process is based on the objective analysis of raw data, without human experience intervention, ensuring the objectivity and reliability of the analysis results, and laying a solid data foundation for subsequent stages of balanced allocation of regional educational resources.

[0076] In one embodiment, determining the idle status of shared resources based on occupancy distribution patterns and obtaining demand difference classification results by clustering data from adjacent educational institutions may include the following steps:

[0077] Step S301: Based on the occupancy rate distribution pattern of shared resources, extract the statistical characteristic parameters of occupancy rate for each time period, combine them with the occupancy rate intervals corresponding to historical idle states, and determine the resource idle threshold through statistical fitting analysis.

[0078] Preferably, the resource idle threshold is calculated using the following formula:

[0079]

[0080] in, Indicates the historical occupancy rate of shared resources. Quantiles This represents the quantile percentage of occupancy corresponding to historical idle periods, determined by statistics from historical idle intervals. This represents the correction coefficient, calibrated based on the regional educational resource allocation scenario and the accuracy requirements for historical idle resource assessment, with a value range of... , The coefficient of variation represents the occupancy rate over a historical period. , The standard deviation of occupancy rate for historical periods. This represents the average occupancy rate over a historical period.

[0081] Step S302: Compare the real-time occupancy rate of the target shared resource with the resource idle threshold. If the real-time occupancy rate is lower than the resource idle threshold, the shared resource is determined to be in an idle state.

[0082] Step S303: Obtain the shared resource occupancy rate dataset of neighboring educational institutions; the dataset includes dynamic demand indicators.

[0083] Step S304: For shared resources that are idle, calculate the demand difference value by combining dynamic demand indicators and shared resource occupancy data to obtain potential demand difference characteristics.

[0084] Step S305: Use a clustering algorithm to group and cluster the potential demand difference features to obtain the demand difference classification results.

[0085] Specifically, based on the occupancy distribution pattern of shared resources, statistical characteristic parameters such as the mean, median, and fluctuation coefficient of occupancy rates for each time period are extracted. Simultaneously, the occupancy rate intervals corresponding to historical idle states are retrieved, and statistical fitting analysis is performed between the statistical characteristic parameters and historical intervals to calculate and determine the critical threshold for determining resource idleness. The real-time occupancy rate of the target shared resource is compared with the aforementioned resource idleness threshold. If the real-time occupancy rate is lower than the resource idleness threshold, the shared resource is determined to be idle. A dataset of shared resource occupancy rates from neighboring educational institutions is collected. This dataset contains core data such as the real-time resource occupancy rate and dynamic demand indicators of each neighboring institution. For shared resources determined to be idle, the demand difference value is calculated using a preset formula, combining the dynamic demand indicators of neighboring educational institutions and the target resource occupancy rate data, to extract potential demand difference features that can characterize the degree of supply and demand matching. These potential demand difference features are selected as clustering dimensions, and a preset clustering algorithm is used to group and cluster the supply and demand data of all educational institutions in the region, ultimately obtaining demand difference classification results reflecting different supply and demand matching types.

[0086] This embodiment determines the resource idle threshold by combining statistical fitting analysis with historical data, solving the problem of traditional idleness judgment relying on fixed values ​​and having poor adaptability, and improving the accuracy and objectivity of idleness status judgment. By introducing dynamic demand indicators of neighboring educational institutions, the resource idleness status is combined with actual demand to calculate the demand difference value, so that the potential demand difference characteristics can truly reflect the resource supply and demand gap in the region. The demand difference classification results obtained based on the clustering algorithm provide scientific data support for subsequent cross-institutional flow path planning of shared resources, effectively avoiding the blind flow of resources.

[0087] In one embodiment, the demand difference value can be calculated using the following formula:

[0088]

[0089] in, Indicates the demand difference value. This represents the resource idle threshold, obtained through statistical fitting of historical occupancy rate distribution. This indicates the real-time occupancy rate of the target institution. This represents the dynamic demand indicator of adjacent institutions, calibrated based on their teaching plans and resource application data. This indicates the real-time occupancy rate of adjacent institutions. This represents the weighting coefficient, which is determined based on the regional resource allocation policy objectives. This represents a regional disparity correction factor, a correction coefficient adapted to urban-rural and inter-school development disparities, with values ​​ranging from [value missing]. .

