Resource scheduling method and system based on campus user behavior analysis

Abstract

The application provides a resource scheduling method and system based on campus user behavior analysis, and relates to the technical field of resource management. The method comprises the following steps: collecting target behavior information of a target campus user in a preset period, and analyzing a target behavior time sequence; acquiring an arbitrary time zone and matching arbitrary behavior data; forming a campus user set, and analyzing first behavior information of a first user; if a first mode index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit value, a mode clustering cluster is formed; acquiring a number of user individuals in the mode clustering cluster, and combining the arbitrary behavior data to obtain arbitrary resource demand of the arbitrary time zone; and performing campus resource scheduling processing. The application solves the technical problem that, in the prior art, inaccurate prediction of user demand leads to unreasonable resource allocation, thereby affecting resource scheduling efficiency. By analyzing user behavior mode and determining resource demand, the efficiency of resource scheduling is improved.

Description

Technical Field

[0001] This application relates to the field of resource management technology, and in particular to a resource scheduling method and system based on campus user behavior analysis. Background Technology

[0002] Campuses contain a variety of resources, and the needs of users vary complexly across different time periods and usage scenarios. Traditional campus resource allocation methods typically rely on manual scheduling or fixed timetables. While this approach can meet the basic needs of daily campus operations to some extent, it still has limitations. Because it usually relies on experience or simple historical data statistics to predict the teaching resource needs of campus users, it is difficult to accurately capture trends in demand changes, especially when faced with the complexity and diversity of user behavior. Furthermore, traditional allocation methods cannot accurately grasp the actual needs and usage habits of campus users for different teaching resources (such as classrooms, equipment, and networks), often leading to a mismatch between resource allocation and user needs, thus affecting the efficiency of resource allocation.

[0003] In summary, existing technologies suffer from technical problems such as inaccurate prediction of user demand, leading to unreasonable resource allocation and thus affecting resource scheduling efficiency. Summary of the Invention

[0004] The purpose of this application is to provide a resource scheduling method and system based on campus user behavior analysis, in order to solve the technical problem in the prior art that inaccurate prediction of user demand leads to unreasonable resource allocation, thereby affecting the efficiency of resource scheduling.

[0005] In view of the above problems, this application provides a resource scheduling method and system based on campus user behavior analysis.

[0006] Firstly, this application provides a resource scheduling method based on campus user behavior analysis. This method is implemented through a resource scheduling system based on campus user behavior analysis. The method includes: collecting target behavior information of target campus users within a preset period and analyzing the target behavior information to obtain a target behavior time series; obtaining any time zone within the preset period and matching any behavior data of the arbitrary time zone with the target behavior time series; constructing a campus user set and analyzing the first behavior information of a first user in the campus user set to obtain a first behavior time series; if the first pattern index of the first behavior time series and the target behavior time series reaches a predetermined index limit, then forming a pattern cluster based on the target campus users and the first user; obtaining the number of individual users in the pattern cluster and combining it with the arbitrary behavior data to obtain any resource demand in the arbitrary time zone; and performing campus resource scheduling processing based on the arbitrary resource demand before the arbitrary time zone.

[0007] Optionally, the location component is activated to dynamically monitor and obtain the target real-time location of the target campus user; based on the target real-time location, the corresponding target real-time resource demand is matched in the resource demand database; and the target behavior information is composed according to the real-time time zone, the mapping relationship between the target real-time location and the target real-time resource demand.

[0008] Optionally, the positioning components include attendance devices, wireless network access management devices, campus card management devices, and access control devices.

[0009] Optionally, a user identity screening mechanism is introduced, and the campus user set is screened in combination with the target identity features of the target campus users to obtain a similar user set; any user in the similar user set is extracted and denoted as the first user; wherein, the target identity features include the target campus user's major, grade, class, and gender.

[0010] Optionally, the first behavior time series after random sampling is sampled based on the random sampling principle to obtain a first sample point, wherein the first sample point corresponds to the sample point time zone; combined with the sample point time zone, a second sample point corresponding to the first sample point is matched in the target behavior time series after random sampling; the first sample point and the second sample point form a patterned evaluation point pair set; a predetermined patterned table is introduced, and the predetermined patterned table is filled and analyzed in combination with the patterned evaluation point pair set to obtain the table result; the value corresponding to the predetermined patterned cell in the table result is taken as the first patterned index.

[0011] Optionally, a first-level filling analysis of the predetermined patterned table is performed based on the patterned evaluation point pair set to obtain a first-level table result; the second-level filling analysis of the predetermined patterned table is performed using the first-level table result as a filling constraint to obtain a second-level table result; the first-level table result and the second-level table result together constitute the table result.

[0012] Optionally, the first-level fill analysis refers to the fill analysis of all patterned cells in the predetermined patterned table, and the second-level fill analysis refers to the fill update analysis of patterned cells in the predetermined patterned table other than the preset cell set.

