Community education resource scheduling system based on multi-dimensional demand matching

Abstract

The invention discloses a community education resource scheduling system based on multi-dimensional demand matching, and particularly relates to the field of education resource management, which comprises a disturbance construction module, an acquisition module, an extraction module, an evaluation module and a scheduling module, the disturbance construction module is used for constructing a disturbance task sequence of a target course, the disturbance task sequence is composed of a plurality of disturbance tasks, and each disturbance task comprises task content, random excitation parameters and task triggering time of the target course. By constructing a disturbance task to induce behavior response, extracting behavior characteristics and combining with a motivation offset evaluation function, identification of pseudo-learning behaviors and dynamic adjustment of scheduling priority are realized, so that long-term occupation of high-value educational resources by users with non-real demands is inhibited, and authenticity of educational resource allocation and fairness of system operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of educational resource management, and more specifically, to a community educational resource scheduling system based on multi-dimensional demand matching. Background Art

[0002] In the current community education scheduling system, skills training courses have gradually become an important vehicle for supporting employment transitions, distributing social assistance, and motivating residents to continue learning. To improve system response efficiency and user engagement, most platforms have established data-driven matching mechanisms centered on registration priority, attendance clock-in records, and staged task completion rates. These mechanisms also enhance incentives through linkage with point-based reward systems and unemployment benefit policies. On the surface, this approach establishes criteria and evaluation benchmarks for resource allocation, enabling a basic level of supply-demand matching. However, in actual application, this mechanism suffers from a problem of distorted behavior. Some users, driven by external interests such as obtaining course points, employment subsidies, or government resume certification, frequently sign up for high-incentive courses. After successfully signing up, their behavior exhibits typical weak execution path characteristics, including repetitive idle attendance, periodic task avoidance, and interruptive course abandonment. These users often have "apparently complete" data traces in system records, making them difficult to identify by traditional filtering mechanisms based on single-point events. This leads to long-term occupation of educational resource quotas, seriously disrupting the teaching rhythm and resource matching fairness of the course. Furthermore, this behavior is pseudo-random at a statistical level and easily masked by existing threshold-based methods. For example, some users alternately complete task nodes to create the illusion of "period compliance," then rapidly sign up for other courses to continuously seek policy subsidies or accumulate community points, ultimately forming clusters of false activity within the system. This not only causes users with real needs to be passively delayed in ranking, but also causes the scheduling system to misassess course popularity and resource demand, resulting in structural resource squeeze. To sum up, the problem with the existing technology is that the current community education resource scheduling system lacks the ability to identify pseudo-learning behaviors and is unable to identify resource occupiers with non-learning goals, resulting in high-value resources being continuously consumed under seemingly high utilization rates and unable to be converted into real educational results. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a community education resource scheduling system based on multi-dimensional demand matching. By constructing a disturbance task to induce behavioral response, extracting behavioral characteristics and combining the motivation offset evaluation function, it realizes the identification of pseudo-learning behavior and dynamic adjustment of scheduling priority, thereby suppressing the long-term occupation of high-value education resources by users with non-real needs, and improving the authenticity of education resource allocation and the fairness of system operation.

[0004] To achieve the above-mentioned object, the present invention provides the following technical solutions: a community education resource scheduling system based on multi-dimensional demand matching, comprising a disturbance construction module, a collection module, an extraction module, an evaluation module, and a scheduling module; The perturbation construction module is used to construct a perturbation task sequence of the target course. The perturbation task sequence is composed of multiple perturbation tasks. Each perturbation task includes the task content of the target course, random incentive parameters and task triggering time. The collection module is used to collect behavioral data of users who have registered for the target course in the disturbance task sequence. The behavioral data includes task entry time, task completion status, task skip status and stimulus response time; the behavioral data is reorganized according to the task trigger time sequence to construct the user's task response sequence; The extraction module extracts several offset features based on the task response sequence, which are used to measure the consistency of user behavior. The offset features include task response delay value, task completion rate change amplitude, and incentive response intensity. The offset features are combined to construct a feature vector of user behavior. The evaluation module is used to input the feature vector into the motivation offset function, calculate the user's motivation offset value, measure the user's goal consistency under the perturbed task sequence through the motivation offset value, and compare the motivation offset value with a preset threshold; The scheduling module includes: when the motivation offset value exceeds a preset threshold, executing scheduling restrictions, the scheduling restrictions include lowering the user's scheduling priority for the incentive course, suspending their registration qualifications or activating additional verification, until the user's motivation offset value falls back to within the preset offset threshold and the scheduling restrictions are restored.

