A team building method and system for full-course case management

Abstract

The present invention relates to the field of medical information technology, and discloses a team-building method and system for full-course case management, comprising: integrating medical data and non-medical Internet of Things data through a cross-domain data fusion engine to generate a patient behavior map, inferring behavioral inducements from wearable device data based on a reverse reasoning algorithm to trigger graded intervention, and utilizing blockchain smart contracts to achieve splittable combination and dynamic pricing of points; the system avoids the data silo limitations of traditional medical monitoring, and through the implicit association between smart home electricity consumption frequency and medication records, can reversely lock risk inducements before physiological indicators become abnormal, achieving accurate early warning, and through the deep coupling of multimodal data collaborative analysis, sandbox pre-rehearsal decision-making and smart contracts, achieving a technological leap from passive treatment to active health management.

Description

Technical Field

[0001] The present invention relates to a team building method and system for full-course case management, belonging to the field of medical information technology. Background Art

[0002] In scenarios such as chronic disease management and postoperative rehabilitation, medical teams need to integrate multi-source data such as patient medical records, physiological monitoring, and lifestyle habits, and dynamically coordinate rehabilitation resources to provide continuous services. The current industry generally adopts the following technical approaches:

[0003] 1. Multi-source data integration: Traditional systems primarily rely on structured data from the medical information system (HIS). While they can integrate basic information such as medication records, they lack the ability to integrate non-medical IoT data, such as smart home electricity usage frequency and wearable device positioning. This results in patient behavior analysis being limited to a single dimension. For example, the implicit correlation between abnormal nighttime lighting and medication compliance is often overlooked, causing risk warnings to lag behind the actual deterioration of physiological indicators.

[0004] 2. Resource scheduling decision-making level: Community rehabilitation resource allocation is mostly based on fixed schedules or manual experience, and lacks dynamic prediction of service demand fluctuations. Although existing digital twin technology can simulate resource allocation, its model is not linked to patients' real-time behavior data, resulting in a significant deviation between virtual simulation results and actual demand, and cannot effectively alleviate the contradiction between idle and scarce resources.

[0005] 3. Patient participation incentives: Existing point systems mostly use a one-way redemption model, where the use of points is fixed and cannot reflect the dynamic changes in resource supply and demand. For example, during periods of shortage of rehabilitation therapists, services are still redeemed at a fixed ratio, which not only exacerbates resource crowding but also makes it difficult to guide patients to actively optimize their health behaviors through the use of point leverage.

[0006] To improve the real-time performance of data integration, some solutions alleviate synchronization delays by increasing the frequency of data transmission from wearable devices. However, this leads to a sharp increase in the risk of patient privacy leakage, and the computing power load of edge devices exceeds the carrying capacity of the medical Internet of Things gateway. In terms of resource scheduling optimization, some studies have introduced reinforcement learning algorithms to predict service needs, but their model training relies on the static characteristics of historical data and is difficult to adapt to the dynamic evolution of patient behavior patterns. Instead, frequent adjustments to schedules increase management costs. Therefore, how to achieve deep coupling of cross-domain behavioral features while ensuring data security and build a two-way dynamic optimization mechanism for resource allocation and patient participation has become the technical problem to be solved by this invention. Summary of the Invention

[0007] The present invention provides a team-building method and system for full-course case management, the main purpose of which is to solve the problems of decision-making lag caused by multimodal data islands, service imbalance caused by rigid resource scheduling, and the difficulty of a one-way points mechanism in stimulating patients' active health management behavior.

[0008] To achieve the above objectives, the present invention provides a team-building method for full-course case management, comprising the following steps:

[0009] Step 1: Integrate patient medication information recorded in the medical information system and patient lifestyle data from non-medical IoT devices through a cross-domain patient behavior association engine. Non-medical IoT devices include smart home devices and wearable health monitoring devices. Smart home devices include at least power consumption monitoring modules and lighting monitoring modules, and wearable health monitoring devices include at least heart rate monitoring modules and location monitoring modules. Use a natural language processing module to perform semantic analysis and feature extraction on medication information and lifestyle data, and construct a patient behavior graph that includes both medical and non-medical behavior characteristics. The patient behavior graph is used to characterize the patient's behavior patterns in the medical and life domains and the potential correlation between the two.

[0010] Step 2: Based on a reverse reasoning algorithm, real-time physiological data from wearable health monitoring devices is analyzed. When abnormal fluctuations in physiological data are detected, such as a sudden increase in heart rate or an activity range exceeding a preset threshold, the possible causes of the abnormal fluctuations are reversely deduced. The reverse deduction at least associates and analyzes non-medical behavioral characteristics in the patient's behavior map. For example, the timestamp of the sudden increase in heart rate can be associated with the positioning data of the smart bracelet to determine whether the patient is outside the range of daily activities and may not be carrying medication, or the abnormal frequency of use of nighttime lighting equipment can be associated with the use of insomnia medication in the medication record to infer the relationship between insomnia and the patient's medication compliance, thereby generating a graded intervention warning signal containing potential behavioral inducements.

