Internet-based health care service system

Abstract

The invention discloses an internet-based health care service system, which relates to the technical field of health care services and comprises a care task delay detection module, a dynamic delay influence analysis module, a delay influence evaluation and priority classification module, a subsequent order adjustment decision module and a real-time monitoring and optimization module. And the delay influence evaluation and priority classification module constructs a delay influence evaluation model for the generated time influence index and priority matching index of each subsequent order, generates a delay evaluation coefficient of each subsequent order, analyzes and evaluates the influence degree of the delay of the nursing personnel in the current task on each subsequent order after generation, and classifies the priority matching index of each subsequent order. And the subsequent orders are divided into high-priority orders, medium-priority orders and low-priority orders according to the evaluation result. According to the invention, the problem of subsequent order time conflict caused by nursing task delay is solved, real-time dynamic analysis and optimization adjustment are realized, and the nursing service efficiency and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of health care services, and in particular to a health care service system based on the Internet. Background Art

[0002] Health care services refer to the provision of daily care, health monitoring, rehabilitation guidance and other services to patients by professional medical staff with the goal of meeting the health needs of patients, aiming to improve the health status of patients and enhance their quality of life. However, the traditional health care service model mainly relies on offline communication and services, which has problems such as low efficiency, uneven resource allocation and inability to respond to patient needs in a timely manner, making it difficult to meet the requirements of modern medical services for efficiency, convenience and personalization. With the rapid development of Internet technology, the use of "Internet +" technology to carry out health care services has become an important way to solve the above problems. Internet-based health care services can realize the online and intelligent operation of nursing services by integrating functions such as order management, resource allocation, patient information management and medical staff scheduling, so that service agencies can efficiently dispatch resources, manage patient information in real time, and quickly match medical staff according to needs, providing patients with more accurate and efficient services. At the same time, the application of Internet technology can ensure the real-time transmission of information and the safe management of data, thereby effectively improving service quality, meeting the growing demand for health management, and providing important technical support for service model innovation in the field of medical care.

[0003] Existing Internet-based health care service technologies carry out health care services through an integrated Internet platform. The platform usually includes core functional modules such as order management, resource management, patient management and medical staff scheduling. Specifically, patients or their families can initiate nursing service needs through the online system. The platform automatically matches suitable medical staff according to the patient's health status, geographical location and service requirements, and generates nursing orders. After the order is generated, the platform supports real-time updating of patient health information and guides medical staff to perform services in accordance with standardized processes through the nursing path management function. In the process of providing services, nursing staff can enter the patient's health monitoring data, such as vital signs, self-test results, etc., through the platform for subsequent evaluation and adjustment of nursing plans. In addition, the platform provides medical staff scheduling and resource allocation functions to ensure the rational allocation of human resources and improve the response efficiency of services. After the service is completed, the platform also supports the generation of nursing records and expense bills for review by institutional managers or patient filing. Throughout the process, strict permission management and data encryption technology are used to protect patient privacy and data security, thereby achieving efficient, secure and personalized health care services.

[0004] The prior art has the following deficiencies:

[0005] During the execution of nursing services, when nursing staff extend the service time of the current order due to special circumstances (such as increased patient needs and increased task complexity), the problem of time conflicts for subsequent orders will arise. Since nursing tasks are usually arranged at fixed time intervals, the system assumes that nursing staff can complete the tasks within the estimated time during planning. However, in actual execution, if the previous task exceeds the estimated completion time, subsequent orders may be forced to be delayed or even overlap in time. However, when faced with this situation, the existing technology only relies on manual adjustment of subsequent order times, lacks the ability to dynamically analyze the impact of nursing staff task delays on subsequent orders in real time, and cannot quickly identify the conflict level or priority of subsequent orders. This deficiency will lead to confusion in the scheduling of subsequent orders, overload of nursing staff tasks, and passive extension of patient waiting time, which seriously affects service efficiency and patient satisfaction.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an Internet-based health care service system to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: an Internet-based health care service system, comprising a nursing task delay detection module, a dynamic delay impact analysis module, a delay impact assessment and priority classification module, a subsequent order adjustment decision module, and a real-time monitoring and optimization module;

[0009] The nursing task delay detection module detects the completion progress of the nursing staff's current task in real time during the execution of nursing services, and triggers a dynamic adjustment process when it detects that the task service time exceeds the set threshold;

[0010] The dynamic delay impact analysis module obtains the dynamic delay impact information of the current task delay on all subsequent orders in real time, analyzes it after acquisition, and generates the time impact index and priority matching index of each subsequent order;

[0011] The delay impact assessment and priority classification module builds a delay impact assessment model for the time impact index and priority matching index of each subsequent order, generates a delay assessment coefficient for each subsequent order, and analyzes it after generation to assess the impact of the nursing staff's delay in the current task on each subsequent order, and divides the subsequent orders into high-priority orders, medium-priority orders, and low-priority orders based on the assessment results;

[0012] The subsequent order adjustment decision module takes corresponding adjustment measures for high-priority orders, medium-priority orders and low-priority orders according to the classification results of each subsequent order;

[0013] The real-time monitoring and optimization module continuously monitors the execution status of nursing tasks and resource allocation information, and dynamically optimizes the delay impact assessment model and task adjustment strategy based on the real-time monitoring results. At the same time, it stores and analyzes historical adjustment data to optimize model parameters and strategy settings, thereby improving the long-term adaptability and adjustment efficiency of the system.

[0014] Preferably, in the dynamic delay impact analysis module, the dynamic delay impact information of the current task delay on all subsequent orders is obtained in real time and preprocessed after acquisition; the task time dynamic information and task resource distribution information in the preprocessed dynamic delay impact information of the current task delay on all subsequent orders are extracted, and analyzed after extraction to generate the time impact index and priority matching index of each subsequent order respectively.

