Optimization and scheduling system based on multi-department revival appointment system

Abstract

The invention relates to the technical field of department reservation and scheduling, and discloses an optimization and scheduling system based on a multi-department re-visit reservation system, which comprises a doctor operation module, a data integration module, a scheme generation module, a scheme display and selection module and a doctor and patient confirmation module, through intelligent integration of out-call information and number source conditions of doctors in all departments, re-visit interval requirements of different departments can be accurately matched, the number of visit times of patients is effectively reduced, and repeated running caused by conflict of re-visit time is avoided; secondly, the system uses an advanced algorithm to generate diversified re-consultation schemes, not only preferentially considers the weekend doctor-seeing demand of the patient, but also provides multiple choices, and significantly improves the doctor-seeing convenience and the autonomous selection right of the patient.

Description

Technical Field

[0001] This invention relates to the field of departmental appointment and scheduling technology, and more specifically discloses an optimization and scheduling system based on a multi-departmental follow-up appointment system. Background Technology

[0002] Multi-department follow-up appointment refers to the process of arranging follow-up visits to different departments such as orthodontics, endodontics, prosthodontics, periodontics, surgery, implantology, mucosal diseases, and joint diseases after a patient has completed their initial treatment, according to the doctor's advice. However, in the traditional appointment method, each department operates independently, and patients need to contact different departments separately to confirm the follow-up time, which is cumbersome and prone to problems such as time conflicts and increased number of visits. Therefore, there is an urgent need for an intelligent and collaborative multi-department follow-up appointment system to optimize the patient's medical experience.

[0003] Most existing follow-up appointment systems are designed for single departments or single diseases, lacking the ability to handle multi-departmental collaboration. When patients need follow-up appointments in multiple departments, existing systems have the following problems: First, they cannot comprehensively consider the various follow-up intervals given by doctors in different departments, making it difficult to balance the follow-up appointment time requirements of each department; second, they cannot intelligently schedule appointments based on doctors' appointment dates and remaining appointment slots, easily leading to situations where patients have to visit multiple times but cannot complete all follow-up appointments; third, in generating appointment plans, they lack consideration for patients' time preferences (such as prioritizing weekend appointments) and cannot provide patients with diverse and optimized appointment plan options; finally, the system's appointment confirmation process for patients and doctors is not smooth enough, lacking an automated processing mechanism, resulting in low efficiency. Summary of the Invention

[0004] The main technical problem solved by this invention is to provide an optimization and scheduling system based on a multi-department follow-up appointment system, which can solve the problems of single solution, poor coordination and unintelligent scheduling in the current optimization and scheduling systems based on multi-department follow-up appointment systems.

[0005] To address the aforementioned technical problems, according to one aspect of the present invention, more specifically, an optimization and scheduling system based on a multi-department follow-up appointment system includes: First, doctors input the follow-up appointment interval and order of visits into an operation module. This module provides a convenient and accurate input interface, facilitating doctors to quickly enter key information and laying the foundation for subsequent processes. The data integration module utilizes distributed computing and caching technology to efficiently and in real-time collect and integrate doctors' outpatient schedules and appointment availability information. This ensures the timeliness and accuracy of the information, providing reliable data support for subsequent plan development and avoiding appointment chaos caused by information delays or errors. Next, the plan generation module, using mixed integer programming algorithms and data mining and machine learning techniques, generates multiple follow-up appointment options based on the previously integrated data. The system employs a mixed-integer programming algorithm to accurately find the optimal solution that balances minimizing patient visits and prioritizing weekend appointments. Data mining and machine learning technologies continuously optimize the solution generation strategy, making the solutions more aligned with actual conditions and patient preferences. This combination significantly enhances the scientific rigor and rationality of the solutions. Subsequently, the solution display and selection module presents the solutions clearly and intuitively to patients through front-end display technology, facilitating patient understanding and selection. After selection, patients proceed to the doctor-patient confirmation module. If confirmed, the system automatically completes the appointment through database operations, promptly updating appointment information for each department to ensure the accuracy and efficiency of medical resource allocation. If not confirmed, patients return to the solution display and selection module to choose again, providing them with ample room for adjustment.

[0006] Furthermore, the data integration module includes: a distributed computing module and a caching technology module;

[0007] The distributed computing module utilizes a distributed database and a distributed computing framework to distribute data processing tasks to other computing nodes for parallel processing, thereby improving the efficiency of collecting and processing information on doctors' outpatient dates and remaining appointment slots in various departments.