[0011] Step 3: Build a dynamic resource sandbox simulation system. Before making a decision, the system simulates the impact of different resource allocation plans on the satisfaction of patients' service needs. Resources include at least community rehabilitation workers. The simulation process is based on historical patient service data and predicted future service needs. It allocates different quantities and types of service resources in a virtual environment, predicts service gaps and service redundancies within a preset time frame (for example, the next 72 hours), and generates a pre-judgment report on the resource allocation effect.

[0012] Step 4: Using a flexible priority algorithm, the priority of the patient service task queue is dynamically adjusted based on the patient's risk level and the resource virtual occupancy rate predicted by the resource dynamic sandbox simulation system. For high-risk patients, service resources that have been simulated and verified in the virtual sandbox and have low resource occupancy rates are preferentially allocated to ensure that high-risk patients can receive the required services in a timely manner.

[0013] Step 5: Deploy a points system based on blockchain technology. The points system uses smart contracts to realize the divisible combination of points and the dynamic pricing of community service resources, allowing patients to split the points they earn into different proportions to redeem different services. For example, part of the follow-up points can be redeemed for registration priority, and the remaining part can be used for drug discounts. At the same time, the smart contract automatically adjusts the points redemption ratio according to the supply and demand relationship of community service resources. When the resources of rehabilitation therapists are tight, the points required for redemption will be increased, and vice versa.

[0014] Preferably, in step 2, the reverse reasoning algorithm further includes: when it is monitored that the frequency of smart home electricity consumption increases abnormally during non-normal sleeping periods, the patient's medication records are correlated and analyzed, and if there is a record of use of sedatives and hypnotic drugs, a warning signal is generated that insomnia may cause medication time deviation; when the patient's geographic location data monitored by the wearable health monitoring device exceeds the preset distance threshold of their daily activity range and the duration exceeds the preset time, the risk mark of not carrying regular medicines is automatically triggered.

[0015] Preferably, in step 3, when simulating the effect of resource allocation, the resource dynamic sandbox simulation system also takes into account the disease characteristics and service preferences of patients in different communities, and performs targeted optimization of the resource allocation plan to improve resource utilization efficiency and service satisfaction.

[0016] Preferably, in step 4, the elastic priority algorithm also considers the patient's recent service history, appointment preferences, and geographical distribution of community service resources when adjusting the priority of the patient service task queue, thereby achieving more refined resource matching and task scheduling.

[0017] Preferably, in step 5, the smart contract nesting mechanism allows patients to combine different types of points to redeem higher value or more personalized service packages, such as combining follow-up points and health behavior points to redeem a home visit service by a family doctor.

[0018] Preferably, in step 5, the dynamic pricing of community service resources is also adjusted in combination with factors such as the professional level of the service provider, the length of service, and the patient's evaluation feedback to achieve fairer and more efficient resource allocation.

[0019] Preferably, step 6 is also included, wherein personalized service recommendations, risk warning information, and redeemable points and service options are displayed to the patient through the user interface, and the patient is allowed to make service reservations and redeem points according to his or her own needs.

[0020] Preferably, the user interface also integrates augmented reality technology to provide patients with visual rehabilitation guidance, medication reminders, and community service navigation information.

[0021] Preferably, in step 1, the cross-domain patient behavior association engine also integrates patient health-related discussion data from social media platforms, uses sentiment analysis and topic modeling techniques to explore patients' potential health needs and psychological states, and integrates the analysis results into the patient behavior map to more comprehensively understand the patient's behavior patterns.

[0022] A team-building system for full-course case management, including:

[0023] A cross-domain patient behavior association module is used to integrate patient medication information from medical information systems and patient lifestyle data from non-medical IoT devices, and use a natural language processing module to construct a patient behavior graph that includes both medical and non-medical behavior characteristics.

[0024] A reverse reasoning analysis module is used to analyze real-time physiological data from wearable health monitoring devices, reversely deduce the possible causes of abnormal fluctuations, and generate graded intervention warning signals including potential behavioral triggers;

[0025] The resource dynamic sandbox simulation module is used to simulate the impact of different resource allocation plans on patient service demand satisfaction before making decisions, and generate a prediction report on the resource allocation effect;

[0026] The flexible priority scheduling module is used to dynamically adjust the priority of the patient service task queue based on the patient's risk level and the resource virtual occupancy rate predicted by the resource dynamic sandbox deduction module;

[0027] The blockchain points management module is used to realize the splittable combination of points and dynamic pricing of community service resources through smart contracts;

[0028] The data interaction and display module is used to show patients personalized service recommendations, risk warning information, redeemable points and service options, and receive patients' service appointment and points redemption operation requests.