[0090] This embodiment addresses the problems of traditional demand difference assessment being one-dimensional and highly subjective: by integrating the idle status of the target institution with the demand data of adjacent institutions, a direct correlation between supply and demand data is achieved, enabling the demand difference value to truly reflect the actual gap between resource supply and demand within the region; the introduction of a weighting coefficient α and a regional difference correction factor β allows the calculation process to adapt to the policy orientation and development differences of different regions, improving the scenario adaptability of demand difference assessment; all parameters are derived from previous analysis stages or regional policy calibration, ensuring the reliability and objectivity of the calculation basis and avoiding biases caused by human experience intervention.

[0091] In one embodiment, extracting demand fluctuation characteristics from the demand difference classification results, analyzing the cross-institutional flow paths of shared resources by correlating regional difference information, and generating a preliminary flow plan may include the following steps:

[0092] Step S401: Extract demand fluctuation characteristics from the demand difference classification results; demand fluctuation characteristics include fluctuation period and fluctuation amplitude.

[0093] Step S402 involves multi-dimensional matching and association of the extracted demand fluctuation characteristics with regional difference information to obtain priority flow paths for shared resources across institutions; the regional difference information includes resource stock data and quantitative values ​​of resource demand gaps for each educational institution.

[0094] Step S403: Use a clustering algorithm to group and cluster the demand fluctuation characteristics to obtain a set of demand fluctuation patterns.

[0095] Step S404: Based on the set of demand fluctuation patterns and regional difference information, calculate the path weight matrix of shared resource cross-institutional flow.

[0096] Step S405: Iteratively update the priority flow path using the path weight matrix to obtain the optimized cross-organizational flow path of shared resources and generate a preliminary flow plan; the preliminary flow plan includes the resource scheduling amount of each path and the corresponding resource flow time node.

[0097] Specifically, demand fluctuation characteristics are extracted from the demand difference classification results. These characteristics encompass two core dimensions: fluctuation cycle (i.e., the alternation interval between peak and trough resource demand, such as monthly cycles, semester cycles, etc.) and fluctuation amplitude (i.e., the quantitative indicator of the difference between peak and trough demand), comprehensively capturing the dynamic changes in resource demand among different educational institutions within the region. Subsequently, the extracted demand fluctuation characteristics are matched and correlated with regional difference information in a multi-dimensional manner. This regional difference information explicitly includes quantitative data on the shared resource stock of each educational institution (representing the scale of idle resources that the institution can output) and quantitative values ​​of resource demand gaps (representing the degree of scarcity of target resources by the institution). During the matching and correlation process, "demand fluctuation timing fit" and "resource supply and demand scale fit" are used as dual criteria to prioritize all possible cross-institutional resource flow paths, ultimately forming a priority-ranked cross-institutional shared resource flow path. Simultaneously, a pre-defined clustering algorithm (such as K-array clustering) is employed. The -means clustering algorithm is used to group and cluster the extracted demand fluctuation features, grouping institutions with similar fluctuation patterns into one category, and extracting a set of demand fluctuation patterns with common characteristics. Based on this set of demand fluctuation patterns and the aforementioned regional difference information, a path weight matrix for the cross-institutional flow of shared resources is calculated using a preset quantitative formula. The matrix dimension corresponds to the total number of educational institutions in the region, and each element in the matrix accurately quantifies the path priority weight from an idle resource output institution to a demand institution. Finally, based on this path weight matrix, the generated priority flow paths are iteratively updated multiple times to continuously optimize the priority ranking and rationality of the paths. Based on the updated optimized flow paths, the resource scheduling volume (i.e., the scale of resource flow in a single instance or time period) and the precise resource flow time nodes (such as specific dates and time periods, matching the demand fluctuation cycle) corresponding to each path are further clarified, generating a standardized and implementable preliminary flow plan.