[0013] Optionally, the preset cell set refers to the set of the first row and the first column of the predefined patterned cells in the predefined patterned table.

[0014] Optionally, obtain any patterned cell to be analyzed in the second-level filling, and the arbitrary patterned cell corresponds to any first-level filling value; construct a set of constraint cells for the arbitrary patterned cell, and obtain the maximum value in the set of constraint cells; sum the arbitrary first-level filling value and the maximum value, and use the summation result to update the filling of the arbitrary patterned cell to obtain the second-level table result.

[0015] Secondly, this application also provides a resource scheduling system based on campus user behavior analysis, used to execute the resource scheduling method based on campus user behavior analysis as described in the first aspect, wherein the resource scheduling system based on campus user behavior analysis includes: a behavior information collection module, used to collect target behavior information of target campus users within a preset period, and analyze the target behavior information to obtain a target behavior time sequence; a behavior information matching module, used to obtain any time zone in the preset period, and match any behavior data of the arbitrary time zone in the target behavior time sequence; a first behavior analysis module, used to construct a campus user set, and analyze the first behavior information of the first user in the campus user set to obtain a first behavior time sequence; a cluster formation module, used to form a pattern cluster based on the target campus user and the first user if the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit; a resource demand determination module, used to obtain the number of individual users in the pattern cluster, and combine the arbitrary behavior data to obtain any resource demand in the arbitrary time zone; and a resource scheduling processing module, used to perform campus resource scheduling processing based on the arbitrary resource demand before the arbitrary time zone.

[0016] One or more technical solutions provided in this application have at least the following beneficial effects:

[0017] By collecting target behavior information of target campus users within a preset period and analyzing the target behavior information to obtain a target behavior time sequence; obtaining any time zone within the preset period and matching any behavior data of that time zone with the target behavior time sequence; constructing a campus user set and analyzing the first behavior information of the first user in the campus user set to obtain a first behavior time sequence; if the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit, a pattern cluster is formed based on the target campus users and the first user; obtaining the number of individual users in the pattern cluster and combining it with the arbitrary behavior data to obtain any resource demand in that time zone; and performing campus resource scheduling processing based on the arbitrary resource demand before that arbitrary time zone. In other words, by collecting user target behavior data, organizing the data in chronological order to form a target behavior time sequence, obtaining any time zone and matching it with corresponding arbitrary behavior data; and combining user behavior data and pattern clusters to predict resource demand in any time zone, resource scheduling processing is performed in advance, improving resource scheduling efficiency and accuracy, and reducing resource waste and shortages.

[0018] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the resource scheduling method based on campus user behavior analysis proposed in this application.

[0021] Figure 2 This is a schematic diagram of the resource scheduling system based on campus user behavior analysis proposed in this application.

[0022] Explanation of reference numerals in the attached diagram: 11. Behavior information collection module; 12. Behavior information matching module; 13. First behavior analysis module; 14. Cluster formation module; 15. Resource requirement determination module; 16. Resource scheduling and processing module. Detailed Implementation

[0023] This application provides a resource scheduling method and system based on campus user behavior analysis, solving the technical problem in existing technologies where inaccurate prediction of user demand leads to unreasonable resource allocation, thus affecting resource scheduling efficiency. By collecting user target behavior data, organizing the data chronologically to form a target behavior time series, and obtaining and matching any time zone with corresponding arbitrary behavior data, this method combines user behavior data and pattern clustering to predict resource demand in any time zone, enabling proactive resource scheduling and improving efficiency and accuracy, while reducing resource waste and shortages.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a resource scheduling method based on campus user behavior analysis, wherein the resource scheduling method based on campus user behavior analysis is executed through a resource scheduling system based on campus user behavior analysis, and the resource scheduling method based on campus user behavior analysis specifically includes the following steps:

[0026] S100: Collect target behavior information of target campus users within a preset period, and analyze the target behavior information to obtain the target behavior time sequence.

[0027] Furthermore, this application S100 includes:

[0028] The target campus user's real-time location is obtained by dynamically monitoring the location component; the corresponding real-time resource demand is obtained by matching the real-time location with the resource demand database; and the target behavior information is formed according to the real-time time zone, the mapping relationship between the real-time location and the real-time resource demand.

[0029] The positioning components include attendance devices, wireless network access management devices, campus card management devices, and access control devices.

[0030] Specifically, the activation positioning component includes multiple hardware devices used to track and record the location of target users, such as attendance devices, wireless access management devices, campus card management devices, and access control devices. Attendance devices typically refer to devices used to monitor the presence of students, teachers, and other personnel, such as card readers and fingerprint recognition devices; wireless access management devices typically use Wi-Fi or other wireless technologies to locate users and monitor their activities on campus; campus card management devices refer to devices that allow users to enter different locations by swiping their campus cards; and access control devices are used to control and record users' entry into or exit from specific areas, such as card-swipe access control systems.

