A wisdom integrated hospital treatment service comprehensive platform

Abstract

This invention discloses a smart integrated hospital service platform, belonging to the field of digital integrated management platform technology. It includes a data interaction layer, an intelligent decision-making layer, a service execution layer, and an external expansion layer. By integrating patient treatment information with multi-dimensional hospital operation data, this invention achieves intelligent collaboration throughout the entire process. Relying on the multi-dimensional analysis mechanism of the intelligent decision-making layer, it accurately estimates waiting time, dynamically plans routes, and recommends personalized resources. Combined with waiting reminders, spatial navigation, and one-stop service processing functions in the service execution layer, it reduces unnecessary gatherings and travel within the hospital. Simultaneously, through personalized services such as barrier-free navigation and transparent drug information, it meets the needs of different patients. The external expansion layer connects to surrounding office, leisure, and parking facilities, linking with in-hospital medical services to form a collaborative system, effectively utilizing patient waiting time and enriching service dimensions.

Description

Technical Field

[0001] This invention relates to the field of digital integrated management platform technology, and in particular to a smart integrated hospital medical service platform. Background Technology

[0002] Currently, hospital services still face numerous pain points that urgently need to be addressed, severely impacting patient experience and hospital operational efficiency. On one hand, patients often face long and uncertain wait times after registration. Crowded waiting areas not only increase the risk of cross-infection but also easily lead to missed appointments and re-queueing due to noise. The mixing of first-time and follow-up patients further prolongs waiting times, making it difficult for patients to plan their trips effectively. On the other hand, large hospital campuses have complex layouts with departments, examination rooms, and payment windows scattered throughout. Patients, especially the elderly and those with special needs, often find themselves running around due to unclear directions and are unclear about the next steps and locations after their initial consultation, wasting significant time and energy. Furthermore, insufficient transparency regarding medication information makes it difficult for patients to understand drug details, leading to medication confusion or waste. Meanwhile, problems such as parking difficulties and inefficient use of waiting time are prominent. Existing hospital service systems are mostly limited to core diagnostic and treatment processes, lacking comprehensive, multi-dimensional intelligent collaborative services, and failing to meet patients' diverse and convenient medical needs. Summary of the Invention

[0003] The purpose of this invention is to provide a smart integrated hospital medical service platform to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a smart integrated hospital medical service platform, comprising a data interaction layer, an intelligent decision-making layer, a service execution layer, and an external expansion layer; The data interaction layer is used to establish a two-way data channel between the patient terminal and the hospital's core system, acquire multi-dimensional data, and realize the real-time collection and transmission of patient diagnosis and treatment information and hospital operation data. The intelligent decision-making layer analyzes and processes the multi-dimensional data obtained from the data interaction layer through a preset algorithm model to generate decision results covering medical time management, route planning, resource allocation, and personalized recommendations. The service execution layer provides patients with full-process medical assistance services based on the decision results output by the intelligent decision layer. These medical assistance services include waiting reminders, spatial navigation, business processing, and information inquiry. The external extension layer connects to external related service resources of the hospital through standardized interfaces, enabling coordinated linkage between medical services and surrounding supporting services.

[0005] Furthermore, the patient medical information collected by the data interaction layer includes the patient's identity information associated with their ID card or medical insurance card, historical medical records, examination reports, medication records, current registration type, and registration department information; The collected hospital operation data includes doctor job categories, statistics on doctors' historical consultation time, current patient queue length, real-time patient flow in various areas of the hospital, idle status of consultation rooms and examination equipment, pharmacy drug inventory and unit price, parking space usage in the hospital parking lot, and data on surrounding public parking resources.

[0006] Furthermore, the specific implementation process of the intelligent decision-making layer's visit time management function is as follows: Based on the doctor's job category, the basic time benchmark for the corresponding diagnosis and treatment scenario is determined. Combined with the average diagnosis and treatment time for the same disease type in the doctor's historical consultation data, the unit diagnosis and treatment efficiency of the doctor is calculated. Count the number of patients preceding the current doctor's consultation queue, and distinguish between first-time patients and returning patients among the preceding patients; Based on the combined effects of the doctor's unit's treatment efficiency, the number of previous patients, and the time differences corresponding to patient types, the estimated waiting time for the current patient is calculated, and real-time patient flow data within the hospital is simultaneously linked. If the patient flow in the area where the current department is located exceeds the preset carrying capacity threshold, the waiting time buffer value is increased.

[0007] Furthermore, the estimated waiting time for current patients is calculated, specifically including: Extract the job category information of the target doctor, and determine the basic consultation time benchmark for the doctor based on the correspondence between the hospital's preset job categories and the basic time benchmark. Retrieve the target doctor's historical consultation data for the past 3 months, filter out the medical records that match the current patients' disease types, calculate the actual treatment time of these records, and take the average value as a reference value for the doctor's unit treatment efficiency for this disease type; Obtain real-time data of the target doctor's current patient queue, count the total number of patients waiting in line, identify the type of each patient in line, and count the number of first-time patients and returning patients in line. Based on preset rules, time weights are assigned to first-time patients and returning patients. The time weight for first-time patients is higher than that for returning patients. Combining the number of preceding first-time patients, the number of returning patients, and their corresponding time weights, the estimated total treatment time for preceding patients is calculated. By combining the reference value of the unit diagnosis and treatment efficiency of the target doctor, the estimated total diagnosis and treatment time of the preceding patients is corrected to obtain the basic time required for the overall diagnosis and treatment of the preceding patients. The system retrieves real-time patient flow data for the current department's area and compares it with the preset capacity threshold for that area. If the real-time patient flow exceeds the capacity threshold, the system increases the corresponding time buffer based on the excess ratio, ultimately obtaining the estimated waiting time for the current patient.

