Integrated volunteer intelligent scheduling system and method

Abstract

The invention discloses an integrated volunteer intelligent scheduling system and method, and the method comprises the steps: S100, obtaining a historical scheduling work order, and carrying out the preprocessing of the historical scheduling work order, and the historical scheduling work order comprises a service demand order and corresponding volunteer personal resource data; s200, the preprocessed historical scheduling work order is input into an intelligent scheduling model, text content of the work order is extracted, feature extraction is carried out on the text content, text features are obtained, and the text features comprise volunteer key features and demand order key features; and S300, clustering analysis is carried out on the text features obtained after preprocessing, different clustering results are obtained, and the clustering results comprise volunteer information, demand list information and position information. S400, training a preset scheduling rule corresponding to the intelligent scheduling model based on different clustering results and the text feature library corresponding to each clustering result to obtain a trained intelligent order dispatching model, the matching process of the preset scheduling rule is that volunteers are matched according to the skill characteristics of the volunteers, the service available time and the priority sequence of the museum to the positions of the volunteers, and different clustering results are in one-to-one correspondence with the matching process of the scheduling rule; and S500, inputting a work order to be processed into the intelligent order dispatching model, and screening volunteers.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, specifically to an integrated intelligent volunteer scheduling system and method, which is applicable to the management and scheduling of volunteers in public places such as museums. Background Art

[0002] With the development of society and the increasing demand of the public for public services such as culture and education, volunteers are playing an increasingly important role in various institutions and organizations. Especially in cultural venues such as museums, volunteers are not only important providers of services but also a bridge connecting museums and audiences. Therefore, how to efficiently manage volunteers, optimize resource allocation, and improve service quality has become an important issue faced by institutions such as museums.

[0003] Traditional volunteer management methods often rely on manual scheduling and paper records, with many limitations. For example, the scheduling efficiency is low and cannot quickly respond to changes in the operation of the museum; the resource allocation is uneven, resulting in shortages or surpluses of staff in some positions; the volunteer information is not updated in a timely manner, affecting the service quality, etc. These problems not only increase the management cost but also reduce the audience experience. With the rapid development of information technology, intelligent scheduling systems have gradually been applied in various fields. An intelligent scheduling system can achieve precise resource allocation and efficient scheduling by integrating advanced algorithms and data analysis technologies. In the field of volunteer management, an intelligent scheduling system can break through the limitations of traditional management methods and achieve automated scheduling of volunteers and optimized allocation of resources. Summary of the Invention

[0004] In view of the above situation, embodiments of this application propose an integrated intelligent volunteer scheduling system and method.

[0005] In a first aspect, embodiments of this application provide an integrated intelligent volunteer scheduling method. The method is as follows: S100, obtain historical scheduling work orders and preprocess the historical scheduling work orders. The historical scheduling work orders include service requirement orders and corresponding personal resource data of volunteers;

[0006] S200, input the preprocessed historical scheduling work orders into an intelligent scheduling model, extract the text content of the work orders, and perform feature extraction on the text content to obtain text features. The text features include key features of volunteers and key features of requirement orders;

[0007] S300, perform clustering analysis on the text features obtained after preprocessing to obtain different clustering results. The clustering results include: volunteer information, requirement order information, and location information;

[0008] S400. Train the preset scheduling rules corresponding to the intelligent scheduling model based on different clustering results and the text feature libraries corresponding to each clustering result to obtain a trained intelligent order assignment model. The matching process of the preset scheduling rules is to match volunteers in the priority order of the volunteers' skills and specialties, service availability time, and the distance between the museum and the volunteers' locations. Different clustering results correspond one-to-one with the matching processes of the scheduling rules.

[0009] S500. Input the work order to be processed into the intelligent order assignment model to screen volunteers.

[0010] In one embodiment, S100 further includes:

[0011] S110. Perform formatting processing on the service demand form, including:

[0012] Use a large language model to convert text or other unstructured data in the service demand form into a formatted demand form through data parsing technology. The formatted demand form is structured data.

[0013] In one embodiment, S100 further includes:

[0014] Step S111 cleans and normalizes the volunteer personal resource data to obtain the volunteer personal valid data.