[0031] The location of target campus users is monitored in real time by activating positioning components on campus (such as attendance devices, wireless network access management devices, campus card management devices, and access control devices), continuously tracking and updating the users' real-time location data. After obtaining the real-time location of the target campus user, a matching process is performed in the resource demand database to determine the target's real-time resource needs corresponding to that location. For example, when a user enters a classroom, the resource demand database is used to view the classroom's resource needs (such as classroom seats, projection equipment, etc.). The resource demand database stores demand data for various resources on campus and is typically updated dynamically based on factors such as user behavior, location, and time. The resource demand database records the resource needs of different times, locations, and user groups.

[0032] Based on the mapping relationship between real-time time zone (i.e., time period), real-time location of the target user, and target resource demand, this information is aggregated to generate the user's target behavior information. For example, suppose student A enters classroom 101 at 10:00 AM. Based on the time (e.g., 9:00 AM to 11:00 AM) and location (classroom 102), the student's target behavior information is generated, describing student A's behavior during a specific time period, such as entering the classroom and requesting multimedia resources.

[0033] A pre-defined period is used to collect target behavior information of target campus users, such as every hour or every day. Within the pre-defined period, the location component collects the target campus users' behavior information, analyzes it, sorts the collected data according to time sequence, and converts it into a target behavior time sequence, including the specific actions of each user at different times. For example, if student A enters classroom 101 at 10:00, the target real-time resource needs at this time include multimedia equipment, empty classroom, and network access; if they enter the cafeteria at 12:00, the target real-time resource needs at this time include cafeteria lighting and water dispensers; if they enter the library at 2:00, the target real-time resource needs at this time include seating. By activating the location component and dynamic monitoring, the location information of target campus users is obtained in real time, accurately predicting their resource needs and improving the targeting and efficiency of resource allocation.

[0034] S200: Obtain any time zone in the preset period, and match any behavior data of the arbitrary time zone in the target behavior time sequence.

[0035] Specifically, the system acquires data from any time zone within a preset period, i.e., a specific time period. For example, if the preset period is one month, the arbitrary time zone could be any day or a specific time period within that month. Based on the arbitrary time zone, it matches the target behavior time sequence to find all behaviors of the target campus users within that time period, obtaining arbitrary behavior data. For example, if the selected arbitrary time zone is 2 PM to 3 PM, it matches the behavior of user A entering the library. During the matching process, all behavioral data occurring within the selected time zone are identified and extracted. This data will be used for subsequent analysis and resource scheduling. By acquiring behavioral data from a specific time zone, user behavior patterns within that time zone can be analyzed, helping to identify peak or trough periods of resource demand within a specific time period, thereby optimizing resource allocation.

[0036] S300: Construct a campus user set and analyze the first behavior information of the first user in the campus user set to obtain the first behavior time sequence.

[0037] Furthermore, this application S300 includes:

[0038] A user identity screening mechanism is introduced, and the campus user set is screened in combination with the target identity features of the target campus users to obtain a similar user set; any user in the similar user set is extracted and denoted as the first user; wherein, the target identity features include the target campus user's major, grade, class, and gender.

[0039] Specifically, a campus user set is constructed, encompassing all possible user groups, such as students, teachers, administrative staff, and others. The behavioral and demand data of all these users can be collected and analyzed to optimize resource allocation. The campus user set includes a large number of users, each with distinct identity characteristics and behavioral data. To more accurately analyze and predict user needs, a user identity filtering mechanism is introduced. This mechanism filters the campus user set based on user identity characteristics (such as major, year, class, gender, etc.), dividing the campus users into multiple subsets for in-depth analysis of the needs of different user groups. The user identity filtering mechanism is a mechanism that filters target user sets based on user characteristics (such as major, year, class, gender, etc.), helping to divide the user group into different subgroups, thereby enabling more accurate analysis of the needs and behaviors of different user groups.

[0040] The process involves identifying the target campus users' identity characteristics, which are various features that represent the target campus users' identities. These typically include the user's major, year of study, class, gender, etc. Based on these target identity characteristics, the campus user set is filtered to obtain a similar user group, where users all possess similar identity characteristics. For example, if the target campus user is a male student in Class 1, Year 2 of Computer Science, then based on this target identity characteristic, all male students in Class 1, Year 2 of Computer Science from the campus user set are selected to form a similar user group.

[0041] A user is randomly selected from a set of similar users, designated as the first user. The first user's first behavioral information is extracted to generate a first behavioral time sequence, recording all actions performed by the first user within a specific time frame, arranged chronologically. For example, user B enters classroom 103 from 9:00 to 10:00 to attend a programming class; uses equipment in the computer lab from 10:30 to 12:00; eats lunch in the cafeteria from 12:20 to 13:00; and enters classroom 205 from 2:00 to 4:00 to participate in a group discussion. Based on user characteristics, users are divided into multiple subgroups with similar needs and behaviors. Patterns in user behavior are discovered and extracted, allowing for advance scheduling and allocation of resources to avoid waste or shortages.