[0098] This embodiment effectively addresses the core shortcomings of traditional cross-institutional resource flow path planning, namely "insufficient time-series adaptation, supply-demand mismatch, and ambiguous priority determination": Accurate extraction of demand fluctuation characteristics breaks through the limitations of traditional planning that only focuses on static demand, enabling path planning to adapt to dynamic changes in resource demand and avoiding mismatches between resource flow and demand peaks; Combining demand fluctuation characteristics with regional difference information for matching and correlation ensures that path planning considers both time-series adaptability and the differences in resource endowments of various institutions, significantly improving the accuracy and feasibility of priority flow paths; The construction of a demand fluctuation pattern set and the calculation of the path weight matrix provide a quantitative basis for determining path priorities, replacing traditional subjective judgments based on experience and ensuring the scientific nature of path optimization; Iteratively updating paths through the weight matrix and generating a preliminary flow plan containing specific scheduling quantities and time nodes allows resource flow planning to move from a "macro-level" approach to a "concrete execution" level.

[0099] In one embodiment, the path weight matrix for cross-agency flow of shared resources can be calculated using the following formula:

[0100]

[0101] in, This represents the elements in the path weight matrix. The dimensional balance weights are determined based on the regional education resource allocation policy objectives. Indicating the organization and The similarity of demand fluctuation patterns is calculated using a dynamic time warping algorithm. These represent the demand fluctuation characteristics of the two institutions, Indicating the organization The gap value for the target shared resources, Indicating the organization The idle stock value of the target shared resources. Indicates the fairness correction factor. It adapts to the differences in development between urban and rural areas and between schools.

[0102] This embodiment effectively solves the core problems of traditional path priority determination, such as its single-dimensional nature, strong subjectivity, and poor adaptability. By integrating two-dimensional data—demand fluctuation pattern similarity and regional resource supply-demand adaptability—it overcomes the limitations of traditional path determination based solely on a single supply-demand indicator. This allows path weights to simultaneously reflect temporal adaptability and resource endowment differences, improving the comprehensiveness and accuracy of priority determination. The introduction of dual-regulation parameters—dimensional balance weights and fairness correction factors—allows for flexible calibration based on policy orientations and development differences across regions, achieving a dynamic balance between efficiency and fairness goals and enhancing the scenario adaptability of the calculation model. All parameters originate from previous analysis stages or objective regional data, without human intervention, ensuring the objectivity and reliability of the calculation results. The generated path weight matrix provides quantitative support for subsequent iterative updates of priority flow paths, replacing traditional subjective ranking methods and significantly improving the scientific nature of path optimization.

[0103] In one embodiment, the preliminary flow plan is simulated and optimized using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods, which may include the following steps:

[0104] Step S501: Obtain the quantitative data input corresponding to the preliminary flow plan; the quantitative data input includes the cross-institutional flow direction of shared resources, the amount of resources allocated across time periods, and the timeliness requirements for resource scheduling.

[0105] Step S502: Based on the quantitative data input, construct a resource flow equilibrium optimization model. With the goal of maximizing resource utilization and achieving optimal allocation balance, use an iterative optimization algorithm to adjust the parameters of the equilibrium optimization model in multiple rounds to obtain a preliminary equilibrium scheme for the flow of shared resources.

[0106] Step S503: Verify the rationality of resource allocation for the preliminary equilibrium scheme and extract quantitative data on flow bottlenecks. The quantitative data on flow bottlenecks includes the scale of resource gaps, timeliness deviation values, and imbalance coefficients corresponding to areas with insufficient resource supply, areas with delayed flow timeliness, and areas with imbalanced allocation.

[0107] Step S504: Construct secondary optimization constraints based on quantitative data of flow bottlenecks, and determine the priority sequence of cross-institutional resource allocation according to the constraints and the real-time matching degree of resource supply and demand; the constraints include resource replenishment priority constraints, timeliness guarantee constraints, and balanced allocation threshold constraints.

[0108] Step S505: Verify whether the resource allocation scheme corresponding to the priority sequence meets the preset balance threshold. If it does, generate a shared resource balance flow configuration scheme. The configuration scheme covers the resource allocation amount, flow path and timeliness requirements of multiple time periods.