[0015] In one embodiment, obtaining the key features of volunteers further includes:

[0016] S210 constructs a decision tree based on the valid data, evaluates the contribution of each valid data to the scheduling decision, and screens the key features of volunteers according to the size of the contribution value.

[0017] In one embodiment, the intelligent algorithms adopted by the intelligent order assignment model include genetic algorithms, particle swarm optimization algorithms, and deep learning.

[0018] In one embodiment, further including: performing clustering analysis on the text features obtained after preprocessing to obtain different clustering results.

[0019] Perform similarity feature analysis on the processed text features and vectorize the text features.

[0020] In one embodiment, it includes S600. Convert the scheduling plan generated in step S500 into actual operation instructions and display and execute them to volunteers and museum managers through mobile applications, Web interfaces, or API interfaces.

[0021] In one embodiment, there is also a model evaluation step, which is measured using accuracy and recall metrics.

[0022] Second aspect, the embodiments of the present application further provide an integrated intelligent volunteer scheduling system, which includes:

[0023] A work order input module, configured to input a service requirement form to be processed into the intelligent scheduling model to match and determine volunteers, and the intelligent scheduling model is constructed by the integrated intelligent volunteer scheduling method according to any one of claims 1-8;

[0024] A result feedback module, configured to feedback the determined volunteer information to museum managers or volunteers.

[0025] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects:

[0026] In the present application, by inputting the historical scheduling work order sample set into the intelligent scheduling model, extracting the text content of the work order, performing word segmentation and feature extraction processing on the text, classifying the text features, obtaining different categories and the corresponding text feature libraries for each category, and training the preset scheduling rules corresponding to the intelligent scheduling model based on the obtained different categories and the corresponding text feature libraries for each category, the matching process of the preset scheduling rules is to match volunteers in the order of priority of the volunteers' skill specialties, service available time, and the distance between the museum and the volunteers' locations. Then, the volunteers corresponding to the museum requirement form are output, rationally allocating human resources, not only realizing efficient, intelligent and safe order dispatching services, but also improving the completion quality and efficiency of task work orders. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0028] Figure 1 A flowchart showing an integrated intelligent volunteer scheduling method according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0030] The technical solutions provided by the embodiments of the present application are described in detail below in conjunction with the drawings.

[0031] The integrated intelligent dispatching method of this application specifically includes:

[0032] S100. Obtain historical dispatching work orders and preprocess the historical dispatching work orders.

[0033] The historical dispatching work orders include service requirement forms and corresponding volunteer personal resource data;

[0034] S110. Perform formatting processing on the service requirement form, including:

[0035] Using a large language model, convert the text or other unstructured data in the service requirement form into a formatted requirement form through data parsing technology. The formatted requirement form is structured data (such as in table form); perform normalization processing on the data to ensure the consistency and comparability of the data. For example, format the service responsibility description information in each service requirement form to obtain structured service responsibility description information.

[0036] The formatted requirement form includes service time arrangement, service experience requirements, number of service personnel, service location, service responsibility description information, etc.

[0037] The large language model can be Wenxin Yiyan large model, Tongyi large model, Zhipu large model.

[0038] Step S111. Clean and normalize the volunteer personal resource data to obtain volunteer personal valid data;

[0039] The volunteer personal resource data includes but is not limited to the basic information, skill specialties, available service time, and service distance of the volunteer. The basic information includes gender, name, age, address, ID number, etc.

[0040] Specifically: Clean the collected volunteer personal resource data, reduce redundant data such as volunteer personal information and service history through deduplication. For example, if the volunteer personal information (ID card, phone number, etc.) in two work orders is the same, only one volunteer personal information data can be retained for classification and storage in the corresponding feature library to reduce the occupation of storage space and improve data transmission efficiency. Then screen useful data such as volunteer information, skill specialties, available service time, service history data, etc., and perform normalization and standardization processing on the useful data. Exemplarily, the valid data includes the available service time, skill specialties, and serviceable addresses of the volunteer.

[0041] S200. Input the preprocessed historical dispatching work order into the intelligent dispatching model, extract the text content of the work order, and perform feature extraction on the text content to obtain text features. The text features include volunteer key features and requirement form key features.

[0042] Obtaining the key features of volunteers further includes:

[0043] S210 constructs a decision tree based on the valid data, evaluates the contribution of each valid data to the scheduling decision, and screens the key features of the volunteers according to the magnitude of the contribution value.