[0005] In a preferred embodiment, in the disturbance construction module, the task flow of the target course is structurally disassembled, and each task content in the task flow is extracted and marked as the first task. Task content of each task ,in , Indicates the total number of tasks; For each task content , set a random excitation parameter , and combined with the time window , construct activation function : ; in is the actual completion time, is the excitation attenuation coefficient; time window express the expected completion time; For each Introducing the perturbation time offset term , and reset the task trigger time for: ; Indicates the The perturbation offset of each task; Indicates that in the interval Uniform distribution on ; is the maximum disturbance amplitude; based on 、 and , integrated into perturbation tasks ; All disturbance tasks Arrange the tasks in the order of the original task flow to generate a perturbation task sequence: ; The disturbance task sequence It is embedded in the task execution process of the target course and replaces the original task set.

[0006] In a preferred embodiment, in the acquisition module, for each user who signs up for the target course, the disturbance task sequence in which the user participates is extracted. ; For each perturbation task , record the corresponding user's behavior data, including the task entry time , Task completion status , Task skip status , stimulus response time ; Based on behavioral data Constituting behavioral data units ; Based on task trigger time , for all behavioral data units Arrange in ascending order to obtain a behavioral data sequence sorted by time ; The behavioral data sequence and the corresponding task trigger time set Combination, building task response sequence .

[0007] In a preferred embodiment, the task entry time Expressed as: ; The task completion status Expressed as: ; ; The skip behavior state Expressed as: ; The stimulus response time Expressed as: ; The task entry time Indicates the The entry time of each task; Indicates task content The complexity of the task content The complexity includes the number of steps or interactions; The task completion status Indicates whether the task is completed. If Indicates the task completion status, otherwise ; Indicates the decay rate of the activation function value under time offset; is the actual completion time; Indicates the upper limit of the response time allowed for the task; in Indicates whether to skip the task. If Indicates that the user skipped the task, otherwise .

[0008] In a preferred embodiment, the task response delay value is calculated in the extraction module : ; in Indicates the The delay from triggering a task to actual response; is an exponential function; Calculate the change in task completion rate in the extraction module : ; Calculate stimulus response strength in the extraction module : ; in Indicates the interval of task duration The maximum value of the rate of change of the excitation function is selected; Represents the rate of change of the activation function; Represents the overall cumulative strength of the task incentive function; Three offset features are combined into a feature vector of user behavior in the extraction module: ; wherein represents the feature vector of user behavior.

[0009] In a preferred embodiment, a motivation offset function is constructed in the evaluation module: ; ; wherein represents the motivation offset value of the user ; represents the total number of perturbation tasks assigned to the user ; wherein the feature vector of the user is represented as , represents the average value of the task response delay value of the user to all perturbation tasks, in time; represents the maximum delay threshold value allowed in all perturbation tasks; represents the normalized delay value; represents the change range of the task completion rate of the user in the perturbation task sequence; represents the average value of the motivation response intensity of the user in all tasks; wherein represents the value of the motivation function of the th perturbation task assigned to the user at time ; represents sigmoid mapping on ; represents the integral of the motivation response from time 0 to the actual task termination time for each task; is the hyperbolic tangent function.

[0010] Technical effects and advantages of the present application: 1. The present application constructs a dynamic behavior trajectory and extracts behavior response features by introducing a perturbation task mechanism, and realizes automatic identification of pseudo-learning motivation under non-strong supervision conditions, thereby solving the problem of difficult identification of non-real learning intention users in existing scheduling systems, and the problem of false activity masking resource occupation, and ensuring relatively efficient allocation of resources to real demanders.

[0011] 2. By embedding incentive-response perturbation tasks into the course task flow, the present invention induces users to show differentiated responses at unexpected time nodes, thereby forming high-resolution behavioral trajectories that can be used to evaluate their behavioral consistency and motivation stability, breaking through the coarse-grained modeling limitations of traditional task data that only focus on completion or failure.

[0012] 3. By collecting and analyzing multi-dimensional data on disturbance task response time, completion status, and incentive sensitivity, a feature vector reflecting the degree of motivational deviation was constructed, enabling the system to establish a highly robust and irregular data discrimination channel, thereby improving the recognition rate and screening accuracy of potential resource disturbance behaviors.