[0029] Compared with the background technology problems, the beneficial effects of the present invention are:

[0030] 1. Through the cross-domain data fusion engine's collaborative analysis of medication records, smart home, and wearable device data, the system can capture behavioral correlation patterns that are difficult to detect in traditional medical monitoring. For example, considering the implicit correlation between abnormal night lighting and medication compliance in practice, this multimodal feature cross-analysis avoids the limitations of a single data dimension, enabling the risk warning mechanism to reversely deduce potential triggers from the patient's life scenarios, triggering precise intervention before abnormal physiological indicators occur, and effectively avoiding the warning lag problem caused by data silos in traditional solutions.

[0031] 2. The resource virtual sandbox simulates the distribution of service gaps under different resource allocation schemes to identify conflicting nodes in community rehabilitation resource scheduling in advance. Combined with the dynamic marking of high-risk patients by the elastic priority algorithm, the system can realize the intelligent reorganization of service queues under resource constraints. This closed-loop mechanism of prediction-simulation-adjustment enables the resource allocation plan to have self-optimization capabilities, avoiding the rigid defects of traditional scheduling and ensuring the feasibility of service strategies through virtual verification.

[0032] 3. By nesting smart contracts that combine splittable points with dynamic pricing rules, the system converts patient behavior data into quantifiable and adjustable service redemption rights. The point combination mechanism not only reflects the cumulative value of individual health behaviors, but also guides community resources to the nodes that need optimization most through the adjustment of the redemption ratio linked to supply and demand. This design avoids the one-way redemption model of the traditional point system, builds a positive feedback loop for patient participation while ensuring privacy and security, and uses a lightweight semantic distillation model to perform real-time analysis of multi-source heterogeneous data. The system can still maintain the accuracy of behavioral intention recognition in resource-constrained environments. Through the reverse reasoning mechanism triggered by timestamp deviation, the system can reconstruct the patient behavior time series and correct data synchronization errors, so that dynamic sandbox deduction is built on a trusted data foundation. The synergy of edge intelligence and semantic enhancement ensures the stable implementation of complex decision-making logic in clinical scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of data integration and processing of the present invention;

[0034] Figure 2 This is a timing diagram of the reverse reasoning warning process of the present invention;

[0035] Figure 3 Construct a flow chart for the patient behavior map of the present invention.

[0036] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0037] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0038] The present invention provides a method for team building for full-course case management, including the following steps:

[0039] Step 1: Integrate patient medication information recorded in the medical information system and patient lifestyle data from non-medical IoT devices through a cross-domain patient behavior association engine. Non-medical IoT devices include smart home devices and wearable health monitoring devices. Smart home devices include at least power consumption monitoring modules and lighting monitoring modules, and wearable health monitoring devices include at least heart rate monitoring modules and location monitoring modules. Use a natural language processing module to perform semantic analysis and feature extraction on medication information and lifestyle data, and construct a patient behavior graph that includes both medical and non-medical behavior characteristics. The patient behavior graph is used to characterize the patient's behavior patterns in the medical and life domains and the potential correlation between the two.

[0040] Step 2: Based on a reverse reasoning algorithm, real-time physiological data from wearable health monitoring devices is analyzed. When abnormal fluctuations in physiological data are detected, such as a sudden increase in heart rate or an activity range exceeding a preset threshold, the possible causes of the abnormal fluctuations are reversely deduced. The reverse deduction at least associates and analyzes non-medical behavioral characteristics in the patient's behavior map. For example, the timestamp of the sudden increase in heart rate can be associated with the positioning data of the smart bracelet to determine whether the patient is outside the range of daily activities and may not be carrying medication, or the abnormal frequency of use of nighttime lighting equipment can be associated with the use of insomnia medication in the medication record to infer the relationship between insomnia and the patient's medication compliance, thereby generating a graded intervention warning signal containing potential behavioral inducements.

[0041] Step 3: Build a dynamic resource sandbox simulation system. Before making a decision, the system simulates the impact of different resource allocation plans on the satisfaction of patients' service needs. Resources include at least community rehabilitation workers. The simulation process is based on historical patient service data and predicted future service needs. It allocates different quantities and types of service resources in a virtual environment, predicts service gaps and service redundancies within a preset time frame (for example, the next 72 hours), and generates a pre-judgment report on the resource allocation effect.

[0042] Step 4: Using a flexible priority algorithm, the priority of the patient service task queue is dynamically adjusted based on the patient's risk level and the resource virtual occupancy rate predicted by the resource dynamic sandbox simulation system. For high-risk patients, service resources that have been simulated and verified in the virtual sandbox and have low resource occupancy rates are preferentially allocated to ensure that high-risk patients can receive the required services in a timely manner.

[0043] Step 5: Deploy a points system based on blockchain technology. The points system uses smart contracts to realize the divisible combination of points and the dynamic pricing of community service resources, allowing patients to split the points they earn into different proportions to redeem different services. For example, part of the follow-up points can be redeemed for registration priority, and the remaining part can be used for drug discounts. At the same time, the smart contract automatically adjusts the points redemption ratio according to the supply and demand relationship of community service resources. When the resources of rehabilitation therapists are tight, the points required for redemption will be increased, and vice versa.