[0042] S400: If the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit, then a pattern cluster is formed based on the target campus user and the first user.

[0043] Furthermore, this application S400 includes:

[0044] Based on the principle of random sampling, the first behavior time series after scattering is sampled to obtain the first sample point, wherein the first sample point corresponds to the time zone of the sample point; combined with the time zone of the sample point, the second sample point corresponding to the first sample point is matched in the scattered target behavior time series; the first sample point and the second sample point form a patterned evaluation point pair set; a predetermined patterned table is introduced, and the predetermined patterned table is filled and analyzed in combination with the patterned evaluation point pair set to obtain the table result; the value corresponding to the predetermined patterned cell in the table result is taken as the first patterned index.

[0045] Specifically, random sampling is a statistical method that estimates the properties of a population by randomly drawing samples from it. It helps in selecting representative small samples from large datasets. The first row of time series data is scattered, transforming continuous data into discrete sample points. A random sampling method is then used to select a data point from the scattered data as the first sample point. The sample time zone refers to the position of the sampled data point on the time axis, that is, a specific moment within a specific time period (such as hours, minutes, etc.).

[0046] The target behavior time series of target campus users is also processed into scatter plots, transforming continuous behavioral data into discrete sample points. Combining the time zone of the sample points, a second sample point corresponding to the first sample point is matched within the scatter plotted target behavior time series. The second sample point and the first sample point should be in the same time zone.

[0047] The pairing of the first and second samples forms a patterned evaluation point pair set, an important data structure used to measure the similarity of behavioral patterns. The patterned evaluation point pair set is used to analyze the demand relationship between different users or different resources under a certain behavioral pattern. For example, by analyzing user behavior in different classrooms over two time periods, the demand intensity of each classroom during that time period can be determined and evaluation point pairs can be formed. A predefined patterned table is a predefined structured table used to record the relationship between different time periods, different behavioral patterns, and resource demand. It is usually built based on historical data, predictive models, or expert experience and can provide guidance for resource scheduling in subsequent analysis.

[0048] Using a patterned evaluation point set, the corresponding cells in a pre-defined patterned table are filled, mapping the data in the evaluation point set to the table so that each cell in the table reflects the resource demand within a specific time period. After filling and analysis, all cells in the pre-defined patterned table are updated, forming a table result that provides the demand information for each time period and each resource for resource scheduling. From the filled table result, the value corresponding to the pre-defined patterned cell is selected as the first patterned index. The pre-defined patterned cell is each cell in the pre-defined patterned table, usually representing the demand intensity of a certain resource within a specific time period. The value in each cell reflects the demand for that resource during that time period. The first patterned index represents the relationship between a certain time period and resource demand. The value of the first patterned index is usually a floating value between [0,1], with a larger value indicating a stronger resource demand and a smaller value indicating a weaker resource demand. For example, assuming that the demand value for classroom A is 0.7 between 9:10 and 10:00, this 0.7 is the first patterned index in the table, used to quantify the demand intensity for classroom A during that time period.

[0049] If the first patterning index reaches a predetermined limit, it indicates that the behavioral pattern has sufficient characteristics or importance. The user is then clustered with other users who have similar patterning indices. All users meeting this condition will be grouped into the same cluster, indicating similarity in certain behavioral characteristics. The predetermined limit is a pre-set threshold used to determine whether a behavioral pattern has reached sufficient importance or intensity. Only when a patterning index reaches or exceeds this limit is the behavioral pattern considered worthy of further analysis or action.

[0050] Pattern clustering is a clustering analysis based on behavioral time-series data, forming user groups or datasets with similar behavioral characteristics. When multiple users' behavioral time-series indices reach the same or similar patterns, they will be clustered into the same cluster, indicating that they share common characteristics in certain behaviors. For example, if there are 50 students in a class, based on behavioral time-series data and pattern indices, these students can be divided into several clusters, with students within each cluster exhibiting high similarity in their behavioral patterns. For instance, suppose students A and B have a behavioral pattern index of 0.8 and exhibit similar class patterns between 9:00 AM and 10:00 AM. Students C and D have a pattern index of 0.9 and also exhibit similar class patterns during the same time period. Then, students A and B might be clustered into one cluster, while students C and D might be clustered into another.

[0051] By identifying user groups with similar behavioral patterns, we can more accurately meet their needs, group users with similar behavioral characteristics (such as students) together, and optimize resource scheduling based on the corresponding behavioral patterns.

[0052] Furthermore, this application also includes the following steps:

[0053] Based on the patterned evaluation point pair set, a first-level filling analysis of the predetermined patterned table is performed to obtain the first-level table result; using the first-level table result as the filling constraint, a second-level filling analysis of the predetermined patterned table is performed to obtain the second-level table result; the first-level table result and the second-level table result together constitute the table result.