[0013] 4. The motivation offset evaluation function adopts a nonlinear combination of multiple behavioral characteristics and constructs a dynamic threshold judgment strategy with a recovery mechanism. This enables the system to not only respond quickly to abnormal behavior, but also support behavioral state repair and strategy adjustment based on time evolution, enhancing system adaptability and strategy flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0016] Refer to the instruction manual Figure 1 , a community education resource scheduling system based on multi-dimensional demand matching according to an embodiment of the present invention includes a disturbance construction module, a collection module, an extraction module, an evaluation module, and a scheduling module; The perturbation construction module is used to construct a perturbation task sequence for the target course. The perturbation task sequence consists of multiple perturbation tasks. Each perturbation task includes the task content of the target course, random incentive parameters, and task trigger time. The perturbation task is embedded in the task flow of the target course and forms a non-fixed task execution path based on the perturbation task sequence. The collection module is used to collect behavioral data of users who have registered for the target course in the disturbance task sequence. The behavioral data includes task entry time, task completion status, task skip status and stimulus response time; the behavioral data is reorganized according to the task trigger time sequence to construct the user's task response sequence; The extraction module extracts several offset features based on the task response sequence, which are used to measure the consistency of user behavior. These offset features include task response delay value, task completion rate variation, and incentive response intensity. The offset features are combined to construct a feature vector of user behavior. This feature vector is used to quantify the stability of user behavior under the perturbed task sequence. The evaluation module is used to input the feature vector into the motivation offset function, calculate the user's motivation offset value, measure the user's goal consistency under the perturbed task sequence through the motivation offset value, and compare the motivation offset value with a preset threshold; The scheduling module includes: when the motivation offset value exceeds a preset threshold, executing scheduling restrictions, the scheduling restrictions include lowering the user's scheduling priority for high-motivation courses, suspending their registration qualifications or activating additional verification, until the user's motivation offset value falls back to within the preset offset threshold and the scheduling restrictions are restored.

[0017] It should be noted that in the formula structure involved in this solution, dimensionless terms can serve as proportionality or structural adjustment factors. When combined with quantities with units, they only play a numerical scaling role and do not introduce new physical dimensions. Therefore, they will not change or confuse the overall unit system of expression. This combination of "dimensionless terms and units" can be understood as a composite structural expression commonly used in mathematical and physical modeling, conforming to the principle of dimensional consistency and having a clear physical interpretation basis. Secondly, in the formula structure of this scheme, if multiple variables with different physical units are involved, including but not limited to time, mass or energy variables, their joint appearance is to express the collaborative modeling relationship of multiple physical mechanisms. Each variable can be formed into a unified structure through function mapping, ratio combination or normalization adjustment. The units and meanings are clear, and the overall expression conforms to the principle of dimensional consistency and the common formula of engineering modeling. Any constants, weights, adjustment factors, threshold parameters, and proportional coefficients involved in this solution are all adjustable control parameters for different application environments. Their values ​​depend on the target device configuration, data input characteristics, and performance optimization goals. During the implementation phase, they are set within a reasonable range through model verification, performance constraints, or engineering calibration. Although these parameters do not have preset unique values, they have clear adjustment logic and calculation paths and are part of the deterministic setting process in engineering implementation. The purpose of such setting is to ensure that the solution is both universally adaptable, reproducible, and operable, without affecting its technical clarity and feasibility. In the perturbation construction module, the task flow of the target course is structurally disassembled, and each task content in the task flow is extracted and marked as the first task. Task content of each task ,in , Indicates the total number of tasks; For each task content , set a random excitation parameter , and combined with the time window , construct activation function : ; in is the actual completion time, is the incentive attenuation coefficient, which is used to dynamically generate incentive feedback for different completion time points; in the value of the incentive attenuation coefficient, when the task needs to be completed at a certain time, When the higher the incentive is, the larger the value, so that exist If a looser completion time range is allowed to obtain effective incentives, the smaller value to slow down the excitation decay rate, so The size of reflects the importance the system places on “on-time completion” and should be determined by combining the course rhythm with the incentive strategy goals, through experience setting or historical behavior data fitting, and satisfying That's it; Respectively represent the minimum and maximum values ​​of the excitation parameters; time window express the expected completion time; For each Introducing the perturbation time offset term , and reset the task trigger time for: ; Indicates the The disturbance offset of a task is used to change the trigger time of the task; Indicates "subject to" a certain probability distribution; Indicates that in the interval Uniform distribution on the interval, that is, the perturbation offset is in this interval The probability of any value within is the same; The maximum disturbance amplitude is set by the system and is used to limit the range of disturbance time; the disturbance time offset term Overall representation The perturbation offset of each task is in the interval The value obtained by random uniform sampling within; based on 、 and , integrated into perturbation tasks ; All disturbance tasks Arrange the tasks in the order of the original task flow to generate a perturbation task sequence: ; The disturbance task sequence It is embedded in the task execution process of the target course and replaces the original task set.