[0008] Furthermore, the waiting reminder function of the service execution layer specifically includes: After the intelligent decision-making layer generates the estimated waiting time, it automatically pushes the waiting time notification to the patient's terminal. The patient can choose to wait in the hospital or leave the hospital temporarily based on the time. If the patient chooses to leave the hospital temporarily, the system needs to authorize access to the patient's terminal location function to obtain the patient's current location and distance from the hospital in real time, and combine it with mainstream map navigation data to calculate the estimated arrival time under different modes of transportation. The system monitors the distance between the patient's terminal and the hospital in real time and the estimated arrival time. When the estimated arrival time is longer than the remaining waiting time, it sends an expedited reminder to the patient's terminal and updates the dynamic changes in the current waiting queue. If the treatment progress of the preceding patient is accelerated or there is a temporary additional treatment, the reminder time is adjusted. The platform refreshes and displays the estimated waiting time updates in real time, and the reasons for the adjustments are also noted in the updates.

[0009] Furthermore, the spatial navigation function of the service execution layer is specifically implemented as follows: A three-dimensional navigation map is constructed based on the coordinates of the patient's current location and the target location, combined with the hospital's indoor and outdoor spatial layout data. Based on real-time data on pedestrian density at various passages and elevator entrances within the hospital, the optimal travel route is planned to avoid congested areas, prioritizing passages with pedestrian flow below the preset congestion threshold during the route planning process. Navigation is based on the optimal travel path. During navigation, changes in pedestrian flow along the path ahead are monitored in real time. If a sudden congestion occurs on the original planned path, the optimal path is automatically recalculated and pushed to the patient's terminal simultaneously. The reason for the path change is also provided through voice or text prompts.

[0010] Furthermore, the service execution layer's business processing functions include inspection appointments and parking appointments, the specific process of which is as follows: After the doctor issues the examination order and the patient completes the payment, an examination appointment QR code with a unique identifier is automatically generated. The examination appointment QR code can be scanned to enter the appointment interface, which displays the available appointment time slots for the current examination equipment, the remaining appointment slots for each time slot, and the location information of the examination room. After the patient selects the target time slot and completes the appointment, a successful appointment notification is sent. The successful appointment notification includes the examination time, the location of the examination room, and precautions before the examination. An appointment reminder is also sent 1 hour before the examination. Based on historical parking data during the patient's registration period, the average parking space utilization rate and the number of vacant parking spaces in the hospital parking lot during that period are calculated to generate an estimated result of available parking spaces. After a patient initiates a parking reservation through their patient terminal, they can select a reservation mode, which includes an instant billing mode or an overdue billing mode.

[0011] Furthermore, the parking reservation function also includes alternative solutions when there are insufficient parking spaces within the compound, specifically: When the number of available parking spaces in the parking lot is detected to be lower than a preset threshold, a recommendation of nearby parking resources is triggered. By accessing the resource data of public parking lots and commercial complex parking lots within a 1-kilometer radius of the hospital through an external extension layer, the system displays the real-time number of available parking spaces, pricing, walking time from the hospital, and reservation methods for each alternative parking lot. The system pushes the parking lot's contact number and real-time parking space update frequency, and displays the parking space information on the patient's terminal, including the navigation route and parking space number.

[0012] Furthermore, the information query function of the service execution layer includes drug information query, and the specific implementation process is as follows: After the doctor completes the prescription and submits it to the hospital system, the prescription details are obtained in real time through the data interaction layer. The prescription details include the type, specifications, quantity, unit price, usage and dosage of the drug, and the corresponding drug inventory status. Simultaneously retrieve high-resolution photos of the drug, ingredient descriptions, indications, common adverse reactions, and precautions from the drug database and display them on the patient's terminal interface in a combination of text and images; After viewing the medication information on the patient's terminal, a selection window is generated, allowing the patient to choose to confirm use or return the medication. If the patient selects to confirm use, the prescription will be automatically submitted to the pharmacy for dispensing; if the patient selects to return the medication, the return will be completed and the prescription cancelled after the patient confirms twice on their terminal.

[0013] Furthermore, the external extension layer accesses hospital-related service resources including office spaces, leisure and entertainment venues, catering establishments, and tourist attractions. The specific service process is as follows: When a patient chooses to wait outside the hospital, the platform uses the patient's authorized location information and estimated waiting time to filter external service resources that are within a reasonable range of the hospital and whose business hours cover the patient's waiting time. External resources are sorted and displayed based on patients' historical usage preferences or the types of services they actively choose. The displayed content includes resource name, specific location, user rating, appointment method, and travel time to and from the hospital. Patients can directly book their target resources through the platform, and the booking time will be recorded synchronously after a successful booking.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention integrates patient diagnosis and treatment information with multi-dimensional data from hospital operations by constructing a four-layer architecture consisting of a data interaction layer, an intelligent decision-making layer, a service execution layer, and an external expansion layer. This enables intelligent collaboration throughout the entire process, breaks down information barriers and process fragmentation in medical services, improves hospital operational efficiency, optimizes resource allocation, and provides patients with a closed-loop service from registration to discharge. It effectively solves pain points such as information opacity and cumbersome processes, and significantly improves the intelligence and refinement of medical services.

[0015] 2. This invention relies on the multi-dimensional analysis mechanism of the intelligent decision-making layer to accurately estimate waiting time, dynamically plan routes, and recommend personalized resources. Combined with waiting reminders, spatial navigation, and one-stop business processing functions in the service execution layer, it allows patients to clearly grasp the progress of their medical treatment, rationally arrange their itinerary, and reduce unnecessary gatherings and travel within the hospital. At the same time, through personalized services such as barrier-free navigation and transparent drug information, it meets the needs of different patients, greatly alleviates anxiety about seeking medical treatment, and improves the comfort and convenience of the medical experience.