[0054] The first-level filling analysis refers to the filling analysis of all patterned cells in the predetermined patterned table, and the second-level filling analysis refers to the filling and updating analysis of patterned cells in the predetermined patterned table other than the preset cell set.

[0055] The preset cell set refers to the set of the first row and the first column of the predefined patterned cells in the predefined patterned table.

[0056] Obtain any patterned cell to be analyzed in the second-level table, and the arbitrary patterned cell corresponds to any first-level fill value; construct a constraint cell set for the arbitrary patterned cell, and obtain the maximum value in the constraint cell set; sum the arbitrary first-level fill value and the maximum value, and use the summation result to update the fill value of the arbitrary patterned cell to obtain the second-level table result.

[0057] Specifically, a predefined pattern table is a structured table used to record and analyze behavioral characteristics of different patterns. Each cell represents a specific behavioral pattern, which can be a single behavior or a combination of multiple behaviors. Through fill-in analysis, the degree of conformity between different user behavioral patterns can be determined. The predefined pattern table undergoes first-level fill-in analysis, which involves analyzing all patterned cells in the table. The first-level fill-in analysis process analyzes and fills in these cells; specifically, based on the patterned evaluation point-to-point set, it determines the degree of matching between each behavioral pattern and the target behavioral sequence, and fills in the corresponding values ​​for each cell.

[0058] When analyzing each cell, the system uses data from the patterned evaluation point set to determine whether the user's behavior matches the preset target behavior. For example, if the target behavior's timing matches the user's behavior in a certain time zone, the cell will be filled with a higher value, indicating a high degree of match. After analysis and filling, a complete first-level table is obtained, representing the matching status of behavioral patterns with the target behavior's timing in all patterned cells. For example, if a cell in the table represents the behavior of entering a classroom, and the matching degree between this behavior and the target behavior's timing is 0.85, then the value of that cell will be 0.85. The values ​​of all cells constitute the first-level table result.

[0059] After the first-level fill analysis, all cells in the table will be filled with preliminary results, i.e., the first-level table results, which can provide a general picture of resource demand. However, it has not yet taken into account complex factors (such as specific constraints, actual behavioral deviations, etc.). For example, if a user group uses the classroom less frequently during a certain period, the demand under certain behavioral patterns may be overestimated because individual user differences have not been considered.

[0060] The table results obtained from the first-level completion analysis serve as constraints. Following the first-level completion analysis, specific cells in the predefined patterned table are updated and filled. Unlike the first-level analysis, the second-level completion analysis focuses on updating non-preset cells (i.e., cells excluding the first row and first column), and the filling of these cells depends on the first-level completion results and constraints from other cells. During the second-level completion analysis, more complex user behavior characteristics and constraints are considered, such as the diversity of user behavior, the actual availability of resources, and the specificity of time periods, leading to further adjustments and optimizations to the table.

[0061] Retrieve any patterned cell to be analyzed in the second-level fill stage. These are cells in a predefined patterned table that require second-level fill updates. They are typically not in the first row or column, but rather represent the relationship between specific behavioral patterns and time periods, potentially involving different combinations of behavioral patterns and resource requirements. For each cell to be analyzed in the second-level fill stage, extract the first-level fill value obtained during the first-level fill stage.

[0062] For each patterned cell to be analyzed, a set of constraint cells related to that cell is selected based on the table's structure or contextual information. The cells in the constraint cell set may come from other cells in the same row or column as the cell to be analyzed, or specific cells related to behavioral patterns and time periods. The constraint cell set is a collection of other cells associated with the cell to be analyzed; these cells provide constraints for the cell to be analyzed, and are typically other cells in the same row or column of the table as the cell to be analyzed, or other table cells related to behavioral patterns.

[0063] Extracting the maximum value from the constraint cell set reflects the strength of resource requirements or behavioral patterns under that constraint. For example, if the constraint cell set contains matching degrees for multiple behavioral patterns, the maximum value represents the most important behavioral pattern under a certain time period or resource requirement. The first-level input value is summed with the maximum value in the constraint cell set, and the value of the cell to be analyzed is further adjusted based on the existing input values ​​and constraints. The summed result represents a more accurate estimate of resource requirements after considering the constraints, based on the first-level input values. The summed result, obtained by adding the first-level input value and the maximum value in the constraint cell set, determines the final input value for that cell.

[0064] The summation result is used as the new input value to update the content of the cells to be analyzed, resulting in the final secondary table result. This reflects the matching between resource requirements and behavioral patterns, improving the accuracy of resource scheduling. The secondary table result is the updated pre-defined pattern table result after secondary input analysis, containing the new values ​​of all cells and reflecting a more precise match between resource requirements and behavioral patterns.

