A smart campus task collaboration method and system for multi-group service optimization

Abstract

This invention provides a smart campus task collaboration method and system for multi-group service optimization, belonging to the field of campus service management technology. The method retrieves historical service logs, allocates storage nodes according to service processes to generate pre- and post-collaboration datasets; determines the group collaboration status based on the datasets, and constructs a dedicated task measurement set and group behavior feature set; quantifies cross-group task collaboration priorities through dual-evaluation modality labeling; and generates a group-task collaboration set through iterative computation, using segmentation coefficients (cohesion + separation) for selection and optimization. The system includes modules for data collection and storage, task and feature construction, collaboration priority quantification, and collaboration adaptation analysis and optimization. This invention solves the problems of insufficient precise adaptation and ambiguous priority quantification in existing multi-group collaboration technologies, achieving targeted optimization of service resources, improving task collaboration efficiency and group satisfaction, and providing an efficient solution for differentiated multi-group services in smart campuses.

Description

Technical Field

[0001] This invention relates to the field of campus service management technology, and more specifically, to a smart campus task collaboration method and system for optimizing services for multiple groups. Background Technology

[0002] With the deepening of smart campus construction, campus service scenarios are becoming increasingly diversified. The service needs of various groups, including students, teachers, administrative staff, and logistics support teams, are showing differentiated and complex characteristics. Task collaboration has become a core element in improving the efficiency of campus service management. Although existing smart campus service systems have achieved basic task allocation and execution functions, there are still many technical bottlenecks in multi-group collaboration and adaptation, making it difficult to meet the needs of refined management.

[0003] First, existing technologies lack a systematic design for data storage and retrieval. They often mix service requirements and task information from all groups, failing to allocate dedicated storage nodes according to service processes. This leads to confusion in task execution data before and after collaboration, making it difficult to quickly distinguish the task collaboration status of different groups, thus affecting the accuracy of subsequent feature extraction and priority determination. Second, existing collaboration methods do not differentiate between groups that have implemented collaboration, uniformly using a single task measurement standard. This ignores the differences in basic needs between non-collaborating groups and optimization needs between collaborating groups, resulting in a lack of specificity in collaboration solutions. Third, the quantification of cross-group task collaboration priorities is rather crude, relying heavily on single-dimensional behavioral data without establishing a mapping between task measurement sets and group behavioral feature sets. This fails to accurately reflect the collaborative value of different service tasks to different groups, leading to a waste of collaboration resources.

[0004] Meanwhile, existing technologies, when generating group-task collaboration sets, can only achieve collaboration matching between some groups, and the screening mechanisms mostly use a single threshold judgment, failing to consider the cohesion and separation of collaboration adaptation similarity. This results in poor adaptability and high redundancy in the collaboration sets. Furthermore, existing systems struggle to dynamically adapt to changes in group needs. When the frequency of group behavior or the type of service task changes, the collaboration scheme cannot respond and optimize quickly, further reducing the flexibility and efficiency of campus services. These problems, combined, lead to low efficiency in multi-group task collaboration and unreasonable resource allocation in smart campuses, making it difficult to meet the personalized service needs of each group and hindering the improvement of smart campus service management.

[0005] For example, in campus psychological service scenarios, there are significant differences in the consultation appointment needs of students, the crisis intervention collaboration needs of counselors, and the follow-up needs of psychological counselors. Existing technologies cannot build dedicated data systems for the collaboration status of each group (e.g., no collaboration implemented for students, but collaboration implemented for counselors), nor can they quantify the priority of tasks such as "psychological assessment collaboration" and "crisis intervention linkage," leading to resources being tilted towards low-value tasks and high-urgency collaboration needs not being responded to in a timely manner. These problems seriously restrict the optimization and upgrading of multi-group services in smart campuses. Therefore, there is an urgent need for a task collaboration method and system that can achieve accurate adaptation to multiple groups, precise quantification of priorities, and dynamic optimization of collaboration solutions. Summary of the Invention

[0006] This invention addresses the technical problems existing in current smart campus multi-group task collaboration, such as insufficient precise adaptation, ambiguous priority quantification, and single optimization mechanism. It provides a smart campus task collaboration method and system for multi-group service optimization. Through the full-process technical logic of data hierarchical collection and storage, differentiated construction of task and behavioral characteristics, dual evaluation modality quantification, iterative optimization, and segmentation coefficient screening, it achieves the technical effect of targeted resource allocation and efficient collaboration for multi-group services, and is adaptable to various full-process scenarios such as campus psychological services, teaching management, and logistical support.

[0007] In view of the above-mentioned technical problems, the present invention provides a smart campus task collaboration method and system for multi-group service optimization.

[0008] In a first aspect, the present invention provides a smart campus task collaboration method for multi-group service optimization, the method comprising:

[0009] Step S1: After user authorization, retrieve the multi-group service request records and task information from the historical service logs of the smart campus service platform, allocate corresponding storage nodes for each service process, extract information from each storage node, and generate a pre-collaboration task execution dataset and a post-collaboration task execution dataset.

[0010] Step S2: Based on the task execution dataset before collaboration and the task execution dataset after collaboration, determine whether collaboration is implemented for the tasks of each group, construct the corresponding task measurement set, and at the same time obtain the frequency of each group's participation in task collaboration under each service process to generate the corresponding group behavior feature set.