[0109] Specifically, the process involves obtaining quantitative data input for the initial resource flow plan. This input includes core information such as the cross-institutional flow direction of shared resources (i.e., the specific flow of resources from the output institution to the demand institution), the cross-time period resource allocation (covering the resource scheduling scale of different time periods), and the resource scheduling timeliness requirements (i.e., the time constraints that resource flow must meet). Based on the above quantitative data input, a resource flow equilibrium optimization model is constructed, with the dual objective functions of maximizing resource utilization and optimizing allocation equilibrium. An iterative optimization algorithm is used to adjust the parameters of this equilibrium optimization model in multiple rounds, and the initial equilibrium scheme for shared resource flow is output through continuous iterative optimization. Subsequently, the rationality of resource allocation is verified on the initial equilibrium scheme, focusing on identifying unreasonable issues in dimensions such as resource supply, flow timeliness, and allocation scale. Quantitative data on flow bottlenecks is extracted, specifically including the resource gap scale corresponding to areas with insufficient resource supply, the timeliness deviation value corresponding to areas with lagging flow timeliness, and the imbalance coefficient corresponding to areas with imbalanced allocation.

[0110] Based on the extracted quantitative data of flow bottlenecks, secondary optimization constraints are constructed. These constraints explicitly cover resource replenishment priority constraints (prioritizing resource supply to scarce areas), timeliness guarantee constraints (ensuring resource flow meets timeliness requirements), and balanced allocation threshold constraints (limiting the range of balanced deviations in resource allocation within the region). Combined with the real-time matching degree of resource supply and demand, a priority sequence for cross-institutional resource allocation is determined. Finally, it is verified whether the resource allocation scheme corresponding to this priority sequence meets the preset balanced threshold. If it does, a final shared resource balanced flow configuration scheme is generated. This scheme fully covers the resource allocation volume, specific flow paths, and corresponding timeliness requirements across multiple time periods, and is ready for direct implementation.

[0111] This embodiment effectively addresses the core shortcomings of traditional resource allocation schemes, such as strong subjectivity, poor adaptability, and insufficient balance. It constructs an optimization model using quantitative data as input, combining a dual objective function with an iterative optimization algorithm to ensure the scientific validity and rationality of the initial balanced scheme, avoiding biases caused by human experience intervention. By extracting quantitative data on flow bottlenecks through rationality verification, it accurately identifies weak links in the scheme, providing a clear basis for adjustment in secondary optimization. The construction of secondary optimization constraints and the determination of priority sequences enable precise control over resource allocation, ensuring the scheme can adapt to real-time changes in resource supply and demand. The final balanced flow allocation scheme covers core elements across multiple time periods, balancing resource utilization efficiency and allocation balance, effectively avoiding problems such as resource supply and demand mismatch and failure to meet flow timeliness standards. It provides feasible technical support for the balanced allocation of shared resources across institutions and time periods within the region, significantly improving the systematicness and efficiency of regional educational resource allocation.

[0112] In one embodiment, such as Figure 2 As shown, this application also provides a device for the balanced allocation of regional educational resources, which may include:

[0113] The data time series analysis module 601 is used to obtain the usage time data of shared resources of various educational institutions to obtain the original log sequence; it is also used to perform time series analysis on the original log sequence and integrate time dimension feature information to obtain the occupancy rate distribution pattern of shared resources in different time periods.

[0114] The resource idleness determination module 602 is used to determine the idle status of shared resources based on the occupancy rate distribution pattern, and to obtain the demand difference classification results by clustering and grouping data of adjacent educational institutions.

[0115] The fluctuation path planning module 603 is used to extract demand fluctuation characteristics from the demand difference classification results, analyze the cross-institutional flow path of shared resources by associating regional difference information, and generate a preliminary flow plan.

[0116] The scheme balance optimization module 604 is used to simulate and optimize the preliminary flow plan using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods.

[0117] The aforementioned regional educational resource equitable allocation device employs a data time-series analysis module to collect data on the usage duration of shared resources from various educational institutions. This data is then structured to obtain a raw log sequence, which is further analyzed to extract and integrate time-dimensional feature information, outputting a distribution pattern of shared resource occupancy rates across different time periods. A resource idleness determination module receives this distribution pattern and uses it to determine the idle status of shared resources. Simultaneously, it collects resource-related data from adjacent educational institutions and uses a clustering algorithm to group the resource supply and demand relationships within the region, generating a demand difference classification result. A fluctuation path planning module takes the demand difference classification result as input, extracts the demand fluctuation characteristics, and correlates them with regional difference information including resource inventory and demand gaps of each institution. This allows for the planning of shared resource flow paths across institutions and the generation of a preliminary flow plan. Finally, a scheme equitable optimization module takes the preliminary flow plan, uses an iterative optimization algorithm to construct a simulation model, and performs multiple rounds of optimization and adjustment, ultimately outputting a balanced allocation scheme for shared resources covering cross-institutional and cross-time periods.