[0016] 3. This invention connects to supporting service resources such as offices, leisure facilities, and parking around the hospital through an external extension layer, forming a collaborative system with the hospital's medical services. This effectively utilizes patients' waiting time, enriches service dimensions, alleviates hospital space pressure, reduces resource waste, and the cross-platform appointment and resource integration design further expands service coverage and convenience, achieving a win-win situation for hospitals, patients, and surrounding resources, and promoting the upgrading of medical services towards diversification and humanization. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the waiting time estimation and reminder process of the present invention; Figure 2 This is a schematic diagram of the entire process of medical visit navigation and business processing of the present invention; Figure 3 This is a schematic diagram of the parking reservation process of the present invention; Figure 4 This is a schematic diagram of the external resource utilization process of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figure 1-3 The present invention provides the following technical solutions: A smart integrated hospital service platform, comprising a data interaction layer, an intelligent decision-making layer, a service execution layer, and an external expansion layer; The data interaction layer is used to establish a two-way data channel between the patient terminal and the hospital's core system, acquire multi-dimensional data, and realize the real-time collection and transmission of patient diagnosis and treatment information and hospital operation data. The intelligent decision-making layer analyzes and processes multi-dimensional data obtained from the data interaction layer through a preset algorithm model to generate decision results covering medical time management, route planning, resource allocation, and personalized recommendations. Based on the decision results output by the intelligent decision-making layer, the service execution layer provides patients with full-process medical assistance services, including waiting reminders, spatial navigation, business processing, and information inquiry. The external extension layer connects to external related service resources of the hospital through standardized interfaces, enabling coordinated linkage between medical services and surrounding supporting services.

[0020] In the above embodiments, by constructing a four-layer architecture consisting of a data interaction layer, an intelligent decision-making layer, a service execution layer, and an external expansion layer, deep integration and efficient collaboration between patient diagnosis and treatment information and hospital operation data are achieved. The data interaction layer ensures real-time communication of multi-dimensional data. The intelligent decision-making layer uses a preset algorithm model to deeply mine the data and generate accurate decision results, avoiding the subjectivity and lag of relying on manual judgment in traditional medical services. The service execution layer transforms the decision results into full-process medical assistance services, covering the full-scenario needs of patients from registration to discharge. The external expansion layer integrates external supporting service resources through standardized interfaces, breaking down the separation between medical services and surrounding services, forming a closed-loop medical service system, improving the intelligence level and operational efficiency of hospital medical services, and greatly optimizing the patient's medical experience, solving the problems of opaque information, inefficient processes, and limited services in the medical service model.

[0021] The patient diagnosis and treatment information collected by the data interaction layer includes the patient's identity information associated with their ID card or medical insurance card, historical medical records, examination reports, medication records, current registration type and registration department information; The collected hospital operation data includes doctor job categories, statistics on doctors' historical consultation time, current patient queue length, real-time patient flow in various areas of the hospital, idle status of consultation rooms and examination equipment, pharmacy drug inventory and unit price, parking space usage in the hospital parking lot, and data on surrounding public parking resources.

[0022] In the above embodiments, the data interaction layer meticulously collects patient diagnosis and treatment information and hospital operation data. By collecting comprehensive diagnosis and treatment information associated with patient ID cards or medical insurance cards, it can accurately grasp the patient's health status and medical needs, providing a basis for personalized services. Meanwhile, the comprehensive collection of hospital operation data, including doctor diagnosis and treatment data, in-hospital resource status data, parking space and drug inventory data, enables the platform to monitor the hospital's operational status in real time and comprehensively reflect various influencing factors in medical services. This ensures that the results generated by the subsequent intelligent decision-making layer are more in line with actual needs, effectively improving the accuracy and relevance of services, while also providing data support for the collaborative linkage of various service modules.

[0023] The intelligent decision-making layer's medical appointment time management function is implemented as follows: Based on the doctor's job category, the basic time benchmark for the corresponding diagnosis and treatment scenario is determined. Combined with the average diagnosis and treatment time for the same disease type in the doctor's historical consultation data, the unit diagnosis and treatment efficiency of the doctor is calculated. The number of patients preceding the current doctor's consultation queue is counted, and the patients preceding the queue are distinguished as first-time patients and returning patients. First-time patients are allocated a longer estimated consultation time because they need to complete procedures such as medical history collection and preliminary examination and consultation. Returning patients are allocated a shorter estimated consultation time because their condition is clear and the consultation process is relatively simplified. Based on the combined effects of the doctor's unit's treatment efficiency, the number of previous patients, and the time differences corresponding to patient types, the estimated waiting time for the current patient is calculated and simultaneously linked to the hospital's real-time patient flow data. If the patient flow in the area where the current department is located exceeds the preset carrying capacity threshold, the waiting time buffer value is increased to ensure the accuracy of the estimated results. Calculate the estimated waiting time for current patients, specifically including: Extract the job category information of the target doctor, and determine the basic consultation time benchmark for the doctor based on the correspondence between the hospital's preset job categories and the basic time benchmark. Among them, the basic time benchmark for special needs clinics is higher than that for chief physician clinics, and the basic time benchmark for chief physician clinics is higher than that for general clinics. Retrieve the target doctor's historical consultation data for the past 3 months, filter out treatment records that match the current patient's condition type, calculate the actual treatment time of these records, and take the average as the reference value for the doctor's unit treatment efficiency for this condition type. The unit treatment efficiency reference value is calculated using the following formula: in, This represents the reference value for the unit treatment efficiency of the target physician for the current disease type. Indicates the first The actual time spent on treating the same illness in a historical record. This indicates the baseline working hours corresponding to the target doctor's job category. This represents the total number of historical medical records with the same condition that were selected. Obtain real-time data of the target doctor's current patient queue, count the total number of patients waiting in line, identify the type of each patient in line, and count the number of first-time patients and returning patients in line. Based on preset rules, time weights are assigned to initial and returning patients, with initial patients receiving a higher weight than returning patients. Combining the number of preceding initial and returning patients and their corresponding time weights, the estimated total treatment time for preceding patients is calculated using the following formula: in, This represents the estimated total treatment time for preceding patients. This indicates the number of patients who were initially diagnosed in the preceding period. Indicates the weight of the duration of the initial consultation for patients. This indicates the number of patients who returned for follow-up visits. Indicates the weight of the duration of follow-up visits for patients; By combining the reference value of the unit diagnosis and treatment efficiency of the target doctor, the estimated total diagnosis and treatment time of the preceding patients is corrected to obtain the basic time required for the overall diagnosis and treatment of the preceding patients. Retrieve real-time patient flow data for the area where the department is located and compare it with the preset capacity threshold for that area. If the real-time patient flow exceeds the capacity threshold, increase the corresponding time buffer based on the excess ratio to obtain the estimated waiting time for the current patient. The time buffer and the estimated waiting time for the current patient are calculated using the following formula: in, Indicates the time buffer size. This represents the estimated total treatment time for preceding patients. This indicates the real-time foot traffic in the area where the department is located. This indicates the preset carrying capacity threshold for the area where the department is located. This indicates the estimated waiting time for the current patient. Indicates the buffer coefficient. The value ranges from 0.1 to 0.3. Hospitals can adjust it according to the size of the area and their capacity to manage traffic flow. The default value is 0.2.