[0011] Step S3: Based on the constructed task measurement set and group behavior feature set, establish a dual evaluation modality label to quantify the task collaboration priority of service tasks among different groups;

[0012] Step S4: Based on the quantified task collaboration priority, evaluate the group-task collaboration adaptation similarity between different groups, generate the group-task collaboration set corresponding to each group through iterative calculation, calculate the segmentation coefficient of each collaboration adaptation similarity, and filter and optimize by combining the preset segmentation coefficient threshold to obtain the final group-task collaboration set.

[0013] Preferably, the specific implementation process of step S1 includes:

[0014] After user authorization, all multi-group service request records and task information are retrieved from the historical service logs of the smart campus service platform. The multi-group service request records and task information contain all information about group service tasks and task execution status. All information includes the service tasks selected by the multi-group and the frequency of group participation in task collaboration under the service tasks.

[0015] Based on the entire process of smart campus services, a storage node is allocated to each service process to store the service demand records and task information of the multiple groups.

[0016] The service requirement records and task information of the multi-groups before task collaboration are implemented in each storage node are obtained to generate a task execution dataset before collaboration; the service requirement records and task information of the multi-groups after task collaboration are implemented in each storage node are obtained to generate a task execution dataset after collaboration; and both the task execution dataset before collaboration and the task execution dataset after collaboration record service tasks selected by multiple groups.

[0017] Preferably, the specific implementation process of step S2 includes:

[0018] Based on the pre-cooperation task execution dataset P and the post-cooperation task execution dataset Q generated by group k, if the pre-cooperation task execution dataset P is equal to the post-cooperation task execution dataset Q, it is determined that no cooperation has been implemented for the tasks of group k, and an initial task measurement set for group k is constructed. If the task execution dataset P before collaboration is not equal to the task execution dataset Q after collaboration, then it is determined that collaboration has been implemented for the tasks of group k, and an optimized task measurement set for group k is constructed. ;

[0019] Based on the pre-collaboration and post-collaboration task execution datasets generated by group k, for cases where collaboration is not implemented, the frequency of group k's participation in task collaboration under each service process is obtained to generate a basic group behavior feature set of group k, denoted as . For cases where collaboration has already been implemented, the frequency of group k's participation in task collaboration under each service process is obtained to generate a collaborative group behavior feature set for group k, denoted as... ,in, This represents the frequency of group k's participation in task collaboration recorded in the nth storage node, where N represents the total number of storage nodes.

[0020] Preferably, the specific implementation process of step S3 includes:

[0021] Based on the initial task measurement set, the optimized task measurement set, the basic group behavior feature set, and the collaborative group behavior feature set, a dual-evaluation modality labeling system for tasks is constructed, with the first evaluation modality labeling being... The second evaluation mode is labeled as Where a and b are group numbers, and a ≠ b. Let be the initial task measurement set for group a. For group a, the basic set of group behavioral characteristics. For the optimization task measurement set of group b, Let b be the set of characteristics of the coordinated group behavior of group b.

[0022] For any p-th service task If service task Simultaneously present in the initial task measurement set and optimize task measurement sets In the middle, the service tasks are quantified. Regarding the task coordination priority between group a and group b In the formula, This indicates that it originates from the basic group behavior feature set. frequency of behavior This indicates that the characteristics originate from the collaborative group behavior feature set. frequency of behavior Basic group behavior feature set With the set of characteristics of collaborative group behavior The Euclidean distance function is used to quantize service tasks. Regarding the task coordination priority between group a and group b; if the service task They do not exist simultaneously in the initial task measurement set. and optimize task measurement sets In the middle, then order .

[0023] Preferably, the specific implementation process of step S4 includes:

[0024] Based on task collaboration priorities, the similarity of group-task collaboration adaptation between group a and group b is evaluated. In the formula, Indicates the total number of pre-set service tasks;

[0025] A group-task collaboration analysis iterative model is constructed. In the first iteration, b = b + 1 is set and substituted into the collaboration adaptation similarity formula to obtain the collaboration adaptation similarity between group a and every other group except group a. A group-task collaboration set is then generated, denoted as […]. In the second iteration, let a = a+1, return to the first iteration, obtain the co-adaptation similarity between group a+1 and every group other than group a+1, and generate the group-task co-adaptation set. ;

[0026] Collect all group-task collaboration sets, and cluster each group-task collaboration set as a collaboration scheme cluster; within the group-task collaboration set... In the process, arbitrarily select a co-adaptation similarity. Analyze the group-task splitting coefficient:

[0027] ;

[0028] In the formula, Represents the group-task splitting coefficient. Cohesion, representing the similarity of co-fitting, Separability, representing the similarity of co-adaptation, Representing a group-task collaborative set The total number of collaborative adaptation similarities included. Representing a group-task collaborative set The total number of collaborative adaptation similarities included;

[0029] Preset group-task segmentation coefficient threshold; if the group-task segmentation coefficient... If the similarity is greater than or equal to the group-task segmentation coefficient threshold, the corresponding collaborative adaptation similarity is retained; otherwise, it is discarded, and the optimized group-task collaborative set is updated and output.