[0044] Specifically: evaluate the contribution of each valid data to the scheduling decision, preset a threshold, and use the valid data corresponding to the contribution value greater than this threshold as the key features to improve the performance and interpretability of the subsequent machine learning model.

[0045] When selecting a model, select a suitable machine learning or deep learning model (such as decision tree, neural network, etc.) according to the data characteristics and requirements. Define the basic information of volunteers (service time availability, service skills, service willingness, etc.), museum operation data (visitor flow, activity arrangements), historical scheduling records (customer feedback, service records), etc. as the basic inputs, and the volunteer scheduling suggestions and scheduling optimization plans as the input and output, and design the model architecture and parameters.

[0046] Use the preprocessed data to train the model and adjust the parameters to optimize the performance. The specific method of parameter tuning is to use Bayesian optimization to automatically adjust the hyperparameters of the machine learning model, such as the learning rate, the depth of the tree, etc., and adjust the number of decision trees in the random forest and the number of feature values, continuously optimize the feature space to achieve the optimal performance.

[0047] The intelligent algorithms adopted by the intelligent dispatching model include but are not limited to genetic algorithms, particle swarm optimization algorithms, deep learning, etc. Consider various influencing factors (such as the skill matching degree, service efficiency, service willingness, etc. of volunteers) and constraint conditions (such as the time arrangement of volunteers, the service requirements of the museum, etc.) to generate a scientific and reasonable scheduling plan.

[0048] In this application, the key features include: the skill specialties, service available time, and service distance of volunteers, which are volunteer attribute information. Different priorities can be set in different situations. For example, if the priority of the skill specialty is set to 1, then volunteers who meet the skill specialty requirements of the demand order will be preferentially matched.

[0049] S300 performs clustering analysis on the text features obtained after preprocessing to obtain different clustering results, and the clustering results include: volunteer information, demand order information, and location information.

[0050] After extracting the text features from the work order content in the historical scheduling work order sample set in the embodiments of the present application, the text features can be classified. For example, similarity feature analysis can be performed on the processed text features, and the analysis object can be vectorized. The Counts or Hashing method can be used for data classification to achieve synonym recommendation and generate a special dictionary. Or a combination of algorithms such as decision tree algorithm, K-means algorithm, or distance calculation can be used to classify the text features, and all the text features are classified into several major categories. For example, some features in a certain category can represent volunteer information, and some features can represent demand form information, etc. Only as an example, all the text features corresponding to each major category constitute a text feature library.

[0051] S400. Based on different clustering results and the text feature libraries corresponding to each clustering result, train the preset scheduling rules corresponding to the intelligent scheduling model to obtain a trained intelligent dispatching model. The matching process of the preset scheduling rules is to match volunteers in the order of priority of the volunteer's skill specialties, service available time, and the distance from the museum to the volunteer's location. Different clustering results correspond one-to-one with the matching process of the scheduling rules.

[0052] The matching process of the preset scheduling rules in this embodiment:

[0053] First, judge that among the volunteer information in the work order, the volunteer's skill is the first priority. Then, screen the volunteers with this skill specialty from the volunteer information list. If there is 1 volunteer, directly select this volunteer. If there are N volunteers, generate a matching priority for the corresponding volunteer information, and add a to the matching priority. Then, take the service available time as the second priority. According to whether the difference between the required volunteer service available time in the demand form information in the work order and the volunteer's service available time is less than the first preset value. If it is less than, generate a matching priority for the corresponding volunteer information, and add b to the matching priority.

[0054] For the second priority weight b of the volunteer's service available time, if selected from N volunteers, generate a matching priority in the corresponding volunteer information, and add c to the matching priority. a is greater than c, and a and c are weight values.

[0055] Then, take the distance from the museum to the volunteer's location as the third priority. According to whether the distance between the required location in the work order information in the process and the address recorded in the volunteer information is less than the preset distance. If it is less than, generate a matching priority in the corresponding volunteer information, and add c to the matching priority.

[0056] Through the size relationship among the above a, b, and c, distinguish the priorities of three situations, where the priority is mainly determined by the degree of importance.

[0057] This application gives a higher priority to the skills of volunteers than to the available service time of volunteers, and a higher priority to the available service time of volunteers than to the distance between the museum and the location of the volunteers.