[0044] Preferably, in step 2, the reverse reasoning algorithm further includes: when it is monitored that the frequency of smart home electricity consumption increases abnormally during non-normal sleeping periods, the patient's medication records are correlated and analyzed, and if there is a record of use of sedatives and hypnotic drugs, a warning signal is generated that insomnia may cause medication time deviation; when the patient's geographic location data monitored by the wearable health monitoring device exceeds the preset distance threshold of their daily activity range and the duration exceeds the preset time, the risk mark of not carrying regular medicines is automatically triggered.

[0045] Preferably, in step 3, when simulating the effect of resource allocation, the resource dynamic sandbox simulation system also takes into account the disease characteristics and service preferences of patients in different communities, and performs targeted optimization of the resource allocation plan to improve resource utilization efficiency and service satisfaction.

[0046] Preferably, in step 4, the elastic priority algorithm also considers the patient's recent service history, appointment preferences, and geographical distribution of community service resources when adjusting the priority of the patient service task queue, thereby achieving more refined resource matching and task scheduling.

[0047] Preferably, in step 5, the smart contract nesting mechanism allows patients to combine different types of points to redeem higher value or more personalized service packages, such as combining follow-up points and health behavior points to redeem a home visit service by a family doctor.

[0048] Preferably, in step 5, the dynamic pricing of community service resources is also adjusted in combination with factors such as the professional level of the service provider, the length of service, and the patient's evaluation feedback to achieve fairer and more efficient resource allocation.

[0049] Preferably, step 6 is also included, wherein personalized service recommendations, risk warning information, and redeemable points and service options are displayed to the patient through the user interface, and the patient is allowed to make service reservations and redeem points according to his or her own needs.

[0050] Preferably, the user interface also integrates augmented reality technology to provide patients with visual rehabilitation guidance, medication reminders, and community service navigation information.

[0051] Preferably, in step 1, the cross-domain patient behavior association engine also integrates patient health-related discussion data from social media platforms, uses sentiment analysis and topic modeling techniques to explore patients' potential health needs and psychological states, and integrates the analysis results into the patient behavior map to more comprehensively understand the patient's behavior patterns.

[0052] A team-building system for full-course case management, including:

[0053] A cross-domain patient behavior association module is used to integrate patient medication information from medical information systems and patient lifestyle data from non-medical IoT devices, and use a natural language processing module to construct a patient behavior graph that includes both medical and non-medical behavior characteristics.

[0054] A reverse reasoning analysis module is used to analyze real-time physiological data from wearable health monitoring devices, reversely deduce the possible causes of abnormal fluctuations, and generate graded intervention warning signals including potential behavioral triggers;

[0055] The resource dynamic sandbox simulation module is used to simulate the impact of different resource allocation plans on patient service demand satisfaction before making decisions, and generate a prediction report on the resource allocation effect;

[0056] The flexible priority scheduling module is used to dynamically adjust the priority of the patient service task queue based on the patient's risk level and the resource virtual occupancy rate predicted by the resource dynamic sandbox deduction module;

[0057] The blockchain points management module is used to realize the splittable combination of points and dynamic pricing of community service resources through smart contracts;

[0058] The data interaction and display module is used to show patients personalized service recommendations, risk warning information, redeemable points and service options, and receive patients' service appointment and points redemption operation requests.

[0059] Example 1: This example integrates patient medication records from a medical information system (HIS) and patient lifestyle data from non-medical IoT devices (such as smart homes and wearable health monitoring devices) through a cross-domain patient behavior association engine. Smart home devices, for example, include at least one electricity monitoring module and a lighting monitoring module, and wearable health monitoring devices include at least a heart rate monitoring module and a location monitoring module. A natural language processing (NLP) module is used to perform semantic analysis and feature extraction on medication records and lifestyle data, thereby constructing a comprehensive patient behavior map. The behavior map can represent the patient's behavioral characteristics in the medical and life fields, as well as the potential correlation between these behavioral characteristics. The patient's medical behavior characteristics include medication status, treatment process, etc., and the life behavior characteristics include sleep quality, activity range, environmental factors, etc.

[0060] During real-time physiological data monitoring of patients, when abnormal fluctuations in heart rate or other physiological indicators occur, a reverse reasoning algorithm is activated to analyze whether the abnormality is caused by lifestyle habits or behavioral triggers. For example, if the heart rate suddenly increases, the system will automatically associate the smart home data within that time period to analyze whether the patient is outside of the scope of regular activities or whether they have not taken medication on time. By analyzing the correlation with the patient's behavioral profile, possible behavioral triggers are reversely inferred, and then corresponding early warning signals are generated. During this process, the system will combine the patient's non-medical behavioral characteristics, such as the frequency of use of nighttime lighting devices and the use of insomnia medication in medication records, to reversely deduce possible medication deviations caused by insomnia symptoms and generate targeted intervention prompts.