[0030] Secondly, the present invention also provides a smart campus task collaboration system optimized for multi-group services, the system comprising:

[0031] The module includes a data acquisition and storage module, a task and feature construction module, a collaborative priority quantification module, and a collaborative adaptation analysis and optimization module.

[0032] The data acquisition and storage module is used to retrieve multi-group service demand records and task information from the historical service logs of the smart campus service platform after user authorization. It allocates corresponding storage nodes for each service process, extracts information from each storage node, and generates task execution datasets before and after collaboration.

[0033] The task and feature construction module, based on the pre-collaboration task execution dataset and the post-collaboration task execution dataset, determines whether collaboration is implemented for tasks of each group, constructs the corresponding task measurement set, and obtains the frequency of each group's participation in task collaboration under each service process, generating the corresponding group behavior feature set.

[0034] The collaborative priority quantification module establishes a dual evaluation modality label based on the constructed task measurement set and group behavior feature set to quantify the task collaborative priority of service tasks among different groups;

[0035] The collaborative adaptation analysis and optimization module evaluates the similarity of group-task collaborative adaptation among different groups based on the quantified task collaboration priority. It generates group-task collaboration sets corresponding to each group through iterative calculation, calculates the segmentation coefficient of each collaborative adaptation similarity, and combines the preset segmentation coefficient threshold for screening and optimization to obtain the final group-task collaboration set.

[0036] Preferably, the data acquisition and storage module includes a user authorization unit, a historical information retrieval unit, a storage node allocation unit, and a dataset generation unit;

[0037] The user authorization unit is used to obtain user authorization to retrieve historical service log information;

[0038] The historical information retrieval unit is used to retrieve records of service requests and task information from multiple groups from the historical service logs of the smart campus service platform.

[0039] The storage node allocation unit is used to allocate dedicated storage nodes for each service process in the entire smart campus service process, and to store the corresponding multi-group service demand records and task information.

[0040] The dataset generation unit is used to extract relevant information from each storage node before and after task collaboration, and generate task execution datasets before and after collaboration, respectively.

[0041] Preferably, the task and feature construction module includes a task measurement set construction unit and a group behavior feature set generation unit;

[0042] The task measurement set construction unit is used to compare the task execution dataset before collaboration with the task execution dataset after collaboration to determine whether the task has implemented collaboration. It constructs an initial task measurement set for groups that have not implemented collaboration and an optimized task measurement set for groups that have implemented collaboration.

[0043] The group behavior feature set generation unit is used to obtain the frequency of task collaboration behavior of the group under each service process for groups that have not implemented collaboration, and generate a basic group behavior feature set; and for groups that have implemented collaboration, it obtains the frequency of task collaboration behavior of the group under each service process, and generates a collaborative group behavior feature set.

[0044] Preferably, the collaborative priority quantification module includes an evaluation modality labeling construction unit and a collaborative priority calculation unit;

[0045] The evaluation modality labeling construction unit establishes two types of evaluation modality labels based on the initial task measurement set, the optimized task measurement set, the basic group behavior feature set, and the collaborative group behavior feature set, respectively associating them with the corresponding task measurement set and the group behavior feature set.

[0046] The collaboration priority calculation unit is used to identify service tasks that exist simultaneously in different task measurement sets, and quantifies the collaboration priority of tasks by calculating the correlation parameters of the frequency of related behaviors.

[0047] Preferably, the collaborative adaptation analysis and optimization module includes a collaborative adaptation similarity evaluation unit, a group-task collaborative set generation unit, a segmentation coefficient calculation unit, and a collaborative set optimization unit;

[0048] The collaborative adaptation similarity evaluation unit is used to calculate the group-task collaborative adaptation similarity between different groups based on the task collaboration priority and the preset total number of service tasks.

[0049] The group-task collaboration set generation unit is used to generate group-task collaboration sets corresponding to each group and other groups in turn through iterative calculations.

[0050] The segmentation coefficient calculation unit is used to calculate the cohesion and separation of the similarity of each collaboration in the group-task collaboration set, and obtain the corresponding group-task segmentation coefficient.

[0051] The collaborative set optimization unit is used to filter and retain the collaborative adaptation similarity that meets the requirements based on the preset group-task segmentation coefficient threshold, and update and output the optimized group-task collaborative set.

[0052] One or more technical solutions provided in this invention have at least the following technical effects or advantages:

[0053] This invention, "allocating storage nodes according to service processes," not only achieves structured management of task data but also differentiates the construction of task measurement sets (initial / optimized) and group behavior feature sets (basic / collaborative). By combining dual evaluation modality labeling to establish a correlation, it can accurately capture the differences in the needs of groups under different collaborative states, which helps to improve the accuracy of group-task collaborative adaptation.

[0054] The closed-loop logic of “Euclidean distance quantification priority + segmentation coefficient (cohesion + separation) screening” helps to solve the problems of ambiguous priority quantification and single optimization mechanism in existing technologies. The objectivity of priority quantification and the optimization of collaborative solutions are improved. While avoiding resource allocation imbalance, the group-task collaboration set is generated through iterative calculation, which can dynamically adapt to changes in the number of multiple groups and iterative needs. The adaptability can be extended to various full-process services on campus.