[0008] The caching technology module uses a caching system to store frequently accessed popular department appointment information and recent outpatient schedules in a high-speed cache, reducing data retrieval time and enabling fast data access and updates. This ensures that the system can obtain accurate doctor outpatient and appointment data in real time and quickly.

[0009] Furthermore, the scheme generation module includes: a mixed integer programming algorithm module and a data mining and machine learning module;

[0010] The mixed integer programming algorithm module, with the help of the Gurobi algorithm library, models the problem of scheduling follow-up visits for multiple departments as an optimization problem. The objective function is to minimize the number of visits for patients and prioritize weekend visits. The constraints are the interval between follow-up visits for each department, the doctor's consultation time and the availability of appointment slots. The optimal follow-up visit scheduling scheme is then solved.

[0011] The data mining and machine learning module uses clustering algorithms to analyze the central trend of follow-up visit times in different departments, and uses association rule algorithms to mine the correlation between follow-up visit times in departments and the number of visits and dates of visits by patients. Based on historical follow-up visit data, it learns the patterns of follow-up visit times in each department and patient visit preference information, and continuously optimizes the plan generation strategy.

[0012] Furthermore, the doctor-patient confirmation module utilizes mobile communication technology via SMS gateway and mobile application interface to send the plan to the doctor's workstation and the patient's mobile phone, and receives confirmation feedback from the doctor and the patient. At the same time, it uses data verification technology to verify the validity of the confirmation feedback information, ensuring the timeliness and convenience of communication between the doctor and the patient, and ensuring that both parties reach a consensus on the follow-up consultation plan.

[0013] Furthermore, the operation module has a user interface that performs basic format verification on the follow-up visit interval and visit order data entered by the doctor, providing a convenient and accurate input interface so that doctors can quickly enter key information and lay the foundation for subsequent processes.

[0014] Furthermore, the appointment completion process utilizes database operation technology to automatically complete the appointment and promptly update the appointment information of doctors in each department after the doctor and patient confirm the plan. Through transaction processing database-related technologies, the consistency and accuracy of the data are ensured, thereby improving the accuracy and efficiency of medical resource allocation.

[0015] Furthermore, the solution display and selection module uses web front-end technology or mobile interface display technology to present different follow-up consultation solutions output by the solution generation module to patients in an intuitive and user-friendly interface, making it convenient for patients to make selections and enhancing their autonomy and medical experience.

[0016] The beneficial effects of this invention, based on the optimization and scheduling system of a multi-department follow-up appointment system, are as follows: First, by intelligently integrating the outpatient information and appointment availability of doctors in various departments, the system can accurately match the follow-up appointment interval requirements of different departments, effectively reducing the number of visits for patients and avoiding repeated trips due to conflicting follow-up appointment times. Second, the system uses advanced algorithms to generate diverse follow-up appointment plans, not only prioritizing patients' weekend appointment needs but also providing multiple options, significantly improving patients' convenience and autonomy in seeking medical care. Third, through automated doctor-patient confirmation and appointment processes, communication time is greatly shortened, human error is avoided, and appointment efficiency is improved. Finally, the system's intelligent scheduling mechanism fully taps into the potential of medical resources and optimizes resource allocation, significantly improving the overall operational management level of the hospital while enhancing patient satisfaction, achieving a win-win situation for both doctors and patients. Attached Figure Description

[0017] The present invention will now be described in further detail with reference to the accompanying drawings and specific implementation methods.

[0018] Figure 1 This is a schematic diagram of the system principle. Detailed Implementation

[0019] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0020] According to one aspect of the invention, such as Figure 1 As shown, an optimization and scheduling system based on a multi-department follow-up appointment system is provided, including: a doctor operation module with a user interface, which performs basic processing on the format verification of the follow-up interval and appointment sequence data entered by the doctor, and provides a convenient and accurate input interface to facilitate doctors to quickly enter key information and lay the foundation for subsequent processes;

[0021] The user interface is developed using front-end technologies such as HTML / CSS / JavaScript. It allows doctors to select or manually fill in the follow-up visit interval (e.g., 1-3 days) through text input boxes, and adjust the order of department visits by dragging and dropping menus (the default order is Orthodontics → Endodontics → Prosthodontics → Periodontics → Surgery / Implantology → Mucosal / Joint Dentistry). The system performs format validation on the input data (such as logical validation of follow-up visit interval time and uniqueness check of department order) to ensure data accuracy.