[0024] In the above embodiments, the intelligent decision-making layer's consultation time management function achieves accurate calculation of estimated waiting time through comprehensive analysis of multi-dimensional factors. It determines the basic time benchmark based on the doctor's job category, then combines historical consultation data with disease type to match unit treatment efficiency, while distinguishing the time difference between initial and return visits. Finally, it dynamically adjusts the time buffer value based on real-time patient flow in the hospital, forming a waiting time prediction mechanism. By considering more key factors affecting consultation time, it significantly improves the accuracy of the prediction results, enabling patients to obtain reliable waiting time references, thereby rationally arranging their own schedules and effectively alleviating patients' anxiety caused by uncertain waiting times. It also helps to fully release medical space, optimize hospital consultation processes, and improve operational efficiency.

[0025] The waiting reminder function of the service execution layer specifically includes: After the intelligent decision-making layer generates the estimated waiting time, it automatically pushes the waiting time notification to the patient's terminal. The patient can choose to wait in the hospital or leave the hospital temporarily based on the time. If a patient chooses to temporarily leave the hospital, access to the patient's terminal location function must be authorized to obtain the patient's current location and distance from the hospital in real time. The estimated arrival time for different modes of transportation (walking, cycling, driving) is calculated by combining mainstream map navigation data. A safety margin weighting factor is introduced when calculating different estimated arrival times. The basic estimated arrival time is multiplied by a weighting coefficient of 1.1-1.3 to generate the final estimated arrival time. The safety margin weighting factor is dynamically adjusted according to the traffic congestion trend of the time period, with 1.2-1.3 during peak hours and 1.1-1.2 during off-peak hours. The system supports patients to change their mode of transportation to the hospital in real time. Patients can switch their mode of transportation on the platform interface (e.g., change from walking to taking a taxi). The platform will recalculate the basic estimated arrival time based on the new mode of transportation and add a weighting factor to generate the updated final estimated arrival time. The system monitors changes in the distance between the patient's terminal and the hospital, changes in transportation methods, and updated estimated arrival time in real time. When the estimated arrival time is longer than the remaining waiting time, an expedited reminder is sent to the patient's terminal. At the same time, the dynamic changes in the current waiting queue are updated. If the treatment progress of the preceding patient is accelerated or there is a temporary additional treatment, the reminder time is adjusted. The platform updates and displays the estimated waiting time in real time, with the reasons for the adjustment also indicated, such as "Waiting time shortened by 15 minutes due to the early completion of treatment by the two preceding patients", "Waiting time extended by 10 minutes due to increased traffic in the current department area", and "Estimated arrival time adjusted to 20 minutes due to change of transportation mode to taxi".

[0026] In the above embodiments, the service execution layer promptly pushes notifications after generating the estimated waiting time. It also supports patients choosing their own waiting method and provides location-based dynamic reminders for patients temporarily discharged, ensuring they don't miss their appointment time. Simultaneously, real-time updates of waiting times and annotations of adjustment reasons enhance transparency, allowing patients to clearly understand the dynamic changes in the waiting queue. Compared to the model that relies solely on the queuing system for in-hospital reminders, this breaks through spatial limitations, providing patients with greater freedom of movement and effectively reducing unnecessary patient gatherings within the hospital. This lowers the risk of cross-infection and improves the patient's overall experience.

[0027] The spatial navigation function of the service execution layer is implemented as follows: Based on the coordinates of the patient's current location (any area within the hospital or a location outside the hospital) and the target location (payment window, designated examination room, pharmacy, reserved parking space), and combined with the hospital's indoor and outdoor spatial layout data (including floor distribution, department location, corridor direction, elevator / escalator location, and distribution of accessible facilities), a 3D navigation map is constructed. The map clearly marks the locations of special facilities such as accessible ramps, elevators, accessible restrooms, and wheelchair rental points. A 3D landscape reference model is added to the 3D navigation map to improve realism. The 3D landscape reference model includes indoor and outdoor 3D landscapes. In the construction of the indoor 3D landscape, the real-life scenes of public areas are reproduced, including the ceiling design, the reception desk, the appearance of the registration window, and the layout of the rest seats, incorporating dynamic elements (such as scrolling screen displays and ghosting of people moving around); matching real-life ground markings (such as departmental signs and yellow lines for accessible pathways), and reproducing the 3D forms of wall decorations, fire-fighting facilities, and lighting fixtures, with real-life corner textures and door details added at passageway turns; adding 3D models of departmental nameplates, waiting seats, and call buttons outside examination rooms, displaying the real-life appearance of the pharmacy counter and signs at the pharmacy window, and reproducing the counter style and queuing area division at the payment window; constructing 1:1 scale 3D models of elevators / escalators, reproducing the dynamic opening and closing of elevator doors and the operating status of escalators, and displaying floor buttons and handrail details inside; and reproducing the 3D forms of ramp slopes, anti-slip textures, and handrails on both sides, with a real-life transition effect displayed at the junction with the ground; When constructing the outdoor 3D landscape, real-scene scanning modeling was used to restore the 3D form of the hospital building's exterior wall materials, window layout, and rooftop signage, matching realistic lighting effects (such as shadows cast by sunlight and illuminated areas at night); the width and paving texture of the main roads and sidewalks in the hospital area were restored, and green facilities such as trees, lawns, and flower beds were modeled according to their real locations and forms, with seasonal vegetation details added (such as dense shade in summer and bare branches in winter); 3D models of parking space lines, numbered signs, and wheel stops were constructed in the reserved parking area, showcasing the real-scene appearance of parking lot entrance signs, payment machines, and special signs for accessible parking spaces.