[0061] Based on patients' behavioral and physiological data, the system utilizes a dynamic resource sandbox simulation model to simulate different community rehabilitation resource allocation scenarios. This model takes into account historical patient service data and future service demand forecasts. By simulating the effects of different resource allocation scenarios, it identifies service gaps and excess resources, ultimately generating a predictive report on service resources. By simulating service demand and resource allocation in a virtual environment, this sandbox simulation system helps decision-makers optimize resource allocation and predict service gaps or redundancies within limited resources. This process ensures optimal resource allocation, avoiding the inaccuracies and inefficiencies of traditional manual scheduling methods. The system also dynamically adjusts patient service task queues using a flexible priority algorithm. This algorithm automatically adjusts the priority of high-risk patients based on their risk level and virtual resource occupancy. High-risk patients are prioritized for service resources that have been verified in the virtual sandbox and have lower resource occupancy rates. This ensures that high-risk patients receive the services they need in a timely manner, avoiding unfair resource allocation or delays.

[0062] During resource scheduling, the algorithm also considers factors such as the patient's historical service history, appointment preferences, and the geographic distribution of community service resources, enabling refined resource matching and task scheduling. This flexible prioritization mechanism allows the system to dynamically adjust based on actual demand and resource availability, improving resource utilization efficiency and service timeliness. In the patient service points system, smart contracts enable the splitting and combining of points and the dynamic pricing of community service resources. Patients accumulate health behavior points using data from smart home and wearable devices and redeem these points for medical services. The system's smart contracts dynamically adjust the point redemption ratio based on the supply and demand of community service resources. When rehabilitation therapist resources are limited, the system increases the point requirement for redemption, while reducing it. This mechanism encourages patients to actively participate in health management while optimizing resource allocation. The user interface displays personalized service recommendations, risk warnings, and redeemable points and service options, allowing patients to schedule services and redeem points based on their needs. The user interface also integrates augmented reality technology, providing patients with visual rehabilitation guidance, medication reminders, and community service navigation, enhancing the user experience and personalized service experience.

[0063] Example 2: This example combines Figures 1 to 3 , describes a team building method and system for full-course case management. Figure 1 As shown in the figure, data is first collected from four data sources: medical information system records, smart home device data, wearable health monitoring device data, and social media platform data. Medical information system records provide patient medication information, smart home device data and wearable health monitoring device data both provide lifestyle data, and social media platform data provides health-related discussion data. This data is integrated into a cross-domain patient behavior association engine, which receives medication and lifestyle data from the natural language processing module and social media data from sentiment analysis and topic modeling. The natural language processing module performs semantic analysis and feature extraction on the data, while sentiment analysis and topic modeling analyze the data's underlying needs and psychological state. The processed data ultimately forms a patient behavior map, which contains the patient's medical and non-medical behavior characteristics and associations, and is ultimately output.

[0064] like Figure 2 As shown, Figure 2The process involves a wearable device, a behavioral graph engine, a reverse reasoning module, an early warning decision-making system, a blockchain network, and a family terminal. The process begins when the wearable device records real-time heart rate data (120 bpm). The wearable device then sends a request to the behavioral graph engine for behavioral association analysis. Upon receiving the request, the behavioral graph engine first retrieves medication records (sedatives not taken), then retrieves location data (outside the normal range of activity), and then sends the returned association features to the reverse reasoning module. Based on the received association features, the reverse reasoning module generates a secondary warning (no medication + abnormal activity) and records this warning information as a warning event (timestamp + risk value). This event record is then confirmed through the blockchain network. Simultaneously, the early warning decision-making system sends a vibration reminder to the wearable device to take medication immediately and sends a location notification to the family terminal.

[0065] like Figure 3 As shown in the figure, the process begins with the integration of cross-domain data sources, including medication information provided by medical information systems and lifestyle data from non-medical IoT systems. After preprocessing the integrated data, natural language processing (NLP) and semantic analysis are performed. Next, the process moves to the extraction of behavioral features. The extracted behavioral features are used to construct a patient behavior graph, which includes medical and non-medical behavior features, as well as potential associations between behaviors. The entire graph is represented by the label "graph." Finally, the graph is stored and updated, and the process ends.

[0066] Example 3: In this invention, the cross-domain data fusion engine's primary task is to integrate medication information from medical information systems with patient lifestyle data from non-medical IoT devices. This process uses a natural language processing (NLP) module to perform semantic analysis and feature extraction on both medical and lifestyle data, constructing a patient behavior graph. This behavior graph includes the patient's medical behavioral characteristics, such as medication history and treatment progress, as well as non-medical behavioral characteristics, such as sleep quality, activity range, and environmental factors, thereby reflecting the patient's behavioral patterns in both medical and lifestyle domains and their potential correlations. When sensors detect an abnormality in a patient's physiological data, such as a sharp increase in heart rate, the reverse reasoning module is triggered to analyze the possible causes of this abnormal fluctuation. The system then correlates non-medical behavioral characteristics in the patient behavior graph, such as the frequency of nighttime smart home lighting use and the patient's activity range, to infer the possible behavioral triggers. For example, the system might discover a correlation between a sudden increase in heart rate and the abnormal frequency of nighttime smart home lighting use, thereby inferring that the patient may have taken medication related to insomnia. In this case, the system automatically generates a warning signal and guides medical staff to take appropriate interventions.