[0022] The data integration module efficiently and in real-time collects and integrates doctors' outpatient schedules and appointment information. Its advantage lies in ensuring the timeliness and accuracy of the information, providing reliable data support for subsequent plan development, and avoiding appointment chaos caused by information delays or errors. This module includes:

[0023] The distributed computing module uses a distributed database (such as HBase) to store the full doctor's outpatient calendar and appointment information. It processes data acquisition tasks in parallel using a distributed computing framework (such as Spark). For example, it shards data from each department onto different computing nodes, synchronously retrieves real-time outpatient data (including date, time period, and remaining appointment slots) from the hospital's registration system, and cleans the data (removing duplicate records and filling in missing fields) to ensure information integrity. The specific implementation method is as follows:

[0024] At the data storage level, based on HBase's distributed architecture, doctors' outpatient data is hash-sharded by department (e.g., generating RowKeys using department IDs) and distributed across different RegionServer nodes, achieving horizontal scaling and load balancing. Each data entry contains multiple versions of timestamps, recording the update history of outpatient times (e.g., backtracking old data when a doctor temporarily stops seeing patients), and HBase's WAL (Write-Ahead Log) mechanism ensures the reliability of data writes.

[0025] In the data acquisition and processing phase, leveraging the Distributed Datasets (RDD) feature of the Spark distributed computing framework, data acquisition tasks for each department are broken down into independent subtasks and distributed to multiple worker nodes in the cluster for parallel execution. For example, separate acquisition threads are created for different departments such as orthodontics and dentistry, synchronously capturing real-time outpatient data through the API interface provided by the hospital's registration system, including fields such as date, morning / afternoon time slot, and remaining appointment slots. The collected data is first entered into the Spark distributed computing framework's memory buffer and cleaned through MapReduce operations, including:

[0026] Deduplication: Based on a combination of doctor ID, consultation date, and time period, duplicate records are filtered out;

[0027] Missing value completion: Fill in the missing source field by using the average of historical data or interpolation of data from nearby dates;

[0028] Standardize the format: unify the time format returned by different departments (e.g., convert "2025 / 5 / 29" to "YYYY-MM-DD");

[0029] The cleaned data is finally written to a distributed database (HBase) to form a standardized doctor's outpatient information table, which can be called in real time by the subsequent solution generation module. This process saves the computing state periodically through the checkpoint mechanism of the distributed computing framework (Spark), avoiding repeated calculations when the task is restarted due to node failure, and further improving the stability and efficiency of data processing.

[0030] The caching technology module uses a caching system (Redis) to store frequently accessed popular department appointment information and recent outpatient schedules in a high-speed cache. It is set to automatically refresh every 10 minutes to ensure real-time performance, reduce data reading time, and enable fast data access and updates, ensuring that the system can obtain accurate doctor outpatient and appointment data in real time and quickly.

[0031] The solution generation module generates multiple follow-up visit plans based on the data integrated by the data integration module. A mixed integer programming algorithm can accurately solve for the optimal plan that balances the needs of patients, such as minimizing the number of visits and prioritizing weekend appointments. This module includes:

[0032] The mixed-integer programming algorithm module, using the Gurobi algorithm library, models the problem of scheduling follow-up visits for multiple departments as an optimization problem. The objective function is to minimize the number of patient visits and prioritize weekend visits, while constraints include the interval between follow-up visits for each department, doctor's consultation time, and limited appointment slots. The optimal follow-up visit scheduling scheme is then solved. The specific implementation is as follows:

[0033] First, define the decision variable, using binary variable x. i,j,k Indicates whether the i-th department schedules a follow-up visit for the patient during the k-th outpatient session on the j-th day (x i,j,k =1 for arrangement, x i,j,k =0 means no appointment will be scheduled), where i corresponds to the department number (e.g., orthodontics is 1, dentistry is 2), j is the date within T days (T is determined based on the longest follow-up interval, e.g., 12 months or 365 days), and k is the time period number (e.g., morning or afternoon). The objective function is set to minimize the number of patient visits, as shown below:

[0034]

[0035] Where N is the total number of departments, K is the number of time slots per day, and a preference for weekend visits is introduced through a weighting coefficient α (e.g., the weight of the number of visits on weekends is α = 1.5, and on weekdays it is α = 1), forming a weighted objective function formula:

[0036]

[0037] Where a j The value is determined based on whether the date is a weekend. Additional constraints include:

[0038] Follow-up visit interval constraints: For department i, the follow-up visit date j i The interval between the date of the initial consultation (j0) and the date of the first consultation must be within the range specified by the doctor (e.g., d). min,i ≤j i -j0≤d max,i ), where d min,i The minimum interval specified by the doctor, d max,i The maximum interval specified for the doctor;

[0039] Doctors' consultation time is restricted. If doctor m does not have a consultation during the k-th time period on the j-th day of department i, then X... i,j,k =0;

[0040] Due to appointment availability constraints, the number of appointments for department i in each time period j and k must be less than or equal to the remaining number of appointments S.i,j,k Then it is represented as:

[0041]

[0042] Where j represents the department, i represents the date, and k represents the time period.