[0015] Preferably, the logic for obtaining the time impact index of each subsequent order is as follows:

[0016] Extract the dynamic information of task time from the dynamic delay impact information of the current task delay on all subsequent orders after preprocessing, including the actual delay time of the nursing staff in performing the current task, the estimated travel time of the nursing staff to the locations of each subsequent order, and the time interval between the appointment time of each subsequent order and the completion time of the current task, and mark them as TD, TT respectively. i andTO i , TD represents the actual delay time for the nurse to perform the current task, TT i represents the estimated travel time of the nursing staff to the i-th subsequent order location, TO i represents the time interval between the appointment time of the i-th subsequent order and the completion time of the current task, i = 1, 2, 3, ..., k, k is a positive integer;

[0017] Calculate the time impact index of each subsequent order. The specific calculation formula is as follows:

[0018]

[0019] Where TII i is the time impact index of the ith subsequent order.

[0020] Preferably, the logic for obtaining the priority matching index of each subsequent order is as follows:

[0021] The task resource distribution information of the dynamic delay impact information caused by the pre-processed current task delay on all subsequent orders is extracted, including the material demand gap of each subsequent order, the total number of tasks completed by the nursing staff, the geographical straight-line distance between the location of each subsequent order and the location of the current task, and the ratio of the total number of orders to the area of ​​the nursing staff's current working area, and they are marked as RD i ,NT,DP i and DA, RD i represents the material demand gap of the ith subsequent order, NT represents the total number of tasks completed by the nursing staff, and DP i represents the geographical straight-line distance between the location of the i-th subsequent order and the location of the current task, DA represents the ratio of the total number of orders in the nursing staff's current working area to the area of ​​the area, i = 1, 2, 3, ..., k, k is a positive integer;

[0022] Calculate the priority matching index of each subsequent order. The specific calculation formula is as follows:

[0023]

[0024] Where PMI i is the priority matching index of the ith subsequent order.

[0025] Preferably, in the delay impact assessment and priority classification module, a delay impact assessment model is constructed for the time impact index and priority matching index of each subsequent order generated, and a delay assessment coefficient of each subsequent order is generated, which specifically includes the following steps:

[0026] Collect the time impact index, priority matching index and corresponding delay assessment coefficient of several subsequent orders generated in the past period of time, and mark them as and x represents the time impact index, priority matching index and corresponding delay assessment coefficient number of each subsequent order generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time is formed into a historical data set;

[0027] The multivariate regression model is selected as the delay impact assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0028]

[0029] Where β0, β1 and β2 are regression coefficients;

[0030] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0031] Using the finalized regression coefficient, the delay impact assessment model is constructed and the time impact index TII of each subsequent order generated in real time is input. i and priority matching index PMI i , generate the delay evaluation coefficient DEC of each subsequent order in real time i .

[0032] Preferably, the delay evaluation coefficient DEC of each subsequent order generated i The delay assessment coefficient threshold interval [DEC min ,DEC max ] to compare, and evaluate the impact of the nursing staff's delay in the current task on each subsequent order based on the comparison results, and divide each subsequent order into high priority orders, medium priority orders and low priority orders based on the evaluation results. The specific comparison analysis and division are as follows:

[0033] If DEC i <DEC min , if the impact of the delay of the nursing staff in the current task on the subsequent order is low, the subsequent order is classified as a low priority order;

[0034] If DEC min ≤DEC i ≤DEC max , if the impact of the delay of the nursing staff in the current task on the subsequent order is medium, then the subsequent order is classified as a medium priority order;

[0035] If DEC i >DEC max , if the impact of the nursing staff's delay in the current task on the subsequent order is high, the subsequent order is classified as a high-priority order.

[0036] Preferably, in the subsequent order adjustment decision module, corresponding adjustment measures are taken for high priority orders, medium priority orders and low priority orders respectively according to the classification results of each subsequent order, specifically:

[0037] For subsequent orders classified as low-priority orders, the specific adjustment measures are as follows: prioritize delaying their planned service time and arranging them to be executed during the time period when nursing staff have fewer tasks to reduce interference with current nursing tasks; and mark their service plans as standby when resources are tight, and deploy them after the priority orders are completed, while continuously monitoring the service needs of low-priority orders;

[0038] For subsequent orders classified as medium priority orders, the specific adjustment measures are as follows: according to the preset task scheduling rules, service time is allocated within the scope of existing nursing staff resources, and the service sequence is dynamically optimized to ensure efficient use of resources. At the same time, the priority status of the order is periodically reviewed in combination with real-time data;

[0039] For subsequent orders that are classified as high-priority orders, the specific adjustment measures taken are: giving priority to ensuring their service time and resource allocation, providing nursing resources for high-priority orders by deploying additional nursing staff and adjusting the service plans of medium and low-priority orders, and monitoring the service status in real time to ensure that high-priority orders can be completed on time, so as to reduce the risk of patient dissatisfaction and reduced care quality due to delays.

[0040] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0041] 1. The present invention can quickly capture delays in nursing tasks caused by special circumstances (such as increased patient demand and increased task complexity) by detecting the completion progress of nursing tasks and service time delays in real time, and significantly improves the ability to respond to emergencies during the execution of nursing tasks. When a task delay is detected, the system can trigger a dynamic adjustment process, from delay impact analysis to task adjustment strategy optimization, to achieve real-time and intelligent management of nursing services. Compared with the prior art method that relies on manual adjustment, the present invention effectively reduces the time cost of manual operation and the possible risk of misjudgment, ensures the orderliness of subsequent order scheduling and the rational use of nursing resources, and improves the overall efficiency and reliability of nursing services.

[0042] 2. The present invention constructs a delay impact assessment model through the precise calculation of the time impact index and the priority matching index, which can quantitatively analyze the comprehensive impact of nursing task delays on subsequent orders, and reasonably divide the orders into high, medium and low priorities based on the classification of delay assessment coefficients. This priority classification method based on quantitative analysis avoids the shortcomings of subjective judgment in traditional methods, can scientifically reflect the actual impact of task delays on subsequent orders, and provide accurate decision-making basis for task scheduling and resource allocation. At the same time, the dynamic classification mechanism supports real-time adjustment of priority status, making the system more adaptable and flexible in the face of changes in nursing needs, thereby improving patient satisfaction and nursing service quality.