[0055] The above description is merely an overview of the technical solution of the present invention. To better understand the technical means of the present invention and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of the present invention more apparent, specific embodiments of the present invention 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 the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily apparent from the following description. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in this invention 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.

[0057] Figure 1 This is a schematic diagram illustrating the steps of a smart campus task collaboration method for multi-group service optimization according to the present invention. Detailed Implementation

[0058] This invention provides a smart campus task collaboration method and system for multi-group service optimization. Its core principle is based on a closed-loop logic of "data-driven - feature mining - priority quantification - precise optimization." First, by allocating storage nodes according to the service process, structured storage and efficient extraction of task data before and after collaboration are achieved. Second, by comparing datasets before and after collaboration, the group collaboration status is determined, and task measurement sets and group behavior feature sets are constructed differently to accurately capture the collaboration needs and behavioral patterns of different groups. Third, the association between the task measurement set and the behavior feature set is established through dual-evaluation modality labeling, and Euclidean distance is used to quantify cross-group task collaboration priorities, achieving objectivity and data-driven prioritization. Finally, group-task collaboration sets are generated through iterative calculations, and a segmentation coefficient is constructed by combining cohesion (similarity within the collaboration set) and separation (difference between different collaboration sets) to select the optimal collaboration scheme, forming a closed-loop technology process.

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, and not all of them.

[0060] Example 1, please refer to Figure 1 This paper provides a smart campus task collaboration method for optimizing services for multiple groups. In this embodiment, it is described in detail in conjunction with the whole process scenario of campus psychological work (the service process includes: appointment consultation, psychological assessment, crisis intervention, and follow-up). The groups include student group (a=1), counselor group (a=2), psychological teacher group (a=3), and parent group (a=4). The total number of service processes corresponds to storage nodes N=4, the total number of service tasks is preset to Ptotal=10, and the group-task splitting coefficient threshold is 0.6.

[0061] The method includes:

[0062] Step S1: After user authorization, retrieve the multi-group service request records and task information from the historical service logs of the smart campus service platform, allocate corresponding storage nodes for each service process, extract information from each storage node, and generate a pre-collaboration task execution dataset and a post-collaboration task execution dataset.

[0063] For example, after user authorization, all multi-group service request records and task information are retrieved from the historical service logs of the smart campus service platform. The multi-group service request records and task information contain all information about group service tasks and task execution status. All information includes the service tasks selected by the multi-group and the frequency of group participation in task collaboration under the service tasks.

[0064] Based on the entire process of smart campus services, a storage node is allocated to each service process to store service demand records and task information of multiple groups;

[0065] The system retrieves multi-group service requirement records and task information from each storage node before task collaboration is implemented, in order to generate a pre-collaboration task execution dataset; it also retrieves multi-group service requirement records and task information from each storage node after task collaboration is implemented, in order to generate a post-collaboration task execution dataset; and both the pre-collaboration task execution dataset and the post-collaboration task execution dataset record service tasks selected by multiple groups.

[0066] For example, service demand records and task information for four groups are retrieved from the historical logs of the smart campus psychological service platform, including appointment consultation records for students (behavior frequency f1=120 times), crisis intervention collaboration records for counselors (f2=85 times), follow-up records for psychological teachers (f3=90 times), and communication collaboration records for parents (f4=60 times). Four storage nodes (nodes 1-4) are allocated according to the four service processes of "appointment consultation, psychological assessment, crisis intervention, and follow-up", and the information of the corresponding process is stored respectively. Data set P (containing 10 service tasks) is generated by extracting the information before collaboration of each node, and data set Q (containing 8 newly added collaboration tasks) is generated by extracting the information after collaboration.

[0067] Step S2: Based on the task execution dataset before collaboration and the task execution dataset after collaboration, determine whether collaboration is implemented for the tasks of each group, construct the corresponding task measurement set, and at the same time obtain the frequency of each group's participation in task collaboration under each service process to generate the corresponding group behavior feature set.

[0068] For example, based on the pre-cooperation task execution dataset P and the post-cooperation task execution dataset Q generated by group k, if the pre-cooperation task execution dataset P is equal to the post-cooperation task execution dataset Q, it is determined that no cooperation has been implemented for the tasks of group k, and an initial task measurement set for group k is constructed. (Including 10 tasks such as appointment consultation and psychological assessment); If the task execution dataset P before collaboration is not equal to the task execution dataset Q after collaboration, then it is determined that collaboration has been implemented for the tasks of group k, and an optimized task measurement set for group k is constructed. (Including 15 tasks such as crisis intervention and cross-group collaboration);

[0069] Based on the pre-collaboration and post-collaboration task execution datasets generated by group k, for cases where collaboration is not implemented, the frequency of group k's participation in task collaboration under each service process is obtained to generate a basic group behavior feature set of group k, denoted as . (Including {f1=120 (node ​​1), f2=80 (node ​​2), f3=50 (node ​​3), f4=30 (node ​​4)}); For cases where collaboration has been implemented, obtain the frequency of group k's participation in task collaboration under each service process to generate a collaborative group behavior feature set for group k, denoted as (Including {f1=85 (node ​​1), f2=70 (node ​​2), f3=95 (node ​​3), f4=65 (node ​​4)}), where, This represents the frequency of group k's participation in task collaboration recorded in the nth storage node, where N represents the total number of storage nodes.