[0058] The matching process of the configuration rules corresponds to different categories one by one, that is, the specified volunteer information corresponds to the museum demand form, the distance between the museum and the location of the volunteer corresponds to the location information, and the preset configuration rules are trained based on different categories and the corresponding text feature libraries of each category, so that according to the text feature library corresponding to a certain category.

[0059] S500, Input the service demand form to be processed into the intelligent dispatching model to screen volunteers.

[0060] S600, Push the scheduling plan generated in step S500 to the volunteer mobile application and the museum management platform through the RESTful API interface, display the task assignment results in real time, and support volunteers to confirm or adjust the service time through the interface button.

[0061] This application transforms the scheduling plan generated by the decision-making layer into actual operation instructions, and displays and executes them to volunteers and museum management personnel through mobile applications, Web interfaces, API interfaces, etc. And provide a friendly user interface and interaction experience, so that volunteers and management personnel can conveniently view and modify the scheduling plan, and realize the real-time transmission and feedback of information.

[0062] This application inputs the historical scheduling work order sample set into the intelligent scheduling model, extracts the text content of the work order, performs word segmentation and feature extraction on the text, classifies the text features, obtains different categories and the corresponding text feature libraries of each category, and trains the preset scheduling rules corresponding to the intelligent scheduling model based on the obtained different categories and the corresponding text feature libraries of each category. The matching process of the preset scheduling rules is to match volunteers in the order of the priority of the volunteer's skill specialties, service available time, and the distance between the museum and the location of the volunteer. Then output the volunteers corresponding to the museum service order, reasonably allocate human resources, not only realize efficient, intelligent and safe dispatching services, but also improve the completion quality and efficiency of task work orders.

[0063] This application also provides an integrated volunteer intelligent scheduling system,

[0064] A work order input module for inputting the service demand form to be processed into the intelligent scheduling model to match and determine volunteers, and the intelligent scheduling model is constructed by the above integrated volunteer intelligent scheduling method;

[0065] A result feedback module for feeding back the determined volunteer information to museum management personnel or volunteers.

[0066] This application also has model evaluation: The effectiveness of the model is evaluated through a test set, and metrics such as accuracy and recall are used for measurement. The performance of the model in actual operation is verified, and feedback is collected.

[0067] This application also has model optimization and deployment: The model is optimized according to the evaluation results, such as adjusting the structure, increasing data, etc. The model is deployed to the volunteer scheduling system, and trigger conditions and scheduling cycles are set.

[0068] This application also has monitoring and feedback loops: The system operation is monitored in real time to ensure the stability of the model. User feedback is collected to continuously optimize the model.

[0069] It aims to optimize the volunteer management and service processes in public places such as museums through efficient information management, precise job matching, and intelligent scheduling algorithms. The system integrates volunteer information management, job demand management, intelligent scheduling, personalized division of labor, an integrated management platform, and training and assessment, comprehensively improving the efficiency and quality of volunteer services.

[0070] This application can achieve intelligence and automation: Through intelligent algorithms and data analysis technologies, automatic scheduling of volunteers and optimal allocation of resources are realized, reducing manual intervention and error rates.

[0071] This application can achieve high efficiency and precision: Considering various factors (such as age, experience, skills, time availability) and constraints comprehensively, an optimal scheduling plan is generated to improve the participation and satisfaction of volunteers.

[0072] This application can achieve flexibility and scalability: The system adopts a modular design, which is easy to expand and integrate other functional modules; at the same time, it supports dynamic adjustment and optimization of the scheduling plan to adapt to different service requirements and scenarios.

[0073] This application can achieve data-driven and decision support: Based on big data analysis technologies, comprehensive data analysis reports and decision support information are provided, providing strong support for the management decisions of museums.

[0074] This application adopts AI algorithm-driven efficient scheduling: Using advanced intelligent algorithms, machine learning, optimization algorithms, etc., the task allocation of volunteers is automatically processed. By real-time analyzing factors such as the operation status of the museum, volunteer attributes, and activity arrangements, the optimal volunteer scheduling plan is quickly generated, significantly improving the efficiency of volunteer allocation and the rationality of configuration.