[0043] 3. Through the detailed setting of adjustment measures for orders of different priorities, the present invention enables the system to intelligently schedule resources for subsequent orders according to the actual nursing resource status, such as delaying low-priority orders, optimizing the order of medium-priority orders, and prioritizing resource allocation for high-priority orders. This multi-level task adjustment strategy fully reflects the pertinence and efficiency of resource allocation, avoiding waste of resources and task conflicts. In addition, the real-time monitoring and optimization module dynamically optimizes the delay impact assessment model and adjustment strategy by storing and analyzing historical adjustment data, ensuring that the system can continuously adapt to emerging nursing scenario requirements during long-term operation, thereby achieving continuous optimization of the nursing service system and improvement of the overall service level. The long-term adaptability and adjustment efficiency of this technical solution make the system more intelligent and stable, and it has extremely strong application value and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0045] Figure 1 The module diagram of a health care service system based on the Internet of the present invention is shown in FIG. DETAILED DESCRIPTION

[0046] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0047] The present invention provides Figure 1 An Internet-based health care service system is shown, comprising a nursing task delay detection module, a dynamic delay impact analysis module, a delay impact assessment and priority classification module, a subsequent order adjustment decision module, and a real-time monitoring and optimization module;

[0048] The nursing task delay detection module detects the completion progress of the nursing staff's current task in real time during the execution of nursing services, and triggers a dynamic adjustment process when it detects that the task service time exceeds the set threshold;

[0049] During the execution of nursing services, real-time detection of the completion progress of the nursing staff's current task can be achieved through data collection and model calculation. The system first collects real-time data related to the task through the nursing staff's mobile terminal device, including the task start time, expected completion time, nursing status update (such as "nursing" and "completed"), and changes in the geographical location of the nursing staff and the patient. After the collected data is transmitted to the platform background via the Internet, the system uses the time progress model to calculate the theoretical progress of the task, and estimates the completion ratio of the task based on the ratio of the current time to the expected completion time. At the same time, the nursing staff actively submits the task status update through the terminal. The system combines these inputs to calculate the actual completion of the task and compares it with the theoretical progress, so as to judge the specific progress of the task completion in real time.

[0050] After detecting that the extended service time of the task exceeds the set threshold, the dynamic adjustment process can be triggered through delay detection and automatic event triggering. The system first dynamically sets the delay time threshold based on the type, complexity and historical data of the nursing task, for example, setting a delay range of 5-10 minutes for a certain type of nursing task. During task execution, the system continuously monitors the deviation between the actual task time and the expected completion time. When the deviation exceeds the set threshold, the system automatically determines the task delay and passes the delay information to the task scheduling module. The task scheduling module starts the dynamic adjustment process through preset event triggers, including priority classification of affected subsequent orders, resource reallocation and task sequence optimization, and notifies nursing staff and patients about detailed information about task adjustments to ensure that delays are resolved in a timely manner.

[0051] The reason why it is necessary to detect the completion progress of nursing tasks in real time and trigger adjustments when there are delays is that nursing tasks are time-sensitive. Delays may cause time conflicts for subsequent orders, leading to overload of nursing staff and passive extension of patient waiting time. Through real-time monitoring, task delays can be captured in a timely manner and their impact can be limited to the minimum range. Triggering the dynamic adjustment process further ensures the service efficiency of subsequent orders and the rational allocation of nursing resources, while improving the system's ability to respond to emergencies, ensuring the continuity of nursing services and patient satisfaction.

[0052] The dynamic delay impact analysis module obtains the dynamic delay impact information of the current task delay on all subsequent orders in real time, analyzes it after acquisition, and generates the time impact index and priority matching index of each subsequent order;

[0053] In this embodiment, in the dynamic delay impact analysis module, the dynamic delay impact information of the current task delay on all subsequent orders is obtained in real time and preprocessed after acquisition; the task time dynamic information and task resource distribution information in the preprocessed dynamic delay impact information of the current task delay on all subsequent orders are extracted, and analyzed after extraction to generate the time impact index and priority matching index of each subsequent order respectively.

[0054] Real-time acquisition of dynamic delay impact information caused by the current task delay on all subsequent orders can be achieved through the data collection system of the nursing service platform. The system collects relevant data from multiple sources in real time, including the real-time completion progress and delay time of the current task in the nursing task management module, and calculates the delay value by comparing it with the estimated completion time of the task stored in the background database; traffic status data is connected to the interface of a third-party map service (such as a real-time navigation system) to obtain real-time driving time and traffic smoothness information from the current location of the nursing staff to the service location of subsequent orders; subsequent order data is synchronized in real time through the order management module, including order appointment time, geographical location, type and quantity of required materials, etc. All data are dynamically integrated through the task scheduling module in the background of the platform to form a complete set of dynamic delay impact information, and passed to the analysis module for subsequent processing.

[0055] The purpose of preprocessing the acquired dynamic delay impact information is to ensure the accuracy, consistency and availability of the data, thereby improving the efficiency of subsequent analysis and the accuracy of the results. The preprocessing includes the following steps: first, data cleaning is performed to remove outliers or incomplete records in the collected data, such as extremely deviated traffic time or invalid task status information, through an outlier detection algorithm (such as the 3σ rule); second, data formatting is performed to standardize the data into a unified unit (such as minutes, kilometers) and format so that it can be directly called in subsequent model calculations; third, multi-source data is synchronized to ensure that the timestamps of each data collection point are consistent to avoid analysis bias caused by data collection delays. These preprocessing steps are completed through software automation and dynamically executed with the help of data pipeline tools to ensure real-time performance and data quality, laying the foundation for the subsequent generation of time impact index and priority matching index.