[0065] By combining the results from the primary and secondary tables, a final table is formed, integrating the preliminary results of the primary analysis and the optimized results of the secondary analysis, ultimately creating a more accurate resource allocation table. For example, the primary table might show higher demand for certain classrooms in the morning, while the secondary table, based on more detailed adjustments to actual behavior, might show slightly lower demand for other classrooms. The final table, combining the information from both, provides a more accurate basis for subsequent resource allocation.

[0066] By combining primary and secondary data analysis, actual resource needs can be reflected more accurately, avoiding the shortcomings of relying solely on historical data. It accurately reflects the similarity of user behavior patterns, effectively improving the efficiency and accuracy of resource scheduling, ensuring the rational allocation of resources, avoiding excessive or insufficient resource allocation, and improving resource utilization.

[0067] S500: Obtain the number of individual users in the pattern cluster and combine it with the arbitrary behavior data to obtain the arbitrary resource requirements of the arbitrary time zone.

[0068] Specifically, the number of individual users within a pattern cluster—that is, the number of users in the cluster who conform to a specific behavioral pattern—is obtained to estimate the amount of resources needed in a specific time zone. By combining arbitrary behavioral data from any time zone, the resource needs of target campus users in any time zone are determined, allowing for the pre-planning and allocation of resources. In situations of limited resources, priority is given to ensuring the supply of resources for important teaching tasks and frequently used resources. Based on users' real-time location and behavioral status, nearby idle resources are dynamically allocated for their use.

[0069] Based on the number of individual users and arbitrary behavioral data from any time zone, the required resource needs are calculated. The number of users typically determines the required area size; a larger number of users means a larger area is needed. Corresponding resources are determined based on behavioral data. For example, if user behavior indicates a need for a computer class, and each student requires a computer and a certain amount of bandwidth, then sufficient computer and network resources can be prepared in advance based on these needs.

[0070] By obtaining the number of individual users within a pattern cluster, we can accurately understand the size of a group exhibiting a particular behavioral pattern, thereby accurately predicting resource demand within a specific time zone. Combining this with user behavior data to extrapolate specific resource needs helps in more rational resource allocation, avoiding excessive or insufficient resource distribution. For example, if only 10 users need a classroom during a certain time period, only one classroom can be allocated instead of multiple classrooms, preventing resource waste. Precise resource scheduling not only improves resource utilization efficiency but also ensures that users can obtain the resources they need in a timely manner during peak demand periods, enhancing user satisfaction and experience.

[0071] S600: Perform campus resource scheduling processing based on the arbitrary resource demand before the arbitrary time zone.

[0072] Specifically, before any time zone is reached, campus resource scheduling is performed based on arbitrary resource demands, meaning resource scheduling occurs before the required time. After determining the arbitrary resource demands, the actual campus resource status is used to determine whether these demands can be met. If resources are insufficient, the scheduling strategy may need to be adjusted to prioritize the most critical needs, i.e., prioritizing important teaching tasks and frequently used resources. For example, if 3 out of 10 classrooms are occupied by other activities, vacant classrooms are prioritized for allocation, and resource allocation for other users is dynamically adjusted, such as postponing some low-priority courses or using multi-functional classrooms.

[0073] Based on a comparison of resource demand and available resources, the scheduling system allocates resources. For example, it prioritizes classroom teaching resources, followed by laboratory and equipment needs, and finally network bandwidth. If resource conflicts occur during scheduling (such as insufficient classrooms or equipment), resource allocation is automatically adjusted, and resources are reassessed and reallocated through a feedback mechanism. For instance, if a change in student usage patterns is detected in a time zone, the number of computers needed might increase from 20 to 25; dynamic adjustments to resource pre-allocation ensure that demand is met. By dynamically scheduling resources based on actual needs, optimal allocation of campus resources is ensured in any time zone. Whether it's classrooms, equipment, or other resources, allocation is based on actual demand, thereby improving resource utilization.

[0074] In summary, the resource scheduling method based on campus user behavior analysis provided in this application has the following beneficial effects:

[0075] By collecting target behavior information of target campus users within a preset period and analyzing the target behavior information to obtain a target behavior time sequence; obtaining any time zone within the preset period and matching any behavior data of that time zone with the target behavior time sequence; constructing a campus user set and analyzing the first behavior information of the first user in the campus user set to obtain a first behavior time sequence; if the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit, a pattern cluster is formed based on the target campus users and the first user; obtaining the number of individual users in the pattern cluster and combining it with the arbitrary behavior data to obtain any resource demand in that time zone; and performing campus resource scheduling processing based on the arbitrary resource demand before that arbitrary time zone. In other words, by collecting user target behavior data, organizing the data in chronological order to form a target behavior time sequence, obtaining any time zone and matching it with corresponding arbitrary behavior data; and combining user behavior data and pattern clusters to predict resource demand in any time zone, resource scheduling processing is performed in advance, improving resource scheduling efficiency and accuracy, and reducing resource waste and shortages.