[0018] In the acquisition module, for each user who signs up for the target course, the perturbation task sequence in which the user participates is extracted. ; For each perturbation task , record the corresponding user's behavior data, including the task entry time , Task completion status , Task skip status , stimulus response time ; Based on behavioral data Constituting behavioral data units ; Based on task trigger time , for all behavioral data units Arrange in ascending order to obtain a behavioral data sequence sorted by time ; The behavioral data sequence and the corresponding task trigger time set Combination, building task response sequence .

[0019] The task entry time Expressed as: ; The task completion status Expressed as: ; ; The skip behavior state Expressed as: ; The stimulus response time Expressed as: ; The task entry time Indicates the The entry time of each task; Indicates task content The complexity of the task content The complexity of includes the number of steps or interactions, where the number of interactions refers to the number of clear behavioral interactions between the user and the task system in the process of completing the disturbance task, and the number of steps refers to the minimum number of operation process nodes that the user needs to complete in sequence according to the task logic in the process of completing the disturbance task. Each node represents a clear execution step for the task to advance. In the expression of The larger the value, the faster the task entry response.

[0020] The task completion status Indicates whether the task is completed. If Indicates the task completion status, otherwise ; Indicates the decay rate of the incentive function value under time offset. It is used to indicate the rate at which the incentive function value decreases with the delay time after the user completes the task relative to the task trigger time. The rate at which the incentive function value decreases with the delay time means that the later the user completes the task, the faster or slower the incentive function value decreases. is the actual completion time; Indicates the upper limit of the response time allowed for the task; in Indicates whether to skip the task. If Indicates that the user skipped the task, otherwise ; The stimulus response time The expression is obtained by putting the task into the time With the activation function The inverse of the task execution cycle The sum of the internal integrals reflects the cumulative response delay caused by the decrease of incentives during the completion process. Therefore, the overall representation is the response time when the incentive actually takes effect after the user completes the task under low incentive perception. The incentive function The value of reflects the intensity of the incentive.

[0021] Calculate task response delay value in the extraction module : ; in Indicates the The delay from triggering a task to actual response; is an exponential function; It is used to reflect the "delay penalty coefficient" of the task under low motivation state, that is, the smaller the motivation, the lower the tolerance for response delay. The overall reflection of the user's "weighted delay behavior" under the influence of incentives; Calculate the change in task completion rate in the extraction module : ; In the formula of , the change amplitude of the completion state of the task in the disturbance task sequence is calculated, wherein represents the completion state of the i-th task, and the fluctuation degree of the completion rate of the user behavior under the disturbance sequence is expressed by calculating the square of the difference between the completion states of two adjacent tasks and taking the average; if the completion state frequently changes, is larger, and vice versa, which reflects the stability of the user task completion behavior; if , it is indicated that the completion rate does not change, the contribution to the overall change amplitude is zero, and the behavior in this stage is stable. In the extraction module, the intensity of the incentive response is calculated : ; ; Among them represents the maximum value of the change rate of the incentive function selected in the interval of the task duration; represents the change rate of the incentive function; represents the overall cumulative intensity of the task incentive function; the product of the two in the calculation process represents the coupling degree of the maximum incentive response rate and the overall incentive perception, which is used to reflect the driving effect of the incentive on the user behavior in the time domain; In the extraction module, three offset features are combined into a feature vector of the user behavior: ; ; Among them represents the feature vector of the user behavior.