[0075] This application adopts the design of an integrated management platform: A comprehensive management platform integrating volunteer information management, task allocation, performance evaluation, and resource scheduling is constructed. This integrated design not only simplifies the management process, reduces manual intervention, but also realizes the real-time sharing and updating of information, improves management efficiency, and ensures the stability and professionalism of the volunteer team.

[0076] This application adopts dynamic optimization and real-time adjustment: it has the ability of dynamic optimization and can adjust and optimize the scheduling plan in real time according to the actual operation situation of the museum and the real-time status of volunteers. This flexibility ensures that the scheduling plan always remains in the optimal state to cope with various emergencies and changes. The balanced distribution of the workload of volunteers avoids the situation of individual volunteers being overburdened or idle and wasted, and improves the work enthusiasm and satisfaction of volunteers.

[0077] In summary, through means such as intelligent algorithms and data analysis, dynamic priority matching, and multi-algorithm fusion, this invention patent realizes the efficient scheduling of volunteers and the optimal allocation of resources, providing a set of innovative volunteer management solutions for the museum, which not only improves the efficiency and effect of museum volunteer management, but also promotes the overall upgrade of museum service quality and audience experience.

[0078] The above are only the embodiments of this application and are not used to limit this application. For those skilled in the art, various changes and modifications can be made to this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

1. An integrated volunteer intelligent scheduling method, characterized in that: The method includes: S100, obtaining historical dispatch work orders and preprocessing the historical dispatch work orders, the historical dispatch work orders including service demand orders and corresponding volunteer personal resource data; S200, inputting the preprocessed historical scheduling work order into the intelligent scheduling model, extracting the text content of the work order, and performing feature extraction on the text content to obtain text features, wherein the text features include key features of volunteers and key features of demand orders; S300, clustering the text features obtained after preprocessing to obtain different clustering results, wherein the clustering results include: volunteer information, demand form information, and location information; S400, based on different clustering results and the text feature library corresponding to each clustering result, the preset dispatching rules corresponding to the intelligent dispatching model are trained to obtain a trained intelligent dispatching model. The matching process of the preset dispatching rules is to match volunteers according to the priority order of the volunteer's skills, service availability time, and the distance between the museum and the volunteer's location. The matching process of different clustering results and dispatching rules corresponds one to one; S500: Input the work order to be processed into the intelligent dispatching model to screen volunteers.

2. The integrated volunteer intelligent scheduling method according to claim 1, characterized in that: S100 further includes: S110, formatting the service request form, including: By using a large language model, the service demand form is converted into a formatted demand form through data parsing technology, and the formatted demand form is structured data.

3. The integrated volunteer intelligent scheduling method according to claim 2, characterized in that: S100 further includes: Step S111 cleans and normalizes the volunteer's personal resource data to obtain the volunteer's personal valid data.

4. The integrated volunteer intelligent scheduling method according to claim 3, characterized in that: Key features for obtaining volunteers further include: S210 constructs a decision tree based on valid data, evaluates the contribution of each valid data to the scheduling decision, and screens the key features of volunteers based on the contribution value.

5. The integrated volunteer intelligent scheduling method according to claim 1, characterized in that: The intelligent algorithms used in the intelligent dispatching model include genetic algorithm, particle swarm optimization algorithm, and deep learning.

6. The integrated volunteer intelligent scheduling method according to claim 1, characterized in that: The clustering analysis of the text features obtained after the preprocessing to obtain different clustering results further includes: The processed text features are subjected to similarity feature analysis and the text features are vectorized.

7. The integrated volunteer intelligent scheduling method according to claim 1, characterized in that: The step also includes S600, which converts the scheduling plan generated in step S500 into actual operation instructions, which are displayed and executed to volunteers and museum managers through mobile applications, web interfaces or API interfaces.

8. The integrated volunteer intelligent scheduling method according to claim 1, characterized in that: There is also a model evaluation step, measured using precision and recall metrics.

9. Integrated volunteer intelligent scheduling system, characterized by: A work order input module, used to input the to-be-processed service demand order into the intelligent scheduling model, and match and determine volunteers, wherein the intelligent scheduling model is constructed by the integrated volunteer intelligent scheduling method according to any one of claims 1 to 8; The result feedback module is used to feed back the determined volunteer information to the museum management staff or volunteers.

Images