[0056] In this embodiment, the logic for obtaining the time impact index of each subsequent order is as follows:

[0057] Extract the dynamic information of task time from the dynamic delay impact information of the current task delay on all subsequent orders after preprocessing, including the actual delay time of the nursing staff in performing the current task, the estimated travel time of the nursing staff to the locations of each subsequent order, and the time interval between the appointment time of each subsequent order and the completion time of the current task, and mark them as TD, TT respectively. i andTOi , TD represents the actual delay time for the nurse to perform the current task, TT i represents the estimated travel time of the nursing staff to the i-th subsequent order location, TO i represents the time interval between the appointment time of the i-th subsequent order and the completion time of the current task, i = 1, 2, 3, ..., k, k is a positive integer;

[0058] Extracting the task time dynamic information from the preprocessed dynamic delay impact information can be achieved through the background data parsing and integration module. The system first uses the data label classification algorithm to filter the fields related to "task time dynamic information" from the preprocessed data set, such as the completion time of the nursing task, the appointment time and geographical location of the subsequent order. Through specific field indexing rules, the system matches and extracts the fields related to task delays (such as the actual delay time of the task) and traffic-related fields (such as the estimated travel time), and groups the time information of different orders according to the order number (or unique identifier) ​​to ensure that the data of each order is fully associated. During the extraction process, the system also checks the integrity and validity of the data, such as checking whether the data set of each order contains the task time, travel time and appointment time at the same time. Missing data will be recorded and marked as abnormal to ensure the consistency and availability of the extracted information.

[0059] The actual delay time of the nursing staff in performing the current task is obtained through the nursing task management module. The system will compare the estimated completion time of the nursing task with the real-time completion time and calculate the actual delay time of the task in minutes. The estimated driving time of the nursing staff to each subsequent order location is obtained by connecting with the real-time traffic service interface. The traffic service interface calculates the estimated driving time in minutes based on the current location of the nursing staff and the geographical location of the subsequent order location, and updates it in real time to reflect the dynamic road conditions. The time interval between the appointment time of each subsequent order and the completion time of the current task is calculated through the time fields of the order management module and the task management module. The system first extracts the appointment time field of the subsequent order from the order management module, and reads the completion time field of the current task from the task management module. The appointment time of the subsequent order is subtracted from the completion time of the current task to calculate the time interval in minutes. These three types of data are automatically collected and updated through the synergy of each module, providing an accurate quantitative basis for subsequent analysis.

[0060] Calculate the time impact index of each subsequent order. The specific calculation formula is as follows:

[0061]

[0062] Where TII i is the time impact index of the ith subsequent order.

[0063] The calculation formula of the time impact index of each subsequent order comprehensively quantifies the impact of task delays on the time conflict of subsequent orders through multiple calculation steps, which is scientific and accurate. First, the first part of the formula The actual delay time TD of the current task is calculated by comparing the estimated travel time TT of the nursing staff to the subsequent order location. i multiplied together, reflecting the combined effect of delays and traffic on time conflicts, the TO in the denominator i ) 2 +1 uses the square of the time interval to suppress the effect of short time intervals on exponential amplification and avoid division by zero. Secondly, the second part of the formula By cubing the sum of the delay time and the travel time, the severity of the impact in the case of significant delays is further highlighted, while the logarithmic operation smoothes the amplification effect of extreme values ​​to ensure the stability of the formula. Through the combined effect of these two parts, the formula can comprehensively evaluate the comprehensive impact of delay time, traffic conditions and time intervals on subsequent orders, thereby providing a scientific basis for subsequent task scheduling and resource allocation.

[0064] Time impact index TII of the i-th subsequent order i The size of directly reflects the severity of the time conflict of the current task delay on the order. The larger the index, the greater the impact of the delay on the order. The calculation factors in the formula, such as the actual delay time of the current task and the estimated travel time of the caregiver to the subsequent order location, amplify the impact of the delay time and traffic time on the appointment time of the subsequent order, while the time interval plays a buffering role. When the time interval is small, the index will increase significantly, indicating that the order time conflict is more serious. Through the nonlinear calculation of this index, the complex relationship between factors such as delays and traffic can be quantified into comparable values, which are used to evaluate the priority of the impact of delays on subsequent orders and provide a clear decision-making basis for dynamic scheduling.

[0065] In this embodiment, the logic for obtaining the priority matching index of each subsequent order is as follows:

[0066] The task resource distribution information of the dynamic delay impact information caused by the pre-processed current task delay on all subsequent orders is extracted, including the material demand gap of each subsequent order, the total number of tasks completed by the nursing staff, the geographical straight-line distance between the location of each subsequent order and the location of the current task, and the ratio of the total number of orders to the area of ​​the nursing staff's current working area, and they are marked as RD i ,NT,DP i and DA, RD i represents the material demand gap of the ith subsequent order, NT represents the total number of tasks completed by the nursing staff, and DP irepresents the geographical straight-line distance between the location of the i-th subsequent order and the location of the current task, DA represents the ratio of the total number of orders in the nursing staff's current working area to the area of ​​the area, i = 1, 2, 3, ..., k, k is a positive integer;

[0067] Extracting the task resource distribution information from the pre-processed dynamic delay impact information can be achieved through the background data aggregation and parsing module. The system dynamically extracts fields related to task resource distribution through integration with the order management module, task management module and geographic service interface. First, the material demand and inventory fields of each order are extracted from the order management module, and the material demand gap is calculated; secondly, the task completion records of the nursing staff are extracted from the task management module and the total number of completed tasks is counted; then, the geographic location coordinates of each order are extracted through the geographic service interface, and the geographic straight-line distance is calculated in combination with the coordinates of the current task location; finally, the total number of orders in the current service area of ​​the nursing staff is counted from the order management module, and the regional order density is calculated in combination with the regional area data. During the extraction process, the system will classify and associate each type of data according to the order number or nursing staff identifier to ensure that the extracted information corresponds correctly and the data is complete.

[0068] The material demand gap of each subsequent order is calculated in real time through the order management module. The system subtracts the current inventory field from the required material quantity of each order to generate the material demand gap value of the corresponding order in pieces; the total number of tasks completed by the nursing staff is obtained through the task status record of the task management module. The system counts the number of tasks marked as "completed" in all task records of the nursing staff in units of tasks; the geographical straight-line distance between the location of each subsequent order and the location of the current task is obtained through the geographic service interface. The system uses the geographic distance formula to calculate the straight-line distance in kilometers based on the coordinates of the current task location of the nursing staff and the coordinates of the subsequent order location; the ratio of the total number of orders in the current working area of ​​the nursing staff to the area of ​​the area is jointly calculated by the order management module and the geographic information module. The system first counts the total number of orders in the specified service area, and then obtains the area value of the area from the geographic information module. The two are divided to obtain the regional order density in units of orders / square kilometer. These quantitative data are updated in real time through the automated calculation and integrated operation of the software module, providing an accurate basis for the generation of the subsequent priority matching index.