[0028] When the navigation function is activated, the platform will automatically pop up a window to prompt the patient whether they need medical volunteer assistance. The pop-up window will simultaneously display the scope of volunteer services (such as accompanying patients to medical appointments, assisting with the use of equipment, and carrying items), the appointment response time (such as accepting the order within 10 minutes), and a description of the service process. Patients can choose to make an appointment immediately, make an appointment later, or not require services based on their own circumstances (such as physical disability, mobility impairment, elderly living alone, etc.). If a patient chooses to book a volunteer, they need to fill in the details of their service request on the platform (such as whether a wheelchair is needed, service time, target location, etc.). After submission, the platform will automatically push the request to the hospital's volunteer management system and match it with available medical volunteers. After the volunteer accepts the order, the platform will synchronize the basic information of both the patient and the volunteer (such as the patient's location and the volunteer's employee number) and enable the location sharing function. Volunteers can access a 3D navigation map through the platform and obtain the optimal travel route based on the patient's real-time shared location information to quickly reach the patient's location. During the navigation process, the platform updates the location dynamics of both parties in real time. If the patient temporarily changes their destination, it can be synchronized to the volunteer's terminal with one click, and the system will automatically replan the route. Once volunteers arrive at the patient's location, they can confirm the start of the service through the platform. During the service, they can share their progress in real time. After the service is completed, the patient can rate the volunteer's service on the platform. The rating data is simultaneously stored in the hospital's volunteer management system as a basis for service quality evaluation. Based on real-time data on pedestrian density in various passages and elevator entrances within the hospital, the optimal travel route is planned to avoid congested areas. During the route planning process, passages with pedestrian flow below the preset congestion threshold are prioritized. For patients who have booked volunteers, the route planning will also take into account the efficiency of meeting between volunteers and patients, prioritizing routes with no obstacles and ample passage space. Navigation is based on the optimal travel path. During the navigation process, changes in pedestrian flow along the path ahead are monitored in real time. If the original planned path experiences sudden congestion (such as equipment failure causing temporary closure of the passage or sudden medical events causing crowd gathering) or if barrier-free facilities are temporarily unavailable, the optimal path is automatically recalculated and pushed to the patient's terminal. At the same time, the reason for the path change is prompted by voice or text. The standard navigation mode focuses on the shortest path, while the accessible navigation mode prioritizes routes that include accessible ramps, elevators, and accessible restrooms. Patients can choose routes based on their physical condition (such as elderly patients or disabled patients). During navigation, real-time voice broadcasts provide information on the direction of travel, remaining distance, and facilities ahead (such as "Turn left in 50 meters to enter the accessible passage" or "We are about to reach the elevator entrance").

[0029] In the above embodiments, the spatial navigation function of the service execution layer solves the problem of patients having difficulty finding their way in hospitals by constructing a three-dimensional navigation map and planning a dynamic path. Based on the hospital's indoor and outdoor spatial layout data, a three-dimensional navigation map is constructed, and the optimal path is planned in combination with real-time pedestrian density data. This can effectively avoid congested areas and shorten the patient's travel time. During the navigation process, the path changes are monitored in real time and the path design is automatically replanned, which can cope with sudden congestion and ensure the continuity and accuracy of the navigation service.

[0030] The service execution layer's business processing functions include inspection appointments and parking appointments. The specific process is as follows: After the doctor issues the examination order and the patient completes the payment, an examination appointment QR code with a unique identifier is automatically generated. The examination appointment QR code can be scanned to enter the appointment interface, which displays the available appointment time slots for the current examination equipment, the remaining appointment slots for each time slot, and the location information of the examination room. After the patient selects the target time slot and completes the appointment, a successful appointment notification will be sent. The successful appointment notification includes the examination time, the location of the examination room, and pre-examination precautions (such as fasting requirements and clothing requirements). An appointment reminder will also be sent 1 hour before the examination. Based on historical parking data during the patient's registration period, the average parking space utilization rate and the number of vacant parking spaces in the hospital parking lot during that period are calculated to generate an estimated result of available parking spaces. After a patient initiates a parking reservation through their terminal, they can select a reservation mode, which includes either an instant billing mode or an overtime billing mode. The instant billing mode calculates the fee from the time the parking space is locked, while the overtime billing mode sets an allowed overtime period. Within the allowed time, the normal fee applies, and an additional overtime fee applies if the allowed time is exceeded. When a patient's vehicle is expected to arrive at the hospital garage within 5 minutes, the platform automatically locks the reserved parking space and simultaneously pushes navigation information on the garage entrance location and the specific location of the parking space. When retrieving the vehicle, the platform provides navigation guidance from the current location to the parking space, calculates the parking fee before leaving the garage, and supports online payment. When the number of available parking spaces in the parking lot is detected to be lower than a preset threshold (e.g., the remaining parking spaces account for less than 10% of the total parking spaces), the recommendation of surrounding parking resources is triggered. By accessing the resource data of public parking lots and commercial complex parking lots within a 1-kilometer radius of the hospital through an external extension layer, the system displays the real-time number of available parking spaces, pricing, walking time from the hospital, and reservation methods for each alternative parking lot. If the alternative parking lots support online booking, patients can directly initiate cross-platform bookings through the platform. After successful booking, they will receive the entrance navigation and booking voucher for that parking lot. If online booking is not supported, the system will push the parking lot's contact number and real-time parking space update frequency to the patient's terminal to display the parking space availability in real time.

[0031] In the above embodiments, the service execution layer's business processing function integrates examination appointment and parking appointment services, enabling one-stop processing of medical-related services. The examination appointment function simplifies the appointment process by generating a unique QR code, eliminating the need for patients to make appointments in the examination room. It also provides appointment reminders and notices, reducing the probability of patients missing appointments or being affected by insufficient preparation. The parking appointment function estimates parking availability based on historical data, supports multiple billing modes, and recommends nearby parking resources when spaces are insufficient, effectively solving the problem of parking difficulties for patients seeking medical care, reducing the number of trips and waiting time, and optimizing the medical process. Furthermore, the design of cross-platform appointment and real-time parking space update functions further expands the service's coverage and convenience.