[0022] In the evaluation module, a motivation offset function is constructed: ; ; Among them represents the motivation offset value of the user , is the final evaluation result, which is used to measure the consistency degree of the user to the target behavior under the disturbance task sequence; represents the total number of the disturbance tasks assigned to the user , that is, the number of tasks completed by the user; Among them, the feature vector of the user is represented as , represents the user The average value of the task response delay for all perturbation tasks, in time; represents the maximum delay threshold allowed in all perturbation tasks, which is used to normalize the time delay; Represents the normalized delay value, which is used to convert the unit into dimensionless, making it easier to measure in a unified manner with other indicators; Represents a user The magnitude of the change in task completion rate in the disturbed task sequence, that is, the degree of fluctuation in completion quality, is dimensionless. Represents a user The average of the stimulus response strengths across all tasks, where and The units of are dimensionless because The unit of is dimensionless "points" or "excitation amplitude"; in Indicates time Next, Assigned to users The incentive function of the perturbation task The value of Express Perform sigmoid mapping to normalize its value to the interval (0, 1) to reflect the "sensitivity" or "instant feedback strength" of the response; Represents the time from time 0 to the actual task termination time for each task The stimulus responses between are integrated to calculate the overall response; Indicates to users The stimulus response integral values ​​of all perturbation tasks are averaged to represent the “mean” of the overall stimulus response; is the hyperbolic tangent function. In the above formula, the hyperbolic tangent function represents projecting the response mean to the interval (1, 1), strengthening the nonlinear discrimination ability, making the high response more concentrated and the low response more compressed.

[0023] It should be noted that the development of this solution stems from an in-depth analysis of the shortcomings of the current community education resource scheduling system in identifying and responding to dynamic changes in user motivation. In particular, the solution introduces the "perturbation task sequence" mechanism as an innovative entry point to address the key issue of inconsistent behavioral behavior among users participating in educational tasks, which cannot be promptly identified, responded to, or used to adjust scheduling strategies. The disturbance task sequence is composed of a plurality of disturbance tasks containing target course task content, incentive parameters and trigger time. The sequence is not fixed and static, but is formed by adding a disturbance amount in a set time offset interval to the original task flow to perform random disturbance, so that the specific task sequence and incentive feedback rhythm faced by each user when completing the course task have a certain uncertainty, thereby helping to expose the behavior stability and motivation persistence of the user under sudden or changing conditions; the disturbance construction module structurally disassembles the original task flow and configures a dynamic incentive feedback function for each task, and the decay degree of the incentive feedback represents the response preference setting for the completion time; Then the maximum disturbance amplitude limit is introduced to control the variation range of the disturbance time, relatively avoiding causing course logic confusion; all disturbance tasks are uniformly embedded in the course task flow to form a new schedulable execution path, and this process ensures the nonlinear expression of the influence of the incentive on the task behavior and the generation of the behavior profile at the structural level; The collection module collects behavior data for each user around the above disturbance task sequence, including multi-dimensional information such as whether the task is entered on time, whether it is completed, whether it is skipped, and the time of responding to the incentive, and reorganizes the data units in the order of the actual trigger time of the disturbance tasks to form a task response sequence with time process characteristics, ensuring that the behavior data has complete and traceable time sequence under the disturbance background; On this basis, the extraction module constructs an offset feature vector by calculating three indexes of response delay, completion rate fluctuation and incentive response strength. These feature dimensions respectively describe the behavior regularity of the user in the task sequence from three angles of time reaction of task execution, behavior stability and incentive perception response ability; The response delay index reflects the entering speed of the user under low incentive situation; the completion rate fluctuation expresses the consistent change trend of the behavior between tasks; and the incentive response strength reflects the coupling degree of the incentive strength on the behavior completion effect; after the three indexes are combined into a feature vector, they are input into the motivation offset function constructed by the evaluation module to output the motivation offset value of the user under the disturbance task background; the motivation offset function processes the normalized values of various features uniformly and embeds a nonlinear mapping mechanism to distinguish the behavior difference amplitude under different motivation states, thereby ensuring that the offset value has strong discriminant ability in numerical value; The scheduling module sets a behavior response mechanism based on the judgment result of the above motivation offset value: when the user motivation offset value exceeds the preset threshold value, a series of restrictive response measures including scheduling priority reduction, registration restriction or additional verification will be triggered, and the module does not use a one-way freezing mode, but automatically removes the restrictions when the motivation offset value recovers to within the threshold value, so that it has dynamic regulation and self-recovery ability.