[0069] Calculate the priority matching index of each subsequent order. The specific calculation formula is as follows:

[0070]

[0071] Where PMI i is the priority matching index of the ith subsequent order.

[0072] The calculation formula of the priority matching index scientifically quantifies the importance of subsequent orders by comprehensively considering material demand, task load, geographical distance and regional order density. The first part of the formula is ln(1+RD i The marginal contribution of the material demand gap is calculated using a logarithmic function to avoid the problem of excessively large values ​​caused by directly using the demand, while emphasizing the importance of larger demand to priority. The combined influence of the number of completed tasks of the nursing staff and the geographical straight-line distance of the order is comprehensively considered. The more tasks the nursing staff has completed, the higher their task load is, which reduces the priority of subsequent orders; the longer the geographical distance, the lower the priority, while the square root operation mitigates the extreme negative impact of long-distance orders on priority. Finally, (DA+1) amplifies the impact of the average order density of the region, and the orders in the high order density region have higher priority to optimize the allocation efficiency of nursing resources. The overall formula design comprehensively quantifies the impact of multiple factors on order priority through multiple nonlinear operations and smoothing control, ensures the scientificity and practicality of the calculation results, and provides an accurate basis for task scheduling.

[0073] The priority matching index PMI of the i-th subsequent order i The size of the index directly reflects the importance of the order and the urgency of resource allocation in the context of current task delays. The larger the index, the more priority the order should be given in the allocation of nursing resources. Specifically, the index combines the gap in material demand and the regional order density to quantify the resource tension and order pressure in the service area that may be caused by delays; at the same time, it reflects the load of nursing resources and service accessibility through the joint trade-off between the number of tasks completed by nursing staff and the geographical distance. The size of the priority matching index comprehensively considers the direct and indirect impact of delays on resource allocation, provides an objective basis for evaluating the priority order of delays in subsequent orders, and ensures the efficiency and fairness of resource allocation.

[0074] The delay impact assessment and priority classification module builds a delay impact assessment model for the time impact index and priority matching index of each subsequent order, generates a delay assessment coefficient for each subsequent order, and analyzes it after generation to assess the impact of the nursing staff's delay in the current task on each subsequent order, and divides the subsequent orders into high-priority orders, medium-priority orders, and low-priority orders based on the assessment results;

[0075] In this embodiment, in the delay impact assessment and priority classification module, a delay impact assessment model is constructed based on the time impact index and priority matching index of each subsequent order generated, and a delay assessment coefficient of each subsequent order is generated, which specifically includes the following steps:

[0076] Collect the time impact index, priority matching index and corresponding delay assessment coefficient of several subsequent orders generated in the past period of time, and mark them as and x represents the time impact index, priority matching index and corresponding delay assessment coefficient number of each subsequent order generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time is formed into a historical data set;

[0077] The collection of the time impact index, priority matching index and corresponding delay assessment coefficient of several subsequent orders generated in the past period of time can be achieved through the background data storage and log management module. Each time the system dynamically evaluates the impact of task delays on subsequent orders, it will automatically store the calculated time impact index, priority matching index and delay assessment coefficient in the history record table of the database. The record includes fields such as the unique identifier of each order, the generation timestamp, the relevant calculation parameters and the result value. In order to collect data from the past period of time, the system sets the time range (such as the past 30 days) through the query function, and filters out all qualified historical records from the database. The query results will be grouped by order number. Each group of data contains a complete record of the time impact index, priority matching index and delay assessment coefficient of the order, and can be sorted in chronological order to ensure the continuity and integrity of the data. To further improve the data quality, the system can also automatically check the integrity and consistency of the data during the query process, for example, confirm whether each record contains and The three values ​​are combined and missing or abnormal data are marked to provide a high-quality historical data set for model training.

[0078] It is very necessary to limit the value range of x to positive integers greater than or equal to 3. Such a limitation ensures the mathematical solvability of the regression model. Three regression coefficients (β0, β1, and β2) need to be calculated in the target equation, so at least three independent historical data points (i.e., x≥3) are required to form three equations and constitute a solvable linear equation system. This requirement is the basis for regression model training, because the number of data points must not be less than the number of model coefficients to ensure the solvability of the model. At the same time, ensuring x≥3 can also avoid the risk of overfitting: if the number of data points is less than the number of regression coefficients, the model may not be able to correctly capture the real laws in the historical data, resulting in inaccurate training results. In addition, x is limited to a positive integer because the number of data points is essentially a discrete value with integer characteristics in the physical sense. In general, such a range setting not only satisfies mathematical solvability, but also ensures the logical rationality of model training and the practical significance of the data.

[0079] The multivariate regression model is selected as the delay impact assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0080]

[0081] Where β0, β1 and β2 are regression coefficients;

[0082] The multivariate regression model is a statistical modeling method used to quantify the combined impact of multiple independent variables (such as the time impact index and the priority matching index) on the dependent variable (delay assessment coefficient) and express the relationship between the variables in the form of a linear equation. The multivariate regression model was chosen as the delay impact assessment model because it can flexibly handle multiple influencing factors and quantify the time delay and priority characteristics as specific contributions to the assessment results. At the same time, the weight of each influencing factor can be determined by training the model with historical data, making the model more in line with the actual situation. The three regression coefficients in the regression model have clear meanings: β0 is a constant term, which means that when and are all the baseline delay assessment values ​​at zero; β1 is the regression coefficient of the time impact index, which quantifies the relative contribution of time delay to the assessment result; β2 is the regression coefficient of the priority matching index, which reflects the impact of order priority characteristics on the assessment result. By minimizing the error between the model prediction value and the actual value, the training process can optimize these coefficients and ultimately generate a mathematical model that can accurately assess the impact of delays.