[0118] This embodiment effectively solves the problems of fragmented data processing, low accuracy of supply and demand matching, and rigid allocation schemes in traditional regional education resource allocation: A data time-series analysis module dynamically and accurately depicts resource usage status, providing a reliable data foundation for subsequent idle resource assessment; a resource idleness assessment module combines data from neighboring institutions to conduct cluster analysis, improving the comprehensiveness of demand difference identification; a fluctuation path planning module associates multi-dimensional information to plan flow paths, ensuring the adaptability of the initial plan; and an iterative optimization mechanism in the scheme balancing optimization module ensures the balance and feasibility of the final allocation scheme. Overall, it achieves a systematic and data-driven approach to regional education resource allocation, significantly improving the efficiency of idle resource revitalization and the balance of resource allocation, providing stable and reliable technical support for the high-quality and balanced development of regional education.

[0119] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0120] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the regional educational resource equitable allocation method as described above.

[0121] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0122] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0123] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for balanced allocation of educational resources in a region, characterized in that, The method includes: Obtain data on the usage time of shared resources from various educational institutions to obtain the raw log sequence; The original log sequence is subjected to time series analysis and the time dimension feature information is integrated to obtain the occupancy distribution pattern of shared resources in different time periods; Based on the occupancy rate distribution pattern, the idle status of shared resources is determined, and clustering is performed using data from adjacent educational institutions to obtain the classification results of demand differences. Demand fluctuation characteristics are extracted from the demand difference classification results, and the cross-institutional flow path of shared resources is analyzed by correlating regional difference information to generate a preliminary flow plan. The preliminary flow plan is simulated and optimized using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods.

2. The method of claim 1, wherein, The step of performing time-series analysis on the original log sequence and integrating time-dimensional feature information to obtain the occupancy distribution pattern of shared resources in different time periods includes: Extract time dimension information from the original log sequence to obtain the resource access time point sequence; The resource access time sequence is divided into preset time intervals to obtain the access event set corresponding to each time interval; Based on the set of access events corresponding to each time period, the number of access events and the cumulative duration are counted to obtain the time period occupancy data. Based on the time period occupancy data, the resource occupancy rate of each time period is calculated and the occupancy rate distribution relationship is constructed to obtain the shared resource occupancy rate pattern. Based on the shared resource occupancy rate pattern recognition, the periodic fluctuation characteristics of resource occupancy are identified, and the resource occupancy periodic attribute is obtained. By associating the resource occupancy cycle attribute with the educational institution type identifier, a differentiated resource occupancy pattern for the institution can be obtained. By integrating the shared resource occupancy rate pattern and the institutional differentiated resource occupancy pattern in multiple dimensions, an occupancy rate distribution pattern is obtained.

3. The method according to claim 1, characterized in that, The process of determining the idle status of shared resources based on the occupancy distribution pattern, and then clustering and grouping data from adjacent educational institutions to obtain a classification result of demand differences, includes: Based on the occupancy rate distribution pattern of shared resources, statistical characteristic parameters of occupancy rate for each time period are extracted. Combined with the occupancy rate interval corresponding to historical idle status, the resource idle threshold is determined through statistical fitting analysis. Compare the real-time occupancy rate of the target shared resource with the resource idle threshold. If the real-time occupancy rate is lower than the resource idle threshold, the shared resource is determined to be in an idle state. Obtain a dataset of shared resource occupancy rates from neighboring educational institutions; the dataset includes dynamic demand indicators. For the shared resources that are idle, the demand difference value is calculated by combining the dynamic demand index and the occupancy rate data of the shared resources to obtain the potential demand difference characteristics. Clustering algorithms are used to group and cluster the potential demand difference features to obtain the demand difference classification results.

4. The method of claim 3, wherein, The demand difference value is calculated using the following formula: in, Indicates the demand difference value. This represents the resource idle threshold, obtained through statistical fitting of historical occupancy rate distribution. This indicates the real-time occupancy rate of the target institution. This represents the dynamic demand indicator of adjacent institutions, calibrated based on their teaching plans and resource application data. This indicates the real-time occupancy rate of adjacent institutions. This represents the weighting coefficient, which is determined based on the regional resource allocation policy objectives. This represents a regional disparity correction factor, a correction coefficient adapted to urban-rural and inter-school development disparities, with values ​​ranging from [value missing]. .