[0076] Example 2: Based on the same inventive concept as the resource scheduling method based on campus user behavior analysis in Example 1, this application also provides a resource scheduling system based on campus user behavior analysis. Please refer to the appendix. Figure 2 The resource scheduling system based on campus user behavior analysis includes:

[0077] The system comprises the following modules: a behavior information collection module 11, which collects target behavior information of target campus users within a preset period and analyzes the target behavior information to obtain a target behavior time sequence; a behavior information matching module 12, which obtains any time zone within the preset period and matches any behavior data of the target behavior time sequence in the arbitrary time zone; a first behavior analysis module 13, which constructs a campus user set and analyzes the first behavior information of the first user in the campus user set to obtain a first behavior time sequence; a clustering module 14, which forms a pattern cluster based on the target campus user and the first user if the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit; a resource demand determination module 15, which obtains the number of individual users in the pattern cluster and combines the arbitrary behavior data to obtain any resource demand in the arbitrary time zone; and a resource scheduling processing module 16, which performs campus resource scheduling processing based on the arbitrary resource demand before the arbitrary time zone.

[0078] Furthermore, the behavior information collection module 11 in the resource scheduling system based on campus user behavior analysis is also used for:

[0079] The target campus user's real-time location is obtained by dynamically monitoring the location component; the corresponding real-time resource demand is obtained by matching the real-time location with the resource demand database; and the target behavior information is formed according to the real-time time zone, the mapping relationship between the real-time location and the real-time resource demand.

[0080] Furthermore, the behavior information collection module 11 in the resource scheduling system based on campus user behavior analysis is also used for:

[0081] The positioning components include attendance devices, wireless network access management devices, campus card management devices, and access control devices.

[0082] Furthermore, the first behavior analysis module 13 in the resource scheduling system based on campus user behavior analysis is also used for:

[0083] A user identity screening mechanism is introduced, and the campus user set is screened in combination with the target identity features of the target campus users to obtain a similar user set; any user in the similar user set is extracted and denoted as the first user; wherein, the target identity features include the target campus user's major, grade, class, and gender.

[0084] Furthermore, the clustering module 14 in the resource scheduling system based on campus user behavior analysis is also used for:

[0085] Based on the principle of random sampling, the first behavior time series after scattering is sampled to obtain the first sample point, wherein the first sample point corresponds to the time zone of the sample point; combined with the time zone of the sample point, the second sample point corresponding to the first sample point is matched in the scattered target behavior time series; the first sample point and the second sample point form a patterned evaluation point pair set; a predetermined patterned table is introduced, and the predetermined patterned table is filled and analyzed in combination with the patterned evaluation point pair set to obtain the table result; the value corresponding to the predetermined patterned cell in the table result is taken as the first patterned index.

[0086] Furthermore, the clustering module 14 in the resource scheduling system based on campus user behavior analysis is also used for:

[0087] Based on the patterned evaluation point pair set, a first-level filling analysis of the predetermined patterned table is performed to obtain the first-level table result; using the first-level table result as the filling constraint, a second-level filling analysis of the predetermined patterned table is performed to obtain the second-level table result; the first-level table result and the second-level table result together constitute the table result.

[0088] Furthermore, the clustering module 14 in the resource scheduling system based on campus user behavior analysis is also used for:

[0089] The first-level filling analysis refers to the filling analysis of all patterned cells in the predetermined patterned table, and the second-level filling analysis refers to the filling and updating analysis of patterned cells in the predetermined patterned table other than the preset cell set.

[0090] Furthermore, the clustering module 14 in the resource scheduling system based on campus user behavior analysis is also used for:

[0091] The preset cell set refers to the set of the first row and the first column of the predefined patterned cells in the predefined patterned table.

[0092] Furthermore, the clustering module 14 in the resource scheduling system based on campus user behavior analysis is also used for:

[0093] Obtain any patterned cell to be analyzed in the second-level table, and the arbitrary patterned cell corresponds to any first-level fill value; construct a constraint cell set for the arbitrary patterned cell, and obtain the maximum value in the constraint cell set; sum the arbitrary first-level fill value and the maximum value, and use the summation result to update the fill value of the arbitrary patterned cell to obtain the second-level table result.

[0094] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The resource scheduling method and specific examples based on campus user behavior analysis in Example 1 are also applicable to the resource scheduling system based on campus user behavior analysis in this example. Through the foregoing detailed description of the resource scheduling method based on campus user behavior analysis, those skilled in the art can clearly understand the resource scheduling system based on campus user behavior analysis in this example. Therefore, for the sake of brevity, it will not be described in detail here.