[0083] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0084] Optimizing the regression coefficient by minimizing the error between the model prediction value and the actual value is to ensure that the regression model fits the historical data to the highest degree, thereby improving the model's prediction accuracy. The specific implementation method is to use historical data sets, which include actual delay assessment coefficients and corresponding time impact indexes and priority matching indexes. The system calculates the model prediction value based on the initial regression coefficients β0, β1, and β2, and then calculates the error between the predicted value and the actual value through an error function (such as mean square error, MSE). Through optimization algorithms (such as gradient descent), the system gradually adjusts the value of the regression coefficient so that the value of the error function tends to be minimized. This process is automatically completed by the training module in the software, and the optimized regression coefficient can capture the greatest extent. and right The real impact relationship of the delay assessment is obtained, thereby generating an accurate and stable delay assessment model, ensuring that the model can generate reliable assessment results based on real-time data in practical applications.

[0085] Using the finalized regression coefficient, the delay impact assessment model is constructed and the time impact index TII of each subsequent order generated in real time is input. i and priority matching index PMI i , generate the delay evaluation coefficient DEC of each subsequent order in real time i .

[0086] In this embodiment, the delay evaluation coefficient DEC of each subsequent order generated is i The delay assessment coefficient threshold interval [DEC min ,DEC max ] to compare, and evaluate the impact of the nursing staff's delay in the current task on each subsequent order based on the comparison results, and divide each subsequent order into high priority orders, medium priority orders and low priority orders based on the evaluation results. The specific comparison analysis and division are as follows:

[0087] If DEC i <DEC min , if the impact of the delay of the nursing staff in the current task on the subsequent order is low, the subsequent order is classified as a low priority order;

[0088] This situation means that the delay of the nursing staff's current task has a low impact on subsequent orders, and will hardly cause significant interference to the appointment time, resource allocation or task sequence of subsequent orders. In this case, the service schedule of subsequent orders remains basically stable, the scheduling of nursing resources does not need to be significantly adjusted, and the nursing staff can continue to perform tasks as originally planned. This low-impact result helps maintain the normal operation of the nursing system, avoids unnecessary waste of resources due to excessive intervention, and improves the efficiency and responsiveness of the system.

[0089] If DEC min ≤DEC i ≤DEC max , if the impact of the delay of the nursing staff in the current task on the subsequent order is medium, then the subsequent order is classified as a medium priority order;

[0090] This situation indicates that the delay of the nursing staff's current task has a moderate impact on subsequent orders, and the delay may cause slight deviations in the service time of some subsequent orders or slightly uneven resource allocation. In this case, the system needs to make moderate adjustments to the scheduling and resource allocation of subsequent orders, such as optimizing the priority of tasks or deploying additional nursing resources when necessary to alleviate conflicts. This moderate impact may increase the short-term burden of nursing staff or cause patients to wait slightly longer, but through timely adjustments, the impact of delays on service quality can be alleviated to a certain extent.

[0091] If DECi >DEC max , if the impact of the nursing staff's delay in the current task on the subsequent order is high, the subsequent order is classified as a high-priority order.

[0092] This situation shows that the delay of the nursing staff's current task has a high degree of impact on subsequent orders. The delay may cause serious conflicts in the service time of subsequent orders, the resource scheduling cannot meet the demand, and even there is a risk that some tasks cannot be completed on time. In this case, the system must focus on adjusting the priority of subsequent orders, such as giving priority to high-priority orders, and taking measures to postpone or reschedule low-priority orders. In addition, it may be necessary to reallocate nursing staff or introduce more resources to deal with emergencies. This high-impact result will significantly increase patient waiting time or service delays, thereby reducing patient satisfaction, but through active dynamic adjustments, the negative impact of delays on overall nursing services can be minimized.

[0093] The pre-set delay assessment factor threshold range [DEC min ,DEC max ] can be determined through historical data analysis and statistical modeling. Specifically, the system first extracts the delay assessment coefficients of all subsequent orders in the historical records from the database, and classifies and sorts them according to conditions such as task type, service area, resource allocation, etc. to ensure the representativeness of the data. Then, the system uses statistical analysis methods (such as distribution fitting or quantile analysis) to process the data. For example, by calculating the overall distribution of the delay assessment coefficient, the data is divided into three levels: the value of the lower quantile (such as 25%) is used as the DEC min , the upper quantile (such as 75%) value is used as DEC max In order to meet actual needs, the interval boundaries can also be fine-tuned by adjusting the ratio of quantiles or combining expert settings to reflect the delay impact characteristics in specific scenarios. This process can be completed automatically through software. After determining the threshold interval, the system stores it in the configuration file for real-time evaluation, thereby ensuring the scientificity, adaptability and operability of the threshold.

[0094] The subsequent order adjustment decision module takes corresponding adjustment measures for high-priority orders, medium-priority orders and low-priority orders according to the classification results of each subsequent order;

[0095] In this embodiment, in the subsequent order adjustment decision module, according to the classification results of each subsequent order, corresponding adjustment measures are taken for high priority orders, medium priority orders and low priority orders respectively, specifically:

[0096] For subsequent orders classified as low-priority orders, the specific adjustment measures are as follows: prioritize delaying their planned service time and arranging them to a time period when nursing staff have fewer tasks to perform, so as to reduce interference with current nursing tasks; and mark their service plans as standby when resources are tight, and deploy them after the priority orders are completed. At the same time, the service needs of low-priority orders are continuously monitored to ensure that they will not affect the overall service level of the system;

[0097] The adjustment of low-priority orders can be achieved through the task scheduling module of the nursing service system. According to the division results, the system dynamically marks the service time of low-priority orders as "delayable", and calculates the available time window of nursing staff during non-peak task periods (such as time periods with low load) through the time adjustment algorithm, and reallocates service time for the order. At the same time, when resources are tight, the system will mark low-priority orders as "standby status", temporarily suspend them through the task priority queue in the database, and wait for the high-priority orders to be processed before starting the scheduling of the order. In addition, the system will monitor the changes in service demand for low-priority orders in real time, and check whether the order status needs to be upgraded to medium priority through a timed refresh mechanism. This method effectively avoids the interference of low-priority orders on current nursing resources, ensures that high- and medium-priority orders can be completed smoothly, and reduces the waste of system resources.