[0070] Step S3: Based on the constructed task measurement set and group behavior feature set, establish a dual evaluation modality label to quantify the task collaboration priority of service tasks among different groups;

[0071] For example, based on the initial task measurement set, the optimized task measurement set, the basic group behavior feature set, and the collaborative group behavior feature set, a dual-evaluation modality label for the task is constructed, and the first evaluation modality label is... The second evaluation mode is labeled as Where a and b are group numbers, and a ≠ b. Let be the initial task measurement set for group a. For group a, the basic set of group behavioral characteristics. For the optimization task measurement set of group b, Let b be the set of characteristics of the coordinated group behavior of group b.

[0072] For any p-th service task If service task Simultaneously present in the initial task measurement set and optimize task measurement sets In the middle, the service tasks are quantified. Regarding the task coordination priority between group a and group b In the formula, This indicates that it originates from the basic group behavior feature set. frequency of behavior This indicates that the characteristics originate from the collaborative group behavior feature set. frequency of behavior Basic group behavior feature set With the set of characteristics of collaborative group behavior The Euclidean distance function is used to quantize service tasks. Regarding the task coordination priority between group a and group b; if the service task They do not exist simultaneously in the initial task measurement set. and optimize task measurement sets In the middle, then order ;

[0073] It should be noted that the storage nodes correspond to processes such as "appointment consultation and psychological assessment" in campus psychological services. The frequency of a group's behavior at each node (e.g., the frequency of students at the appointment consultation node f1=120 times) directly reflects the group's participation in and urgency of needs for the tasks within that process; higher frequency indicates higher collaborative value. The task measurement set is bound to the group behavior feature set, and the priority is calculated only for co-occurring tasks that "exist in both the initial measurement set and the optimized measurement set". These tasks are the core intersection needs of different groups, and the matching degree of the intersection needs is quantified by the frequency of behavior.

[0074] Step S4: Based on the quantified task collaboration priority, evaluate the group-task collaboration adaptation similarity between different groups, generate the group-task collaboration set corresponding to each group through iterative calculation, calculate the segmentation coefficient of each collaboration adaptation similarity, and combine the preset segmentation coefficient threshold for screening and optimization to obtain the final group-task collaboration set.

[0075] For example, based on task collaboration priorities, the similarity of group-task collaboration adaptation between group a and group b is evaluated. In the formula, Indicates the total number of pre-set service tasks;

[0076] A group-task collaboration analysis iterative model is constructed. In the first iteration, b = b + 1 is set and substituted into the collaboration adaptation similarity formula to obtain the collaboration adaptation similarity between group a and every other group except group a. A group-task collaboration set is then generated, denoted as […]. In the second iteration, let a = a+1, return to the first iteration, obtain the co-adaptation similarity between group a+1 and every group other than group a+1, and generate the group-task co-adaptation set. ;

[0077] Collect all group-task collaboration sets, and cluster each group-task collaboration set as a collaboration scheme cluster; within the group-task collaboration set... In the process, arbitrarily select a co-adaptation similarity. Analyze the group-task splitting coefficient:

[0078] ;

[0079] In the formula, Represents the group-task splitting coefficient. Cohesion, representing the similarity of co-fitting, Separability, representing the similarity of co-adaptation, Representing a group-task collaborative set The total number of collaborative adaptation similarities included. Representing a group-task collaborative set The total number of collaborative adaptation similarities included;

[0080] Preset group-task segmentation coefficient threshold; if the group-task segmentation coefficient... If the similarity is greater than or equal to the group-task segmentation coefficient threshold, the corresponding collaborative adaptation similarity is retained; otherwise, it is discarded, and the optimized group-task collaborative set is updated and output.

[0081] For example, through iterative operations, the synergy set R(1)={E(1,2)=637.5, E(1,3)=580, E(1,4)=420} of group 1 and the synergy set R(2)={E(2,1)=637.5, E(2,3)=720, E(2,4)=510} of group 2 are generated;

[0082] Segmentation coefficient:

[0083] C[E(1,2)]=[|637.5-580|+|637.5-420|] / (3-1)=(57.5+217.5) / 2=13 7.5; D[E(1,2)]=[|637.5-720|+|637.5-510|] / 3=(82.5+127.5) / 3=70;

[0084] Y[E(1,2)]=|70-137.5| / max(70,137.5)=67.5 / 137.5≈0.49<0.6, so this co-fit similarity is discarded;

[0085] It should be noted that the collaboration set R(a) includes the adaptation similarity of group a with all other groups (e.g., R(1) = {E(1,2), E(1,3), E(1,4)}). Cohesion is measured by the mean difference between each adaptation similarity in the set and the target value, which measures the "internal difference" of the collaboration relationship between the same group and different groups. The smaller the difference, the lower the cohesion, indicating that the collaboration needs of the group are more concentrated. R(a) and R(a+1) correspond to the collaboration sets of groups a and a+1, respectively. Separation is measured by the mean difference between the target adaptation similarity and all values ​​in another collaboration set, which measures the "external difference" of the collaboration relationship between different groups. The larger the difference, the higher the separation, indicating that the collaboration needs of different groups are clearer. The segmentation coefficient (Y) is a comprehensive derivation of cohesion and separation. Collaboration adaptation similarity with Y ≥ 0.6 is retained, essentially because this coefficient can measure "whether the collaboration relationship is of high quality". A high-quality collaboration relationship needs to meet the requirements of "internal consistency and external clarity" to ensure that the output group-task collaboration scheme is accurate and efficient.