5. The method of claim 1, wherein, The step of extracting demand fluctuation characteristics from the demand difference classification results, analyzing the cross-institutional flow paths of shared resources by associating regional difference information, and generating a preliminary flow plan includes: Demand fluctuation characteristics are extracted from the demand difference classification results; the demand fluctuation characteristics include fluctuation period and fluctuation amplitude. The extracted demand fluctuation characteristics are matched and correlated with regional difference information in multiple dimensions to obtain priority flow paths of shared resources across institutions; the regional difference information includes resource stock data and resource demand gap quantification values ​​of each educational institution. The demand fluctuation characteristics are grouped and clustered using a clustering algorithm to obtain a set of demand fluctuation patterns; Based on the set of demand fluctuation patterns and the regional difference information, the path weight matrix for the cross-institutional flow of shared resources is calculated. The priority flow path is iteratively updated using the path weight matrix to obtain the optimized cross-institutional flow path of shared resources, and a preliminary flow plan is generated; the preliminary flow plan includes the resource scheduling amount of each path and the corresponding resource flow time node.

6. The method according to claim 5, characterized in that, The path weight matrix for the cross-institutional flow of shared resources is calculated using the following formula: in, This represents the elements in the path weight matrix. The dimensional balance weights are determined based on the regional education resource allocation policy objectives. Indicating the organization and The similarity of demand fluctuation patterns is calculated using a dynamic time warping algorithm. These represent the demand fluctuation characteristics of the two institutions, Indicating the organization The gap value for the target shared resources, Indicating the organization The idle stock value of the target shared resources. Indicates the fairness correction factor. It adapts to the differences in development between urban and rural areas and between schools.

7. The method of claim 1, wherein, The preliminary flow plan is simulated and optimized using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods, including: Obtain the quantitative data input corresponding to the preliminary flow plan; the quantitative data input includes the cross-institutional flow direction of shared resources, the cross-time period resource allocation amount, and the resource scheduling timeliness requirements. Based on the quantitative data input, a resource flow equilibrium optimization model is constructed. With the goal of maximizing resource utilization and achieving optimal allocation balance, an iterative optimization algorithm is used to adjust the parameters of the equilibrium optimization model in multiple rounds to obtain a preliminary equilibrium scheme for the flow of shared resources. The rationality of resource allocation is verified for the preliminary equilibrium scheme, and quantitative data of flow bottlenecks are extracted. The quantitative data of flow bottlenecks includes the scale of resource gaps, timeliness deviation values ​​and imbalance coefficients corresponding to areas with insufficient resource supply, areas with lagging flow timeliness, and areas with imbalanced allocation. Based on the quantitative data of the flow bottleneck, a secondary optimization constraint is constructed, and the priority sequence of cross-institutional resource allocation is determined according to the constraint and the real-time matching degree of resource supply and demand; the constraint includes resource replenishment priority constraint, timeliness guarantee constraint, and balanced allocation threshold constraint. Verify whether the resource allocation scheme corresponding to the priority sequence meets the preset balance threshold. If it does, generate a shared resource balanced flow configuration scheme. The configuration scheme covers the resource allocation amount, flow path and timeliness requirements of multiple time periods.

8. A device for balancing the allocation of regional educational resources, characterized in that: The device includes: The data time series analysis module is used to obtain the usage time data of shared resources of various educational institutions to obtain the original log sequence; it is also used to perform time series analysis on the original log sequence and integrate time dimension feature information to obtain the occupancy rate distribution pattern of shared resources in different time periods. The resource idleness determination module is used to determine the idle status of shared resources based on the occupancy rate distribution pattern, and to obtain the demand difference classification result by clustering and grouping data of adjacent educational institutions. The fluctuation path planning module is used to extract demand fluctuation characteristics from the demand difference classification results, analyze the cross-institutional flow path of shared resources by associating regional difference information, and generate a preliminary flow plan. The scheme balance optimization module is used to simulate and optimize the preliminary flow plan using an iterative optimization algorithm to obtain a balanced flow configuration scheme for shared resources across institutions and time periods.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images