[0098] For subsequent orders classified as medium priority orders, the specific adjustment measures are as follows: according to the preset task scheduling rules, service time is allocated within the scope of existing nursing staff resources, and the service sequence is dynamically optimized to ensure efficient use of resources. At the same time, the priority status of the order is periodically reviewed in combination with real-time data, and adjusted to high or low priority when necessary to adapt to changes in system load;

[0099] The adjustment of medium-priority orders is achieved through the task optimization and priority dynamic update module. The system allocates appropriate service time for medium-priority orders according to the preset task scheduling rules, and dynamically adjusts the service order based on the current task status, geographical distribution and expected completion time of the nursing staff. For example, the system can re-sort the execution priority of medium-priority orders according to the delay assessment coefficient to avoid service time conflicts. At the same time, the system uses a periodic evaluation mechanism to collect delay impact data and nursing resource conditions in real time, re-evaluate the classification results of medium-priority orders, and upgrade the orders to high priority or downgrade them to low priority when necessary. This adjustment method can optimize resource allocation without significantly increasing the burden on nursing resources, ensuring service efficiency while improving the flexibility and accuracy of order processing.

[0100] For subsequent orders that are classified as high-priority orders, the specific adjustment measures taken are: giving priority to ensuring their service time and resource allocation, providing nursing resources for high-priority orders by deploying additional nursing staff and adjusting the service plans of medium and low-priority orders, and monitoring the service status in real time to ensure that high-priority orders can be completed on time, so as to reduce the risk of patient dissatisfaction and reduced care quality due to delays.

[0101] The adjustment of high-priority orders is achieved through the resource scheduling and monitoring module. Based on the division results, the system prioritizes the allocation of nursing staff and other required resources to high-priority orders, and calls on spare nursing resources (such as adding temporary nursing staff or calling unallocated resource pools) when necessary to ensure service execution. At the same time, the system will adjust the planned service time of low- and medium-priority orders to prioritize the freeing up of resources for the processing of high-priority orders. The real-time monitoring module continuously monitors the service progress of high-priority orders, including task execution status, changes in the impact of delays, etc., identifies potential risks in advance through predictive models (such as the further impact of delays on subsequent orders), and triggers dynamic adjustments in a timely manner. This approach can minimize the impact of delays on critical tasks, reduce patient dissatisfaction, and improve the overall quality and reliability of nursing services.

[0102] The real-time monitoring and optimization module continuously monitors the execution status of nursing tasks and resource allocation information, and dynamically optimizes the delay impact assessment model and task adjustment strategy based on the real-time monitoring results. At the same time, it stores and analyzes historical adjustment data to optimize model parameters and strategy settings, thereby improving the long-term adaptability and adjustment efficiency of the system.

[0103] Real-time monitoring of nursing task execution status and resource allocation information can be achieved through the real-time data collection and monitoring module of the nursing service system. The system dynamically collects nursing staff's task execution status (such as current task progress, delay time, etc.) and resource allocation information (such as current nursing resource utilization rate, available resource quantity, etc.) through the real-time data interface of the nursing task management module and the resource scheduling module. For example, the execution status of nursing tasks can be uploaded in real time through the nursing staff's mobile application, including task start time, estimated completion time and actual completion time; resource allocation information is generated through the system's integrated analysis of nursing staff's task allocation records, real-time geographic location and resource usage. The collected data is processed in real time by the background task status monitoring engine and displayed in a visual form in the system dashboard, providing an accurate data basis for subsequent optimization.

[0104] Dynamic optimization of the delay impact assessment model and task adjustment strategy can be achieved through the model update and strategy optimization module. Based on the real-time monitored task execution status and resource allocation information, the system dynamically adjusts the parameters of the delay impact assessment model, such as retraining the multivariate regression model according to the latest data and optimizing the regression coefficient so that the model can more accurately reflect the impact of the current task delay on subsequent orders. At the same time, the task adjustment strategy module combines real-time data for optimization, such as dynamically adjusting the service plan according to the real-time task load and resource allocation status of the nursing staff, prioritizing the allocation of resources for high-priority orders, and reordering the execution order of medium and low-priority orders. In this way, the system can respond to changes in real time during task execution, ensure the applicability of the evaluation model, and improve the flexibility and efficiency of task scheduling.

[0105] The purpose of real-time monitoring and optimization of nursing task execution status and resource allocation information is to ensure that the system can dynamically adapt to the complex changes in task execution and resource allocation in nursing scenarios. Delays are often real-time and unpredictable, and only through continuous monitoring can these changes be accurately captured and responded to immediately. In addition, by dynamically optimizing the delay impact assessment model and task adjustment strategy, the accuracy of assessment and scheduling can be improved, ensuring that high-priority orders are given priority while reducing the risk of delays for medium and low-priority orders. The storage and analysis of historical adjustment data further provides data support for the system. By analyzing and summarizing past optimization measures, the scientificity and reliability of model parameters and strategy settings can be continuously improved, thereby enhancing the long-term adaptability of the system and improving the overall operating efficiency and patient satisfaction of nursing services.

[0106] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0107] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0108] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0109] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0110] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0113] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A health care service system based on the Internet, characterized in that: It includes nursing task delay detection module, dynamic delay impact analysis module, delay impact assessment and priority classification module, subsequent order adjustment decision module and real-time monitoring and optimization module; The nursing task delay detection module detects the completion progress of the nursing staff's current task in real time during the execution of nursing services, and triggers a dynamic adjustment process when it detects that the task service time exceeds the set threshold; The dynamic delay impact analysis module obtains the dynamic delay impact information of the current task delay on all subsequent orders in real time, analyzes it after acquisition, and generates the time impact index and priority matching index of each subsequent order; The delay impact assessment and priority classification module builds a delay impact assessment model for the time impact index and priority matching index of each subsequent order, generates a delay assessment coefficient for each subsequent order, and analyzes it after generation to assess the impact of the nursing staff's delay in the current task on each subsequent order, and divides the subsequent orders into high-priority orders, medium-priority orders, and low-priority orders based on the assessment results; The subsequent order adjustment decision module takes corresponding adjustment measures for high-priority orders, medium-priority orders and low-priority orders according to the classification results of each subsequent order; The real-time monitoring and optimization module continuously monitors the execution status of nursing tasks and resource allocation information, and dynamically optimizes the delay impact assessment model and task adjustment strategy based on the real-time monitoring results. At the same time, it stores and analyzes historical adjustment data to optimize model parameters and strategy settings, thereby improving the long-term adaptability and adjustment efficiency of the system.