[0086] Example 2 provides a smart campus task collaboration system optimized for multiple user groups. The system includes the following steps:

[0087] The module includes a data acquisition and storage module, a task and feature construction module, a collaborative priority quantification module, and a collaborative adaptation analysis and optimization module.

[0088] The data acquisition and storage module is used to retrieve multi-group service demand records and task information from the historical service logs of the smart campus service platform after user authorization. It allocates corresponding storage nodes for each service process, extracts information from each storage node, and generates task execution datasets before and after collaboration.

[0089] Specifically, the data acquisition and storage module includes a user authorization unit, a historical information retrieval unit, a storage node allocation unit, and a dataset generation unit;

[0090] The user authorization unit is used to obtain user authorization to retrieve historical service log information;

[0091] The historical information retrieval unit is used to retrieve records of service requests and task information from multiple groups from the historical service logs of the smart campus service platform.

[0092] The storage node allocation unit is used to allocate dedicated storage nodes for each service process in the entire smart campus service process, and to store the corresponding multi-group service demand records and task information.

[0093] The dataset generation unit is used to extract relevant information from each storage node before and after task collaboration, and generate task execution datasets before and after collaboration, respectively.

[0094] The task and feature construction module, based on the pre-collaboration task execution dataset and the post-collaboration task execution dataset, determines whether collaboration is implemented for tasks of each group, constructs the corresponding task measurement set, and obtains the frequency of each group's participation in task collaboration under each service process, generating the corresponding group behavior feature set.

[0095] Specifically, the task and feature construction module includes a task measurement set construction unit and a group behavior feature set generation unit;

[0096] The task measurement set construction unit is used to compare the task execution dataset before collaboration with the task execution dataset after collaboration to determine whether the task has implemented collaboration. It constructs an initial task measurement set for groups that have not implemented collaboration and an optimized task measurement set for groups that have implemented collaboration.

[0097] The group behavior feature set generation unit is used to obtain the frequency of task collaboration behavior of the group under each service process for groups that have not implemented collaboration, and generate a basic group behavior feature set; and to obtain the frequency of task collaboration behavior of the group under each service process for groups that have implemented collaboration, and generate a collaborative group behavior feature set.

[0098] The collaborative priority quantification module establishes a dual evaluation modality label based on the constructed task measurement set and group behavior feature set to quantify the task collaborative priority of service tasks among different groups;

[0099] Specifically, the collaborative priority quantification module includes an evaluation modality labeling construction unit and a collaborative priority calculation unit;

[0100] The evaluation modality labeling construction unit establishes two types of evaluation modality labels based on the initial task measurement set, the optimized task measurement set, the basic group behavior feature set, and the collaborative group behavior feature set, respectively associating them with the corresponding task measurement set and the group behavior feature set.

[0101] The collaboration priority calculation unit is used to identify service tasks that exist simultaneously in different task measurement sets, and quantifies the collaboration priority of tasks by calculating the correlation parameters of the frequency of related behaviors.

[0102] The collaborative adaptation analysis and optimization module evaluates the similarity of group-task collaborative adaptation between different groups based on the quantified task collaboration priority. It generates the group-task collaboration set corresponding to each group through iterative calculation, calculates the segmentation coefficient of each collaborative adaptation similarity, and combines the preset segmentation coefficient threshold for screening and optimization to obtain the final group-task collaboration set.

[0103] Specifically, the collaborative adaptation analysis and optimization module includes a collaborative adaptation similarity evaluation unit, a group-task collaborative set generation unit, a segmentation coefficient calculation unit, and a collaborative set optimization unit.

[0104] The collaborative adaptation similarity evaluation unit is used to calculate the group-task collaborative adaptation similarity between different groups based on the task collaboration priority and the preset total number of service tasks.

[0105] The group-task collaboration set generation unit is used to generate group-task collaboration sets corresponding to each group and other groups in turn through iterative calculations.

[0106] The segmentation coefficient calculation unit is used to calculate the cohesion and separation of the similarity of each collaboration in the group-task collaboration set, and obtain the corresponding group-task segmentation coefficient.

[0107] The collaborative set optimization unit is used to filter and retain the collaborative adaptation similarity that meets the requirements based on the preset group-task segmentation coefficient threshold, and update and output the optimized group-task collaborative set.

[0108] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. The smart campus task collaboration method and specific examples for multi-group service optimization described in Embodiment 1 are also applicable to the smart campus task collaboration system for multi-group service optimization described in this embodiment. Through the foregoing detailed description of the smart campus task collaboration method for multi-group service optimization, those skilled in the art can clearly understand the smart campus task collaboration system for multi-group service optimization described in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0109] In the several embodiments provided by this invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0110] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0111] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0112] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory, random access memory, magnetic disks, or optical disks.