[0043] The data mining and machine learning module uses the K-Means clustering algorithm to analyze the central trend of follow-up visit times in different departments, and the Apriori association rule algorithm to mine the association between departmental follow-up visit times and the number of patient visits and visit dates. Based on historical follow-up visit data, it learns the patterns of follow-up visit times in each department and patient visit preference information, and continuously optimizes the plan generation strategy. The specific implementation method is as follows:

[0044] First, based on historical follow-up visit datasets (including fields such as department, follow-up visit interval days, visit date, and number of visits), the K-Means clustering algorithm is used to perform unsupervised learning on the follow-up visit intervals for each department. For example, the follow-up visit interval data for the periodontology department is clustered into several categories such as "within 1 week after surgery," "1-2 weeks," and "2-4 weeks" to determine the common follow-up visit time ranges for this department, providing a reference for doctors to set default follow-up visit intervals. Second, the Apriori association rule algorithm is used to mine cross-departmental follow-up visit time associations. For example, the follow-up visit order and time interval between the orthodontics and endodontics departments are analyzed. If it is found that "within 3 days after the orthodontics follow-up visit..." If the support rate for "re-visiting the dental department" reaches 70% and the confidence rate reaches 85%, then this time combination will be given priority in the plan generation to reduce repeated visits caused by unreasonable department order. In addition, time series analysis technology is used to model patients' visits on appointment dates. For example, the proportion of patients in each department who visit on weekends is statistically analyzed. If the weekend visit rate of patients in the mucosal department reaches 45%, then the weight of the weekend time slot of that department will be increased in the objective function of plan generation. By regularly (e.g., weekly) updating historical data to train the model, the cluster center, association rule threshold and time series weight are continuously optimized so that the plan generation strategy can dynamically adapt to changes in patients' visit patterns.

[0045] The treatment plan display and selection module uses web front-end technologies (such as HTML5 / CSS3 responsive layout + Vue.js framework) or mobile interface display technologies (such as ReactNative cross-platform development) to display four sets of plans in calendar view and list view. Each set of plans includes the appointment date, department order, corresponding doctor, total number of appointments, number of weekend appointments, and appointment availability status (e.g., "2 appointments remaining in the Implantology Department"). Patients can switch between plans by swiping or by clicking to view details. A one-click selection button is set at the bottom of the interface and a modal pop-up confirmation mechanism is integrated to prevent accidental operation. The different follow-up appointment plans output by the plan generation module are presented to patients in an intuitive and user-friendly interface, making it convenient for patients to make choices and improving their autonomy and medical experience.

[0046] The doctor-patient confirmation module utilizes mobile communication technologies such as SMS gateways (e.g., Alibaba Cloud SMS service) and mobile application programming interfaces (APIs) to send an SMS message containing a summary of the treatment plan and a confirmation link to the patient's mobile phone. Simultaneously, it pushes the plan details to the doctor's workstation. After clicking the link, the patient confirms via verification code or fingerprint recognition. The doctor clicks "Confirm" or "Reject" on the workstation (with a reason provided). The system uses data verification technology (e.g., signature verification) to ensure the authenticity and validity of the feedback information, sends the plan to both the doctor's workstation and the patient's mobile phone, and receives confirmation feedback from both the doctor and the patient. Data verification technology is also used to verify the validity of the confirmation feedback information, ensuring timely and convenient communication between doctors and patients, and ensuring that both parties reach a consensus on the follow-up consultation plan. If confirmed, the system automatically locks available appointment slots through a database transaction mechanism (e.g., MySQL InnoDB transactions), updates the remaining appointment slots in each department, and generates an appointment voucher (including a QR code) which is pushed to the patient's app, ensuring timely updates of appointment information in each department and guaranteeing the accuracy and efficiency of medical resource allocation. If not confirmed, the system returns to the plan display and selection module, allowing the patient to choose again and providing ample adjustment options.

[0047] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the examples given above. Any changes, modifications, additions or substitutions made by those skilled in the art within the scope of the present invention are also within the protection scope of the present invention.