2. The Internet-based health care service system according to claim 1, characterized in that: In the dynamic delay impact analysis module, the dynamic delay impact information of the current task delay on all subsequent orders is obtained in real time and preprocessed after acquisition; the task time dynamic information and task resource distribution information in the preprocessed dynamic delay impact information of the current task delay on all subsequent orders are extracted and analyzed after extraction to generate the time impact index and priority matching index of each subsequent order respectively.

3. The Internet-based health care service system according to claim 2, characterized in that: The logic for obtaining the time impact index of each subsequent order is as follows: Extract the dynamic information of task time from the dynamic delay impact information of the current task delay on all subsequent orders after preprocessing, including the actual delay time of the nursing staff in performing the current task, the estimated travel time of the nursing staff to the locations of each subsequent order, and the time interval between the appointment time of each subsequent order and the completion time of the current task, and mark them as TD, TT respectively. i andTO i , TD represents the actual delay time for the nurse to perform the current task, TT i represents the estimated travel time of the nursing staff to the i-th subsequent order location, TO i represents the time interval between the appointment time of the i-th subsequent order and the completion time of the current task, i = 1, 2, 3, ..., k, k is a positive integer; Calculate the time impact index of each subsequent order. The specific calculation formula is as follows: Where TII i is the time impact index of the ith subsequent order.

4. The Internet-based health care service system according to claim 3, characterized in that: The logic for obtaining the priority matching index of each subsequent order is as follows: The task resource distribution information of the dynamic delay impact information caused by the pre-processed current task delay on all subsequent orders is extracted, including the material demand gap of each subsequent order, the total number of tasks completed by the nursing staff, the geographical straight-line distance between the location of each subsequent order and the location of the current task, and the ratio of the total number of orders to the area of ​​the nursing staff's current working area, and they are marked as RD i ,NT,DP i and DA, RD i represents the material demand gap of the ith subsequent order, NT represents the total number of tasks completed by the nursing staff, and DP i represents the geographical straight-line distance between the location of the i-th subsequent order and the location of the current task, DA represents the ratio of the total number of orders in the nursing staff's current working area to the area of ​​the area, i = 1, 2, 3, ..., k, k is a positive integer; Calculate the priority matching index of each subsequent order. The specific calculation formula is as follows: Where PMI i is the priority matching index of the ith subsequent order.

5. The Internet-based health care service system according to claim 4, characterized in that: In the delay impact assessment and priority classification module, a delay impact assessment model is constructed for the time impact index and priority matching index of each subsequent order generated, and a delay assessment coefficient of each subsequent order is generated, which specifically includes the following steps: Collect the time impact index, priority matching index and corresponding delay assessment coefficient of several subsequent orders generated in the past period of time, and mark them as and x represents the time impact index, priority matching index and corresponding delay assessment coefficient number of each subsequent order generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time is formed into a historical data set; The multivariate regression model is selected as the delay impact assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula: Where β0, β1 and β2 are regression coefficients; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined; Using the finalized regression coefficient, the delay impact assessment model is constructed and the time impact index TII of each subsequent order generated in real time is input. i and priority matching index PMI i , generate the delay evaluation coefficient DEC of each subsequent order in real time i .

6. The Internet-based health care service system according to claim 5, characterized in that: The delay evaluation coefficient DEC of each subsequent order generated i The delay assessment coefficient threshold interval [DEC min ,DEC max ] to compare, and evaluate the impact of the nursing staff's delay in the current task on each subsequent order based on the comparison results, and divide each subsequent order into high priority orders, medium priority orders and low priority orders based on the evaluation results. The specific comparison analysis and division are as follows: If DEC i <DEC min , if the impact of the delay of the nursing staff in the current task on the subsequent order is low, the subsequent order is classified as a low priority order; If DEC min ≤DEC i ≤DEC max , if the impact of the delay of the nursing staff in the current task on the subsequent order is medium, then the subsequent order is classified as a medium priority order; If DEC i >DEC max , if the impact of the nursing staff's delay in the current task on the subsequent order is high, the subsequent order is classified as a high-priority order.

7. The Internet-based health care service system according to claim 6, characterized in that: In the subsequent order adjustment decision module, according to the classification results of each subsequent order, corresponding adjustment measures are taken for high priority orders, medium priority orders and low priority orders respectively, specifically: For subsequent orders classified as low-priority orders, the specific adjustment measures are as follows: prioritize delaying their planned service time and arranging them to be executed during the time period when nursing staff have fewer tasks to reduce interference with current nursing tasks; and mark their service plans as standby when resources are tight, and deploy them after the priority orders are completed, while continuously monitoring the service needs of low-priority orders; For subsequent orders classified as medium priority orders, the specific adjustment measures are as follows: according to the preset task scheduling rules, service time is allocated within the scope of existing nursing staff resources, and the service sequence is dynamically optimized to ensure efficient use of resources. At the same time, the priority status of the order is periodically reviewed in combination with real-time data; For subsequent orders that are classified as high-priority orders, the specific adjustment measures taken are: giving priority to ensuring their service time and resource allocation, providing nursing resources for high-priority orders by deploying additional nursing staff and adjusting the service plans of medium and low-priority orders, and monitoring the service status in real time to ensure that high-priority orders can be completed on time, so as to reduce the risk of patient dissatisfaction and reduced care quality due to delays.

Images