[0032] The information query function of the service execution layer includes drug information query, and the specific implementation process is as follows: After the doctor completes the prescription and submits it to the hospital system, the prescription details are obtained in real time through the data interaction layer. The prescription details include the type of medicine, specifications, quantity, unit price, usage and dosage, and the corresponding inventory status of the medicine. Simultaneously retrieve high-resolution photos of the drug, ingredient descriptions, indications, common adverse reactions, and precautions from the drug database and display them on the patient's terminal interface in a combination of text and images; After viewing the medication information on the patient's terminal, a selection window is generated, allowing the patient to choose to confirm use or return the medication. If the patient selects to confirm use, the prescription will be automatically submitted to the pharmacy for dispensing; if the patient selects to return the medication, the return will be completed and the prescription will be cancelled after the patient confirms twice on their terminal. It provides a drug inventory query portal, which allows patients to pre-check drug stock information, avoiding the problem of drugs being out of stock when they go to pick them up, thus improving the convenience for patients.

[0033] In the above embodiments, the service execution layer obtains prescription details in real time and simultaneously displays physical photos of the drugs, ingredient descriptions, usage and dosage information, so that patients can clearly understand the relevant information of the prescribed drugs, avoid medication confusion caused by unclear information or waste caused by over-prescribing drugs, provide a two-way choice of confirming use and returning drugs, enhance the transparency of drug information, protect patients' right to know and medication safety, and help to make rational use of medical resources.

[0034] The external extension layer connects to external service resources related to the hospital, including office spaces, leisure and entertainment venues, catering establishments, and tourist attractions. The specific service process is as follows: When a patient chooses to temporarily leave the hospital to wait, the platform filters external service resources that are within a reasonable distance of the hospital (such as within 30 minutes on foot or within 15 minutes by car) and whose business hours cover the patient's waiting time, based on the patient's authorized location information and estimated waiting time. Based on the patient's historical usage preferences (e.g., if the patient has previously selected leisure coffee resources on the platform, similar venues will be recommended first) or the service type actively selected (office, catering, shopping, attractions), external resources are sorted and displayed. The displayed content includes resource name, specific location, user rating, reservation method, and travel time to and from the hospital. Patients can directly book target resources (such as coffee shop seats, shared office workstations, and attraction tickets) through the platform, and the booking time will be recorded synchronously after the booking is successful.

[0035] In the above embodiments, the external extension layer integrates service resources such as offices, leisure, restaurants, and attractions around the hospital, providing patients with diverse options while waiting. This achieves synergistic linkage between medical services and surrounding supporting services. Based on the patient's estimated waiting time and location information, the platform filters suitable external service resources and makes personalized recommendations. Patients can directly book target resources through the platform. At the same time, the platform adjusts the appointment reminder time according to the appointment situation to ensure that patients can receive medical treatment on time. This breaks the limitation of traditional hospitals only providing medical services, extends medical services to outside the hospital, effectively utilizes patients' waiting time, improves the overall patient experience, reduces the gathering of patients in the hospital, alleviates the spatial pressure on the hospital, and achieves a win-win situation for the hospital and surrounding resources.

[0036] To further illustrate the integrated smart hospital service platform, the following embodiments are provided to further explain the present invention: Mr. Zhang, a project manager at an internet company, recently needed to visit a hospital due to a persistent cough. He experienced the fully intelligent medical service through the hospital's official app's integrated smart medical service platform. The specific process is as follows: I. Appointment Registration and Parking Reservation Mr. Zhang opened the hospital's app at home, linked his personal medical information using his ID card, and selected the Department of Respiratory Medicine to make an appointment. The moment the appointment was successful, the platform's data interaction layer simultaneously collected his historical medical records (no previous respiratory disease records), current appointment type, and other medical information, as well as operational data such as the length of the hospital's respiratory medicine queue and the availability of parking spaces in the hospital's parking lot.

[0037] Based on historical parking data for the registration period (Wednesday morning at 10:00 AM), the platform's intelligent decision-making layer calculated that the average parking space occupancy rate in the hospital parking lot during that period was 85%, indicating that there were still vacant spaces. The platform then sent a parking reservation notification to Mr. Zhang. Mr. Zhang selected the instant billing mode, and the platform, through its service execution layer, locked in parking space number 32 in section C of the underground parking garage, and sent parking garage entrance navigation and parking space location information, while also noting that "the parking space is expected to remain locked for 5 minutes after arriving at the hospital."

[0038] II. Waiting time for medical treatment and arrangements for going out At 9:30 a.m. on Wednesday, Mr. Zhang arrived at the hospital by car and quickly found his reserved parking space using the platform's navigation. After parking, the platform simultaneously updated his location information within the hospital, and the intelligent decision-making layer began calculating the estimated waiting time: it extracted the baseline time (15 minutes / person) corresponding to the attending physician's job category (chief physician outpatient clinic), retrieved the physician's respiratory disease diagnosis and treatment data for the past 3 months, and determined that the average treatment time for the same symptoms was 18 minutes, thus determining the unit treatment efficiency reference value to be 18 minutes / person; there were 6 patients ahead of him in the current queue, including 4 initial visits and 2 return visits, and calculated the estimated total treatment time for the preceding patients according to the preset weights (initial visit weight 1.2, return visit weight 0.8) as 4×18×1.2+2×18×0.8=115.2 minutes; combined with the real-time flow of people in the area where the respiratory medicine department is located (not exceeding the carrying capacity threshold, no need to add buffer), the final estimated waiting time of 110 minutes was generated and pushed to Mr. Zhang's mobile phone.

[0039] Considering the long waiting time, Mr. Zhang checked the nearby service resources recommended by the platform's external extension layer and found a chain coffee shop 2 kilometers away from the hospital that supports shared office space reservations, and the round-trip travel time was in line with the waiting time. He selected "wait after leaving the hospital" and authorized location services. The platform simultaneously recorded the reservation time and reminded him to "please ensure that you allow sufficient return time before your visit".

[0040] III. Dynamic Alerts and Changes in Transportation Mode Mr. Zhang walked to the coffee shop. During the walk, the platform calculated a base estimated time of 20 minutes to return to the hospital. After adding a 1.2x safety margin weighting factor, the final estimated arrival time was 24 minutes. Upon arriving at the coffee shop, he began a project meeting, during which the platform continuously monitored his location and waiting queue dynamics.