[0067] The resource dynamic sandbox simulation module of the present invention is designed to optimize the allocation plan of community rehabilitation resources. During the resource allocation process, the module will simulate different resource allocation plans and predict service demand and resource usage in the future (such as within 72 hours); the simulation process is based on historical patient data and future forecasts, taking into account the availability of resources and fluctuations in patient demand, to generate service gap reports and excess resource reports. This report provides a reference for decision makers so that they can reasonably allocate service resources when resources are limited to avoid resource waste or service loss. At the same time, the elastic priority algorithm dynamically adjusts the priority of the task queue according to the patient's risk level and resource virtual occupancy rate. For high-risk patients, the system will give priority to allocating verified service resources with lower resource occupancy rates. The implementation of the elastic priority algorithm takes into account factors such as the patient's historical service records, appointment preferences, and service duration, thereby achieving more refined resource matching and task scheduling.

[0068] The points system of the present invention uses smart contracts to achieve dynamic pricing and splitting of points. Each patient's behavioral data, such as medication records and health monitoring data, will be converted into points. These points can be used to redeem different types of service resources, such as registration priority, drug discounts, community health services, etc.; the smart contract mechanism enables the points redemption ratio to be adjusted in real time according to the supply and demand of service resources. When the resources of community rehabilitation therapists are tight, the system will automatically increase the points required for redemption, and vice versa. The system not only optimizes resource allocation, but also promotes patients' active participation in health management through the points incentive mechanism.

[0069] Example 4: First, a cross-domain patient behavior association engine is used to integrate medication records from the medical information system (HIS) with lifestyle data from non-medical IoT devices, such as smart homes and wearable health monitoring devices. A natural language processing (NLP) module is then used to perform semantic analysis and feature extraction on both medical and non-medical data. During feature extraction, particular attention is paid to the following variables: medication records, including drug name, time of use, and dosage; and non-medical behavior features, including smart home power usage, lighting patterns, and wearable device-recorded exercise, heart rate, and location. This data fusion generates a patient behavior map, which comprehensively characterizes the patient's behavioral characteristics and potential connections in both medical and daily life, serving as a foundation for subsequent behavioral prediction and intervention.

[0070] When abnormal fluctuations are detected in a patient's real-time physiological data, such as heart rate or range of activity, the reverse reasoning algorithm is activated. This algorithm analyzes the potential causes behind these abnormal fluctuations, primarily through the following steps: Heart rate surge analysis: If the heart rate increases significantly during the monitoring period, the system first correlates the timestamp with smart home data, such as lighting frequency, to determine whether the patient is in an unusual range of activity. If the patient's location is outside their regular activity area, it is inferred that the patient may not have taken medication on time, thereby generating a risk warning signal. Sleep disorder inference: If the frequency of nighttime lighting equipment use increases abnormally, the system correlates and analyzes the patient's medication records. If sedatives are found, it is inferred that insomnia may have caused a shift in medication time, generating targeted intervention prompts. The reverse reasoning algorithm is not limited to analyzing physiological data anomalies; it also combines non-medical data in the patient's behavioral map for comprehensive judgment, ensuring that the behavioral triggers that lead to physiological fluctuations can be accurately located, avoiding reasoning based on a single data source.

[0071] To ensure dynamic resource allocation, the system simulates the effects of different resource configuration schemes before making decisions. This process is based on historical patient data and future service demand forecasts. The specific steps are as follows: Simulate resource allocation. Based on predicted patient demand and historical data, the virtual sandbox system will simulate resource allocation plans, identify service gaps and redundancies, and implement a priority scheduling algorithm. Using a flexible priority algorithm, the system dynamically adjusts the priority of the task queue based on the patient's risk level and resource occupancy rate. This algorithm considers the patient's historical service record, appointment preferences, and the geographical distribution of service resources to ensure that resources are allocated first in the most urgent situations. In this process, virtual occupancy rate serves as an important parameter that describes the usage of each resource in the virtual sandbox. Based on the virtual occupancy rate of different resources, the algorithm can dynamically adjust the resource allocation strategy to respond to different service needs.

[0072] Based on blockchain technology, the points system utilizes smart contracts to enable splittable and dynamic pricing of points. Specifically, patients generate points using data from wearable devices and smart home appliances, which can be redeemed for medical services. Patients can choose to redeem different types of services, such as priority appointments and drug discounts. Smart contracts regulate the redemption ratio, automatically adjusting the points required based on the supply and demand of service resources. When resources are scarce, the system increases the points required, while lowering the requirement. This mechanism guides patients in optimizing their health behaviors and ensures that community service resources are flexibly allocated according to actual needs.