Claims

1. An optimization and scheduling system based on a multi-department follow-up appointment system, characterized in that, include: First, doctors input their follow-up appointment intervals and appointment order into the operation module. This module provides a convenient and accurate input interface, allowing doctors to quickly enter key information and laying the foundation for subsequent processes. The data integration module utilizes distributed computing and caching technology to efficiently and in real-time collect and integrate doctors' appointment schedules and available appointments. This ensures the timeliness and accuracy of the information, providing reliable data support for subsequent plan development and avoiding appointment chaos caused by information delays or errors. Next, the plan generation module uses mixed integer programming algorithms, data mining, and machine learning techniques to generate multiple follow-up appointment plans based on the integrated data. The mixed integer programming algorithm can accurately solve for the optimal plan that balances the needs of patients, such as minimizing the number of appointments and prioritizing weekend appointments. Data mining and machine learning techniques continuously optimize the plan generation strategy, making the plans more aligned with actual situations and patient preferences. The combination of these two approaches greatly enhances the scientific rigor and rationality of the plans. Subsequently, the plan display and selection module presents the plans clearly and intuitively to the patient through front-end display technology, making it easy for the patient to understand and choose. After the patient makes a selection, they enter the doctor-patient confirmation module. If confirmed, the system automatically completes the appointment through database operation technology and updates the appointment information of each department in a timely manner to ensure the accuracy and efficiency of medical resource allocation. If not confirmed, the patient returns to the plan display and selection module to choose again, giving the patient ample room for adjustment.

2. The optimization and scheduling system based on a multi-department follow-up appointment system according to claim 1, characterized in that: The data integration module includes: a distributed computing module and a caching technology module; The distributed computing module utilizes a distributed database and a distributed computing framework to distribute data processing tasks to other computing nodes for parallel processing, thereby improving the efficiency of collecting and processing information on doctors' outpatient dates and remaining appointment slots in various departments. The caching technology module uses a caching system to store frequently accessed popular department appointment information and recent outpatient schedules in a high-speed cache, reducing data retrieval time and enabling fast data access and updates. This ensures that the system can obtain accurate doctor outpatient and appointment data in real time and quickly.

3. The optimization and scheduling system based on a multi-department follow-up appointment system according to claim 1, characterized in that: The scheme generation module includes: a mixed integer programming algorithm module and a data mining and machine learning module; The mixed integer programming algorithm module, with the help of the Gurobi algorithm library, models the problem of scheduling follow-up visits for multiple departments as an optimization problem. The objective function is to minimize the number of visits for patients and prioritize weekend visits. The constraints are the interval between follow-up visits for each department, the doctor's consultation time and the availability of appointment slots. The optimal follow-up visit scheduling scheme is then solved. The data mining and machine learning module uses clustering algorithms to analyze the central trend of follow-up visit times in different departments, and uses association rule algorithms to mine the correlation between follow-up visit times in departments and the number of visits and dates of visits by patients. Based on historical follow-up visit data, it learns the patterns of follow-up visit times in each department and patient visit preference information, and continuously optimizes the plan generation strategy.

4. The optimization and scheduling system based on a multi-department follow-up appointment system according to claim 1, characterized in that: The doctor-patient confirmation module utilizes mobile communication technology via SMS gateway and mobile application interface to send the plan to the doctor's workstation and the patient's mobile phone, and receives confirmation feedback from the doctor and the patient. At the same time, it uses data verification technology to verify the validity of the confirmation feedback information, ensuring the timeliness and convenience of communication between the doctor and the patient, and ensuring that both parties reach a consensus on the follow-up visit plan.

5. The optimization and scheduling system based on a multi-department follow-up appointment system according to claim 1, characterized in that: The operation module has a user interface that performs basic processing such as format verification on the follow-up visit interval and visit order data entered by the doctor, providing a convenient and accurate input interface to facilitate doctors to quickly enter key information and lay the foundation for subsequent processes.

6. The optimization and scheduling system based on a multi-department follow-up appointment system according to claim 1, characterized in that: The appointment completion process utilizes database operation technology to automatically complete the appointment and promptly update the appointment information of doctors in each department after the doctor and patient confirm the plan. Through transaction processing database-related technologies, the consistency and accuracy of the data are ensured, thereby improving the accuracy and efficiency of medical resource allocation.

7. The optimization and scheduling system based on a multi-department follow-up appointment system according to claim 1, characterized in that: The solution display and selection module uses web front-end technology or mobile interface display technology to present different follow-up consultation solutions output by the solution generation module to patients in an intuitive and user-friendly interface, making it convenient for patients to make choices and enhancing their autonomy and medical experience.

Images