[0095] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0096] Obviously, those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A resource scheduling method based on campus user behavior analysis, characterized in that, include: Collect target behavior information of target campus users within a preset period, and analyze the target behavior information to obtain the target behavior time sequence; Obtain any time zone within the preset period, and match any behavior data of the arbitrary time zone in the target behavior time sequence; A campus user set is constructed, and the first behavior information of the first user in the campus user set is analyzed to obtain the first behavior time sequence; If the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit, then a pattern cluster is formed based on the target campus user and the first user; Obtain the number of individual users in the pattern cluster, and combine the arbitrary behavior data to obtain the arbitrary resource requirements of the arbitrary time zone; Campus resource scheduling is performed based on the arbitrary resource demand before the arbitrary time zone; Before forming a pattern cluster based on the target campus user and the first user if the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit, the process includes: Based on the principle of random sampling, the time sequence of the first row after scattering is sampled to obtain the first sample point, wherein the first sample point corresponds to the time zone of the sample point; Based on the time zone of the sample points, the second sample point corresponding to the first sample point is matched in the scattered target behavior time sequence; The first sample point and the second sample point form a patterned evaluation point pair set; A predefined patterned table is introduced, and the filling analysis of the predefined patterned table is performed in combination with the patterned evaluation point pair set to obtain the table results; The value corresponding to the predefined patterned cell in the table result is used as the first patterned index.

2. The resource scheduling method based on campus user behavior analysis as described in claim 1, characterized in that, Collect target behavior information of target campus users within a preset period, including: The target campus user's real-time location is obtained by activating the positioning component for dynamic monitoring. Based on the real-time location of the target, the corresponding real-time resource requirement of the target is obtained by matching in the resource requirement database; The target behavior information is composed based on the mapping relationship between the real-time time zone, the real-time location of the target, and the real-time resource requirements of the target.

3. The resource scheduling method based on campus user behavior analysis as described in claim 2, characterized in that, The positioning components include attendance devices, wireless network access management devices, campus card management devices, and access control devices.

4. The resource scheduling method based on campus user behavior analysis as described in claim 1, characterized in that, After establishing the campus user group, it also includes: A user identity screening mechanism is introduced, and the campus user set is screened in combination with the target identity characteristics of the target campus users to obtain a similar user set; Extract any user from the set of similar users and denote it as the first user; The target identity features include the target campus user's major, grade, class, and gender.

5. The resource scheduling method based on campus user behavior analysis as described in claim 1, characterized in that, A predetermined patterned table is introduced, and the filling analysis of the predetermined patterned table is performed in conjunction with the patterned evaluation point pair set to obtain the table results, including: Based on the patterned evaluation point pair set, a first-level filling analysis of the predetermined patterned table is performed to obtain the first-level table results; Using the results of the first-level table as filling constraints, the second-level filling analysis of the predetermined patterned table is performed to obtain the results of the second-level table; The results of the first-level table and the results of the second-level table together constitute the table results.

6. The resource scheduling method based on campus user behavior analysis as described in claim 5, characterized in that, The first-level filling analysis refers to the filling analysis of all patterned cells in the predetermined patterned table, and the second-level filling analysis refers to the filling and updating analysis of patterned cells in the predetermined patterned table other than the preset cell set.

7. The resource scheduling method based on campus user behavior analysis as described in claim 6, characterized in that, The preset cell set refers to the set of the first row and the first column of the predefined patterned cells in the predefined patterned table.

8. The resource scheduling method based on campus user behavior analysis as described in claim 5, characterized in that, Using the results of the first-level table as filling constraints, the second-level filling analysis of the predetermined patterned table is performed to obtain the second-level table results, including: Obtain any patterned cell to be analyzed in the second level, and the arbitrary patterned cell corresponds to any first-level fill value; Construct a set of constraint cells for the arbitrary patterned cell, and obtain the maximum value in the set of constraint cells; Sum the values ​​entered at any first level with the maximum value, and use the sum to update the values ​​entered in any patterned cell to obtain the result of the second-level table.

9. A resource scheduling system based on campus user behavior analysis, characterized in that, The steps for implementing the resource scheduling method based on campus user behavior analysis according to any one of claims 1 to 8, wherein the resource scheduling system based on campus user behavior analysis comprises: The behavior information collection module is used to collect target behavior information of target campus users within a preset period, and analyze the target behavior information to obtain the target behavior time sequence; The behavior information matching module is used to obtain any time zone in the preset period and match any behavior data of the arbitrary time zone in the target behavior time sequence. The first behavior analysis module is used to construct a campus user set and analyze the first behavior information of the first user in the campus user set to obtain the first behavior time sequence. A clustering module is used to form a pattern cluster based on the target campus user and the first user if the first pattern index of the first behavior time sequence and the target behavior time sequence reaches a predetermined index limit. The resource demand determination module is used to obtain the number of individual users in the pattern cluster and combine the arbitrary behavior data to obtain the arbitrary resource demand of the arbitrary time zone. The resource scheduling processing module is used to perform campus resource scheduling processing based on the arbitrary resource demand before the arbitrary time zone.

Images