[0073] Example 5: At the data integration level, the cross-domain patient behavior association engine serves as the core of information aggregation, actively acquiring data from multiple channels. It not only receives standard medication records from the medical information system (HIS), which contain key information such as medication name, usage, dosage, and time of use; it also integrates lifestyle data generated by smart home devices and wearable health monitoring devices. Smart home devices can provide indirect behavioral information such as patients' sleep and rest patterns and electricity usage patterns, such as the duration of nighttime lighting; wearable devices monitor physiological data such as heart rate, activity level, sleep duration, and location in real time. Furthermore, to more comprehensively understand patients' potential needs and psychological states, the engine also accesses health-related discussions posted by patients on public social media platforms. All of this raw data is first preprocessed, including cleaning, deduplication, and formatting, before being fed into the natural language processing (NLP) module for in-depth analysis. The NLP module performs semantic analysis and entity extraction on text data, such as medication orders and social media content, to identify technical characteristics related to patients' health, such as emotional tendencies, health concerns, and attitudes toward treatment options. The processed structured and unstructured data is used to construct and continuously update a multimodal patient behavior graph. This graph represents entities such as patients, their behaviors, physiological states, medications, environmental factors, and social activities, and their interrelationships, using nodes and edges.

[0074] The reverse reasoning analysis module works closely with the patient's behavioral profile to analyze the underlying causes of abnormal physiological data. When the wearable device detects a significant deviation from a patient's baseline or normal medical range in real-time, the reverse reasoning mechanism is triggered. For example, if a patient's heart rate is continuously elevated, the system searches the patient's behavioral profile for other behavioral data related to that time point, such as whether the patient was resting or exercising at the time, whether the patient's geographic location is outside of their usual activity area, whether they have recently taken specific medications such as stimulants or sedatives, and even whether the patient's emotional state, as reflected in the profile, shows signs of anxiety or stress. By comparing this information with a set of pre-set inference rules, the system attempts to eliminate superficial causes and infer more likely triggers. For example, if the elevated heart rate occurs at night and the profile indicates recent sleep disturbances (as determined by nighttime lighting duration and sleep quality monitored by the wearable device), as well as the use of sedatives and hypnotic medications, the inference module may conclude that the abnormal heart rate may be related to anxiety caused by insomnia or irregular medication schedules, and generate a corresponding risk warning signal. These are all extended implementations known to those skilled in the art.

[0075] The resource dynamics sandbox simulation module plays a key role in planning service resource allocation plans. It constructs a virtual environment to simulate the service resources of a specific community, including the supply capacity of medical staff, equipment, venues, and other aspects, and the service demand predicted based on patient behavior patterns and early warning information. This sandbox does not perform complex mathematical calculations, but rather simulates the process of discrete events. The simulation process takes into account the type, quantity, and available time period of resources, as well as the patient's service preferences and disease characteristics, in order to evaluate the pros and cons of different plans. For example, for the predicted regular follow-up needs of diabetic patients, the sandbox will simulate whether the existing doctor resources can meet these needs within the specified time period; for the home care needs triggered by sudden high-risk early warnings, the sandbox will simulate whether the nursing resources can respond in a timely manner. After the simulation is completed, the system will generate a predictive report indicating the service gaps or resource redundancies that may occur in the simulated scenario, providing a basis for the final resource allocation decision.

[0076] The elastic priority scheduling module is responsible for dynamically managing the patient's service task queue. When the system receives a new service request or the status of an existing task changes, the module will adjust the execution order of the task based on a comprehensive evaluation mechanism. The evaluation mechanism takes multiple factors into consideration. The first is the patient's current risk level. Tasks for high-risk patients are usually given higher priority. Secondly, combined with the resource dynamic sandbox deduction module's predicted virtual occupancy rate, if a certain key resource is expected to be very tight in a certain period of time, and a high-priority task happens to need this resource, the priority of the task will be further increased to ensure priority protection of resources. In addition, the algorithm will also refer to the patient's historical service records, their appointment preferences reflected in the map, and the geographical location of the required service resources. While meeting urgency and importance, it improves the accuracy of resource matching and the efficiency of scheduling. The entire scheduling process is dynamically adjusted and can respond flexibly based on real-time information received and simulation prediction results.

[0077] The blockchain points management module provides a flexible and transparent incentive and service redemption mechanism. Patients can accumulate health points by performing specific behaviors that contribute to their health (such as taking medication on time, exercising regularly, and actively participating in community activities). The completion of these behaviors is verified by a behavior correlation engine from multiple data sources. These points are recorded on the blockchain, and their accumulation, transfer, and use are transparent and traceable. The points system allows for the combination of different types of points. For example, points earned from daily health check-ins can be combined with points earned from completing phased rehabilitation goals to redeem higher-value services, such as expert remote consultations. Dynamic pricing is also used when redeeming points for community service resources. Smart contracts, acting as the automated vehicle for executing these rules, adjust the point redemption ratio based on the real-time supply and demand of community service resources. For example, if a surge in bookings for a particular rehabilitation training service leads to resource constraints, the smart contract will automatically increase the number of points required to redeem that service. Conversely, if resource utilization is low, the required points will be reduced. This dynamic adjustment aims to guide patient behavior through economic signals, encouraging redemption of services during off-peak hours, thereby optimizing overall resource allocation efficiency and motivating patients to more proactively manage their health. These are all extended implementations known to those skilled in the art.