[0041] At 10:40 AM, the platform detected that the previous three patients had completed their treatment, reducing the remaining waiting time to 30 minutes. It then sent Mr. Zhang his first reminder: "Current remaining waiting time is 30 minutes. Your estimated walk back to the hospital from your current location is 24 minutes (including a safety margin). Please plan your return trip accordingly." At this point, the meeting entered a crucial discussion phase. Anticipating that the meeting wouldn't end within 24 minutes, Mr. Zhang changed his return transportation method to a taxi on the platform.

[0042] The platform immediately recalculated: based on real-time location and map navigation data, the basic estimated arrival time at the hospital by taxi was 10 minutes, and after adding a 1.2 times weighting factor, the final estimated arrival time was 12 minutes. At 10:50, the remaining waiting time was updated to 20 minutes, and the platform sent an urgent reminder: "Remaining waiting time 20 minutes, estimated taxi ride back to the hospital 12 minutes, it is recommended to return immediately," while also noting the reason for the adjustment: "The two patients before me finished their treatment early, reducing the waiting time by 25 minutes."

[0043] IV. Return to Medical Treatment and Diagnosis / Prescription After receiving the urgent notification, Mr. Zhang ended his meeting and quickly booked a ride through the platform, arriving at the hospital's outpatient building precisely at 11:00 AM. The platform used 3D navigation, combined with real-time pedestrian density data, to plan the optimal route for him (avoiding congested areas near elevators), guiding him to the entrance of the respiratory medicine clinic. Just then, it was his turn for his appointment, with no delays whatsoever.

[0044] Based on Mr. Zhang's symptoms and examination results, the attending physician issued a prescription and submitted it to the hospital system. The data interaction layer retrieved the prescription details in real time: Amoxicillin Capsules (0.5g x 20 capsules, unit price 28 yuan, 1 capsule 3 times daily), and simultaneously accessed the drug database information, displaying high-resolution photos of the drug, ingredient descriptions, indications, and a warning about "occasional gastrointestinal discomfort" in a graphic format. After Mr. Zhang reviewed and confirmed the use, the prescription was automatically submitted to the pharmacy for dispensing.

[0045] V. Navigation to Medication Pickup and End of Medical Visit After the consultation, the platform's service execution layer pushed out medication pickup instructions. Based on Mr. Zhang's current location (the clinic entrance) and the pharmacy coordinates, the optimal medication pickup route was planned: "Go straight for 50 meters along the west side passage on the 3rd floor of the outpatient building, take the No. 2 accessible elevator downstairs, and pick up your medication at the pharmacy window on the east side of the first floor." During the navigation process, the system avoided the temporarily congested north side passage in real time and provided a voice prompt: "The passage ahead is crowded, and a new route has been planned for you."

[0046] Mr. Zhang quickly arrived at the pharmacy following the navigation, collected his medication using his mobile phone prescription, and the entire consultation process was successfully completed at 11:40. After his consultation, he rated the service on the platform.

[0047] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A smart integrated hospital medical service platform, characterized in that, It includes a data interaction layer, an intelligent decision-making layer, a service execution layer, and an external expansion layer; The data interaction layer is used to establish a two-way data channel between the patient terminal and the hospital's core system, acquire multi-dimensional data, and realize the real-time collection and transmission of patient diagnosis and treatment information and hospital operation data. The intelligent decision-making layer analyzes and processes the multi-dimensional data obtained from the data interaction layer through a preset algorithm model to generate decision results covering medical time management, route planning, resource allocation, and personalized recommendations. The service execution layer provides patients with full-process medical assistance services based on the decision results output by the intelligent decision layer. These medical assistance services include waiting reminders, spatial navigation, business processing, and information inquiry. The external extension layer connects to external related service resources of the hospital through standardized interfaces, enabling coordinated linkage between medical services and surrounding supporting services.

2. The intelligent integrated hospital medical service platform as described in claim 1, characterized in that, The patient diagnosis and treatment information collected by the data interaction layer includes the patient's identity information associated with the ID card or medical insurance card, historical medical records, examination reports, medication records, current registration type and registration department information; The collected hospital operation data includes doctor job categories, statistics on doctors' historical consultation time, current patient queue length, real-time patient flow in various areas of the hospital, idle status of consultation rooms and examination equipment, pharmacy drug inventory and unit price, parking space usage in the hospital parking lot, and data on surrounding public parking resources.

3. The intelligent integrated hospital medical service platform as described in claim 1, characterized in that, The specific implementation process of the intelligent decision-making layer's visit time management function is as follows: Based on the doctor's job category, the basic time benchmark for the corresponding diagnosis and treatment scenario is determined. Combined with the average diagnosis and treatment time for the same disease type in the doctor's historical consultation data, the unit diagnosis and treatment efficiency of the doctor is calculated. Count the number of patients preceding the current doctor's consultation queue, and distinguish between first-time patients and returning patients among the preceding patients; Based on the combined effects of the doctor's unit's treatment efficiency, the number of previous patients, and the time differences corresponding to patient types, the estimated waiting time for the current patient is calculated, and real-time patient flow data within the hospital is simultaneously linked. If the patient flow in the area where the current department is located exceeds the preset carrying capacity threshold, the waiting time buffer value is increased.

4. The intelligent integrated hospital service platform as described in claim 3, characterized in that, Calculate the estimated waiting time for current patients, specifically including: Extract the job category information of the target doctor, and determine the basic consultation time benchmark for the doctor based on the correspondence between the hospital's preset job categories and the basic time benchmark. Retrieve the target doctor's historical consultation data for the past 3 months, filter out the medical records that match the current patients' disease types, calculate the actual treatment time of these records, and take the average value as a reference value for the doctor's unit treatment efficiency for this disease type; Obtain real-time data of the target doctor's current patient queue, count the total number of patients waiting in line, identify the type of each patient in line, and count the number of first-time patients and returning patients in line. Based on preset rules, time weights are assigned to first-time patients and returning patients. The time weight for first-time patients is higher than that for returning patients. Combining the number of preceding first-time patients, the number of returning patients, and their corresponding time weights, the estimated total treatment time for preceding patients is calculated. By combining the reference value of the unit diagnosis and treatment efficiency of the target doctor, the estimated total diagnosis and treatment time of the preceding patients is corrected to obtain the basic time required for the overall diagnosis and treatment of the preceding patients. The system retrieves real-time patient flow data for the current department's area and compares it with the preset capacity threshold for that area. If the real-time patient flow exceeds the capacity threshold, the system increases the corresponding time buffer based on the excess ratio, ultimately obtaining the estimated waiting time for the current patient.