[0113] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0114] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. 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 the invention. Therefore, the invention 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.

[0115] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. If such modifications and variations fall within the scope of this invention and its equivalents, then this invention is also intended to include such modifications and variations.

Claims

1. A smart campus task collaboration method for multi-group service optimization, characterized in that, The method includes the following steps: Step S1: After user authorization, retrieve the multi-group service request records and task information from the historical service logs of the smart campus service platform, allocate corresponding storage nodes for each service process, extract information from each storage node, and generate a pre-collaboration task execution dataset and a post-collaboration task execution dataset. Step S2: Based on the task execution dataset before collaboration and the task execution dataset after collaboration, determine whether collaboration is implemented for the tasks of each group, construct the corresponding task measurement set, and at the same time obtain the frequency of each group's participation in task collaboration under each service process to generate the corresponding group behavior feature set. Step S3: Based on the constructed task measurement set and group behavior feature set, establish a dual evaluation modality label to quantify the task collaboration priority of service tasks among different groups; Step S4: Based on the quantified task collaboration priority, evaluate the group-task collaboration adaptation similarity between different groups, generate the group-task collaboration set corresponding to each group through iterative calculation, calculate the segmentation coefficient of each collaboration adaptation similarity, and combine the preset segmentation coefficient threshold for screening and optimization to obtain the final group-task collaboration set. The specific implementation process of step S3 includes: Based on the initial task measurement set, the optimized task measurement set, the basic group behavior feature set, and the collaborative group behavior feature set, a dual-evaluation modality labeling system for tasks is constructed, with the first evaluation modality labeling being... The second evaluation mode is labeled as Where a and b are group numbers, and a ≠ b. Let be the initial task measurement set for group a. For group a, the basic set of group behavioral characteristics. For the optimization task measurement set of group b, Let b be the set of characteristics of the coordinated group behavior of group b; For any p-th service task If the service task Also exists in the initial task measurement set and optimize task measurement sets In the middle, the service tasks are quantified. Regarding the task coordination priority between group a and group b In the formula, This indicates that it originates from the basic group behavior feature set. frequency of behavior This indicates that the characteristics originate from the collaborative group behavior feature set. frequency of behavior Basic group behavior feature set With the set of characteristics of collaborative group behavior The Euclidean distance function is used to quantize service tasks. Regarding the task coordination priority between group a and group b; if the service task They do not exist simultaneously in the initial task measurement set. and optimize task measurement sets In the middle, then order .

2. The smart campus task collaboration method for multi-group service optimization according to claim 1, characterized in that, The specific implementation process of step S1 includes: After user authorization, all multi-group service request records and task information are retrieved from the historical service logs of the smart campus service platform. The multi-group service request records and task information contain all information about group service tasks and task execution status. All information includes the service tasks selected by the multi-group and the frequency of group participation in task collaboration under the service tasks. Based on the entire process of smart campus services, a storage node is allocated to each service process to store the service demand records and task information of the multiple groups. The service requirement records and task information of the multi-groups before task collaboration are implemented in each storage node are obtained to generate a task execution dataset before collaboration; the service requirement records and task information of the multi-groups after task collaboration are implemented in each storage node are obtained to generate a task execution dataset after collaboration; and both the task execution dataset before collaboration and the task execution dataset after collaboration record service tasks selected by multiple groups.

3. The smart campus task collaboration method for multi-group service optimization according to claim 2, characterized in that, The specific implementation process of step S2 includes: Based on the pre-cooperation task execution dataset P and the post-cooperation task execution dataset Q generated by group k, if the pre-cooperation task execution dataset P is equal to the post-cooperation task execution dataset Q, it is determined that no cooperation has been implemented for the tasks of group k, and an initial task measurement set for group k is constructed. If the task execution dataset P before collaboration is not equal to the task execution dataset Q after collaboration, then it is determined that collaboration has been implemented for the tasks of group k, and an optimized task measurement set for group k is constructed. ; Based on the pre-coordination and post-coordination task execution datasets generated by group k, for the case where no coordination is implemented, the frequency of group k's participation in task coordination under each service process is obtained to generate a basic group behavior feature set of group k, denoted as . For cases where collaboration has already been implemented, the frequency of group k's participation in task collaboration under each service process is obtained to generate a collaborative group behavior feature set for group k, denoted as... ,in, This represents the frequency of group k's participation in task collaboration recorded in the nth storage node, where N represents the total number of storage nodes.