[0078] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A team building method for full-course case management, characterized by: The following steps are involved: Step 1: Integrate patient medication information recorded in the medical information system and patient lifestyle data from non-medical IoT devices through a cross-domain patient behavior association engine. The non-medical IoT devices include smart home devices and wearable health monitoring devices. The smart home devices include a lighting monitoring module, and the wearable health monitoring devices include at least a heart rate monitoring module and a location monitoring module. Use a natural language processing module to perform semantic analysis and feature extraction on the medication information and lifestyle data to construct a patient behavior graph that includes both medical and non-medical behavior characteristics. The patient behavior graph is used to characterize the patient's behavior patterns in the medical and lifestyle fields and the potential correlation between the two. Step 2: Analyze real-time physiological data from wearable health monitoring devices based on a reverse reasoning algorithm. When abnormal fluctuations in physiological data are detected, reverse reasoning is performed to deduce the possible causes of the abnormal fluctuations. This reverse reasoning can at least correlate and analyze non-medical behavioral characteristics in the patient's behavioral profile to determine whether the patient is outside of their daily activities and may not be carrying medication. Alternatively, the abnormal frequency of nighttime lighting use can be correlated with the use of insomnia medications in medication records to infer the relationship between insomnia and the patient's medication compliance, thereby generating a graded intervention warning signal containing potential behavioral triggers. Step 3: Build a dynamic resource sandbox simulation system. Before making a decision, the system simulates the impact of different resource allocation plans on the satisfaction of patients' service needs. Resources include at least community rehabilitation workers. The simulation process is based on historical patient service data and predicted future service needs. It allocates different quantities and types of service resources in a virtual environment, predicts service gaps and service redundancies within a preset time frame, and generates a pre-judgment report on the resource allocation effect. Step 4: Using the elastic priority algorithm, the priority of the patient service task queue is dynamically adjusted based on the patient's risk level and the resource virtual occupancy rate predicted by the resource dynamic sandbox simulation system. For high-risk patients, service resources with low resource occupancy rates that have been simulated and verified in the virtual sandbox are preferentially allocated. Step 5: Deploy a points system based on blockchain technology. This system uses smart contracts to implement splittable points and dynamic pricing of community service resources. Patients can split their points into different proportions to redeem different services. At the same time, the smart contract automatically adjusts the points redemption ratio based on the supply and demand of community service resources. When the number of rehabilitation therapists is tight, the points required for redemption are increased, and vice versa. In step 2, the reverse reasoning algorithm further includes: when monitoring the abnormal increase in the frequency of smart home electricity consumption during non-normal sleep periods, correlating and analyzing the patient's medication records, and if there is a record of the use of sedatives and hypnotic drugs, generating a warning signal that insomnia may cause medication time deviation; when the wearable health monitoring device monitors the patient's geographic location data beyond a preset distance threshold of their daily activity range and the duration exceeds a preset time, automatically triggering a risk flag for not carrying regular medications; The method further includes step 6, displaying personalized service recommendations, risk warning information, and redeemable points and service options to the patient through the user interface, and allowing the patient to make service reservations and redeem points according to their needs; The user interface also integrates augmented reality technology to provide patients with visual rehabilitation guidance, medication reminders, and community service navigation information.

2. A team building method for full-course case management according to claim 1, characterized in that: In step 4, the elastic priority algorithm also considers the patient's recent service history, appointment preferences, and geographic location distribution of community service resources when adjusting the priority of the patient service task queue.

3. A team building method for full-course case management according to claim 1, characterized in that: In step 1, the cross-domain patient behavior association engine also integrates patient health-related discussion data from social media platforms, uses sentiment analysis and topic modeling techniques to explore patients' potential health needs and psychological states, and integrates the analysis results into the patient behavior map.

4. A team building system for full-course case management, characterized by: include: A cross-domain patient behavior association module is used to integrate patient medication information from medical information systems and patient lifestyle data from non-medical IoT devices, and use a natural language processing module to construct a patient behavior graph that includes both medical and non-medical behavior characteristics. A reverse reasoning analysis module is used to analyze real-time physiological data from wearable health monitoring devices, reversely deduce the possible causes of abnormal fluctuations, and generate graded intervention warning signals including potential behavioral triggers; The resource dynamic sandbox simulation module is used to simulate the impact of different resource allocation plans on patient service demand satisfaction before making decisions, and generate a prediction report on the resource allocation effect; The flexible priority scheduling module is used to dynamically adjust the priority of the patient service task queue based on the patient's risk level and the resource virtual occupancy rate predicted by the resource dynamic sandbox deduction module; The blockchain points management module is used to realize the splittable combination of points and dynamic pricing of community service resources through smart contracts; The data interaction and display module is used to show patients personalized service recommendations, risk warning information, redeemable points and service options, and receive patients' service appointment and points redemption operation requests.

Images