5. The intelligent integrated hospital medical service platform as described in claim 1, characterized in that, The waiting reminder function of the service execution layer specifically includes: After the intelligent decision-making layer generates the estimated waiting time, it automatically pushes the waiting time notification to the patient's terminal. The patient can choose to wait in the hospital or leave the hospital temporarily based on the time. If a patient chooses to temporarily leave the hospital, access to the patient's terminal location function must be authorized to obtain the patient's current location and distance from the hospital in real time. The estimated arrival time under different modes of transportation is calculated by combining mainstream map navigation data. When calculating different estimated arrival times, a safety margin weighting factor is introduced. The basic estimated arrival time is multiplied by a weighting coefficient of 1.1-1.3 to generate the final estimated arrival time. The safety margin weighting factor is dynamically adjusted according to the traffic congestion trend of the time period, with 1.2-1.3 during peak hours and 1.1-1.2 during off-peak hours. The system supports patients to change their mode of transportation to the hospital in real time. Patients can switch their mode of transportation independently on the platform interface. The platform will recalculate the basic estimated arrival time based on the new mode of transportation and add a weighting factor to generate the updated final estimated arrival time. The system monitors changes in the distance between the patient's terminal and the hospital, changes in transportation methods, and updated estimated arrival time in real time. When the estimated arrival time is longer than the remaining waiting time, an expedited reminder is sent to the patient's terminal. At the same time, the dynamic changes in the current waiting queue are updated. If the treatment progress of the preceding patient is accelerated or there is a temporary additional treatment, the reminder time is adjusted. The platform refreshes and displays the estimated waiting time updates in real time, and the reasons for the adjustments are also noted in the updates.

6. The intelligent integrated hospital medical service platform as described in claim 1, characterized in that, The spatial navigation function of the service execution layer is implemented as follows: A three-dimensional navigation map is constructed based on the coordinates of the patient's current location and the target location, combined with the hospital's indoor and outdoor spatial layout data. Based on real-time data on pedestrian density at various passages and elevator entrances within the hospital, the optimal travel route is planned to avoid congested areas, prioritizing passages with pedestrian flow below the preset congestion threshold during the route planning process. Navigation is based on the optimal travel path. During navigation, changes in pedestrian flow along the path ahead are monitored in real time. If a sudden congestion occurs on the original planned path, the optimal path is automatically recalculated and pushed to the patient's terminal simultaneously. The reason for the path change is also provided through voice or text prompts.

7. The intelligent integrated hospital medical service platform as described in claim 1, characterized in that, The service execution layer's business processing functions include inspection appointment and parking appointment, and the specific process is as follows: After the doctor issues the examination order and the patient completes the payment, an examination appointment QR code with a unique identifier is automatically generated. The examination appointment QR code can be scanned to enter the appointment interface, which displays the available appointment time slots for the current examination equipment, the remaining appointment slots for each time slot, and the location information of the examination room. After the patient selects the target time slot and completes the appointment, a successful appointment notification is sent. The successful appointment notification includes the examination time, the location of the examination room, and precautions before the examination. An appointment reminder is also sent 1 hour before the examination. Based on historical parking data during the patient's registration period, the average parking space utilization rate and the number of vacant parking spaces in the hospital parking lot during that period are calculated to generate an estimated result of available parking spaces. After a patient initiates a parking reservation through their patient terminal, they can select a reservation mode, which includes an instant billing mode or an overdue billing mode.

8. The intelligent integrated hospital service platform as described in claim 7, characterized in that, The parking reservation function also includes alternative options when there are insufficient parking spaces on site, specifically: When the number of available parking spaces in the parking lot is detected to be lower than a preset threshold, a recommendation of nearby parking resources is triggered. By accessing the resource data of public parking lots and commercial complex parking lots within a 1-kilometer radius of the hospital through an external extension layer, the system displays the real-time number of available parking spaces, pricing, walking time from the hospital, and reservation methods for each alternative parking lot. The system pushes the parking lot's contact number and real-time parking space update frequency, and displays the parking space information on the patient's terminal, including the navigation route and parking space number.

9. The intelligent integrated hospital medical service platform as described in claim 1, characterized in that, The information query function of the service execution layer includes drug information query, and the specific implementation process is as follows: After the doctor completes the prescription and submits it to the hospital system, the prescription details are obtained in real time through the data interaction layer. The prescription details include the type, specifications, quantity, unit price, usage and dosage of the drug, and the corresponding drug inventory status. Simultaneously retrieve high-resolution photos of the drug, ingredient descriptions, indications, common adverse reactions, and precautions from the drug database and display them on the patient's terminal interface in a combination of text and images; After viewing the medication information on the patient's terminal, a selection window is generated, allowing the patient to choose to confirm use or return the medication. If the patient selects to confirm use, the prescription will be automatically submitted to the pharmacy for dispensing; if the patient selects to return the medication, the return will be completed and the prescription cancelled after the patient confirms twice on their terminal.

10. The intelligent integrated hospital medical service platform as described in claim 1, characterized in that, The external extension layer accesses external service resources related to the hospital, including office spaces, leisure and entertainment venues, catering establishments, and tourist attractions. The specific service process is as follows: When a patient chooses to wait outside the hospital, the platform uses the patient's authorized location information and estimated waiting time to filter external service resources that are within a reasonable range of the hospital and whose business hours cover the patient's waiting time. External resources are sorted and displayed based on patients' historical usage preferences or the types of services they actively choose. The displayed content includes resource name, specific location, user rating, appointment method, and travel time to and from the hospital. Patients can directly book their target resources through the platform, and the booking time will be recorded synchronously after a successful booking.

Images