[0024] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A community education resource scheduling system based on multi-dimensional demand matching, comprising a disturbance construction module, a collection module, an extraction module, an evaluation module, and a scheduling module, characterized by: The perturbation construction module is used to construct a perturbation task sequence of the target course. The perturbation task sequence is composed of multiple perturbation tasks. Each perturbation task includes the task content of the target course, random incentive parameters and task triggering time. The collection module is used to collect behavioral data of users who have registered for the target course in the disturbance task sequence. The behavioral data includes task entry time, task completion status, task skip status and stimulus response time; the behavioral data is reorganized according to the task trigger time sequence to construct the user's task response sequence; The extraction module extracts several offset features based on the task response sequence, which are used to measure the consistency of user behavior. The offset features include task response delay value, task completion rate change amplitude, and incentive response intensity. The offset features are combined to construct a feature vector of user behavior. The evaluation module is used to input the feature vector into the motivation offset function, calculate the user's motivation offset value, measure the user's goal consistency under the perturbed task sequence through the motivation offset value, and compare the motivation offset value with a preset threshold; The scheduling module includes: when the motivation offset value exceeds a preset threshold, executing scheduling restrictions, the scheduling restrictions include lowering the user's scheduling priority for the incentive course, suspending their registration qualifications or activating additional verification, until the user's motivation offset value falls back to within the preset offset threshold and the scheduling restrictions are restored.

2. A community education resource scheduling system based on multi-dimensional demand matching according to claim 1, characterized in that: In the perturbation construction module, the task flow of the target course is structurally disassembled, and each task content in the task flow is extracted and marked as the first task. Task content of each task ,in , Indicates the total number of tasks; For each task content , set a random excitation parameter , and combined with the time window , construct activation function : ； in is the actual completion time, is the excitation attenuation coefficient; time window express the expected completion time; Respectively represent the minimum and maximum values ​​of the excitation parameters; For each Introducing the perturbation time offset term , and reset the task trigger time for: ; Indicates the The perturbation offset of each task; Indicates that in the interval Uniform distribution on ; is the maximum disturbance amplitude; based on 、 and , integrated into perturbation tasks ; All disturbance tasks Arrange the tasks in the order of the original task flow to generate a perturbation task sequence: ; The disturbance task sequence It is embedded in the task execution process of the target course and replaces the original task set.

3. A community education resource scheduling system based on multi-dimensional demand matching according to claim 2, characterized in that: In the acquisition module, for each user who signs up for the target course, the perturbation task sequence in which the user participates is extracted. ; For each perturbation task , record the corresponding user's behavior data, including the task entry time , Task completion status , Task skip status , stimulus response time ; Based on behavioral data Constituting behavioral data units ; Based on task trigger time , for all behavioral data units Arrange in ascending order to obtain a behavioral data sequence sorted by time ; The behavioral data sequence and the corresponding task trigger time set Combination, building task response sequence .

4. The community education resource scheduling system based on multi-dimensional demand matching according to claim 3 is characterized by: The task entry time Expressed as: ； The task completion status Expressed as: ； ； The skip behavior state Expressed as: ； The stimulus response time Expressed as: ； The task entry time Indicates the The entry time of each task; Indicates task content The complexity of the task content The complexity includes the number of steps or interactions; The task completion status Indicates whether the task is completed. If Indicates the task completion status, otherwise ; Indicates the decay rate of the activation function value under time offset; is the actual completion time; Indicates the upper limit of the response time allowed for the task; in Indicates whether to skip the task. If Indicates that the user skipped the task, otherwise .

5. The community education resource scheduling system based on multi-dimensional demand matching according to claim 4 is characterized by: Calculate task response delay value in the extraction module : ； in Indicates the The delay from triggering a task to actual response; is an exponential function; Calculate the change in task completion rate in the extraction module : ； Calculate stimulus response strength in the extraction module : ； in Indicates the interval of task duration The maximum value of the rate of change of the excitation function is selected; Represents the rate of change of the activation function; Represents the overall cumulative strength of the task incentive function; In the extraction module, the three offset features are combined into a feature vector of user behavior: ； in A feature vector representing user behavior.

6. The community education resource scheduling system based on multi-dimensional demand matching according to claim 5 is characterized by: Construct the motivation offset function in the evaluation module: ； ； in Represents a user Motivation offset value; Indicates that it is assigned to the user The perturbation task the total number of; Among them users The eigenvector of , Represents a user The average value of the task response delay for all perturbation tasks, in time; Indicates the maximum delay threshold allowed in all perturbation tasks; Indicates the normalized delay value; Represents a user The magnitude of the change in task completion rate during the perturbed task sequence; Represents a user The average of the stimulus response strengths across all tasks; in Indicates time Next, Assigned to users The activation function of the perturbation task The value of Express Perform sigmoid mapping; Represents the time from time 0 to the actual task termination time for each task Integrate the stimulus responses between is the hyperbolic tangent function.

Images