4. The smart campus task collaboration method for multi-group service optimization according to claim 3, characterized in that, The specific implementation process of step S4 includes: Based on task collaboration priorities, the similarity of group-task collaboration adaptation between group a and group b is evaluated. In the formula, Indicates the total number of pre-set service tasks; A group-task collaboration analysis iterative model is constructed. In the first iteration, b = b + 1 is set and substituted into the collaboration adaptation similarity formula to obtain the collaboration adaptation similarity between group a and every other group except group a. A group-task collaboration set is then generated, denoted as […]. In the second iteration, let a = a+1, return to the first iteration, obtain the co-adaptation similarity between group a+1 and every group other than group a+1, and generate the group-task co-adaptation set. ; Collect all group-task collaboration sets, and cluster each group-task collaboration set as a collaboration scheme cluster; within the group-task collaboration set... In the process, arbitrarily select a co-adaptation similarity. Analyze the group-task splitting coefficient: ； In the formula, Represents the group-task splitting coefficient. Cohesion, representing the similarity of co-fitting, Separability, representing the similarity of co-adaptation, Representing a group-task collaborative set The total number of collaborative adaptation similarities included. Representing a group-task collaborative set The total number of collaborative adaptation similarities included; Preset group-task segmentation coefficient threshold; if the group-task segmentation coefficient... If the similarity is greater than or equal to the group-task segmentation coefficient threshold, the corresponding collaborative adaptation similarity is retained; otherwise, it is discarded, and the optimized group-task collaborative set is updated and output.

5. A smart campus task collaboration system for multi-group service optimization, executing the smart campus task collaboration method for multi-group service optimization as described in any one of claims 1-4, characterized in that, The system includes: a data acquisition and storage module, a task and feature construction module, a collaborative priority quantification module, and a collaborative adaptation analysis and optimization module; The data acquisition and storage module is used to retrieve multi-group service demand records and task information from the historical service logs of the smart campus service platform after user authorization. It allocates corresponding storage nodes for each service process, extracts information from each storage node, and generates task execution datasets before and after collaboration. The task and feature construction module, based on the pre-collaboration task execution dataset and the post-collaboration task execution dataset, determines whether collaboration is implemented for tasks of each group, constructs the corresponding task measurement set, and obtains the frequency of each group's participation in task collaboration under each service process, generating the corresponding group behavior feature set. The collaborative priority quantification module establishes a dual evaluation modality label based on the constructed task measurement set and group behavior feature set to quantify the task collaborative priority of service tasks among different groups; The collaborative adaptation analysis and optimization module evaluates the similarity of group-task collaborative adaptation among different groups based on the quantified task collaboration priority. It generates group-task collaboration sets corresponding to each group through iterative calculation, calculates the segmentation coefficient of each collaborative adaptation similarity, and combines the preset segmentation coefficient threshold for screening and optimization to obtain the final group-task collaboration set.

6. A smart campus task collaboration system for multi-group service optimization according to claim 5, characterized in that, The data acquisition and storage module includes a user authorization unit, a historical information retrieval unit, a storage node allocation unit, and a dataset generation unit. The user authorization unit is used to obtain user authorization to retrieve historical service log information; The historical information retrieval unit is used to retrieve records of service requests and task information from multiple groups from the historical service logs of the smart campus service platform. The storage node allocation unit is used to allocate dedicated storage nodes for each service process in the entire smart campus service process, and to store the corresponding multi-group service demand records and task information. The dataset generation unit is used to extract relevant information from each storage node before and after task collaboration, and generate task execution datasets before and after collaboration, respectively.

7. A smart campus task collaboration system for multi-group service optimization according to claim 5, characterized in that, The task and feature construction module includes a task measurement set construction unit and a group behavior feature set generation unit; The task measurement set construction unit is used to compare the task execution dataset before collaboration with the task execution dataset after collaboration to determine whether the task has implemented collaboration. It constructs an initial task measurement set for groups that have not implemented collaboration and an optimized task measurement set for groups that have implemented collaboration. The group behavior feature set generation unit is used to obtain the frequency of task collaboration behavior of the group under each service process for groups that have not implemented collaboration, and generate a basic group behavior feature set; and for groups that have implemented collaboration, it obtains the frequency of task collaboration behavior of the group under each service process, and generates a collaborative group behavior feature set.

8. A smart campus task collaboration system for multi-group service optimization according to claim 5, characterized in that, The collaborative priority quantification module includes an evaluation modality labeling construction unit and a collaborative priority calculation unit; The evaluation modality labeling construction unit establishes two types of evaluation modality labels based on the initial task measurement set, the optimized task measurement set, the basic group behavior feature set, and the collaborative group behavior feature set, respectively associating them with the corresponding task measurement set and the group behavior feature set. The collaboration priority calculation unit is used to identify service tasks that exist simultaneously in different task measurement sets, and quantifies the collaboration priority of tasks by calculating the correlation parameters of the frequency of related behaviors.

9. A smart campus task collaboration system for multi-group service optimization according to claim 5, characterized in that, The collaborative adaptation analysis and optimization module includes a collaborative adaptation similarity evaluation unit, a group-task collaborative set generation unit, a segmentation coefficient calculation unit, and a collaborative set optimization unit. The collaborative adaptation similarity evaluation unit is used to calculate the group-task collaborative adaptation similarity between different groups based on the task collaboration priority and the preset total number of service tasks. The group-task collaboration set generation unit is used to generate group-task collaboration sets corresponding to each group and other groups in turn through iterative calculations. The segmentation coefficient calculation unit is used to calculate the cohesion and separation of the similarity of each collaboration in the group-task collaboration set, and obtain the corresponding group-task segmentation coefficient. The collaborative set optimization unit is used to filter and retain the collaborative adaptation similarity that meets the requirements based on the preset group-task segmentation coefficient threshold, and update and output the optimized group-task collaborative set.

Images