High-positioning-precision medical emergency center data information management system and method

Abstract

The invention discloses a medical emergency center data information management system and method with high positioning precision, and the system comprises a multi-mode positioning terminal, an Ai central station and an emergency information integrated sharing platform, and the multi-mode positioning terminal collects original positioning data through a GPS, Bluetooth or UWB sensor; and distributing the processed data to the Ai central station according to the priority through the security gateway, outputting structured decision information to the first-aid information integrated sharing platform after Ai processing, realizing cross-department cooperative completion of a first-aid task, and returning an actual rescue result to the Ai central station for model optimization. According to the scheme, the multi-source fusion positioning technology is adopted to improve the positioning precision, the corresponding optimal positioning modes are selected for different areas, the first-aid response time is shortened, and the patient can be rescued more quickly; moreover, after the information of the patient is collected, key data can be encrypted and stored, so that the confidentiality, traceability and safety of the data are ensured.

Description

Technical Field

[0001] This invention relates to a data information management system, and more particularly to a high-precision medical emergency center data information management system and method, belonging to the interdisciplinary technical field of medical management and electronic systems. Background Technology

[0002] Currently, smart emergency medical centers are a new type of emergency medical service system that utilizes modern information technology and intelligent methods to improve the efficiency and quality of emergency services. It combines traditional emergency medical services with technologies such as the Internet of Things, big data, and artificial intelligence to achieve optimized allocation of emergency resources and rapid response. Based on the smart emergency medical center, a medical emergency center data information management system is designed. This is a comprehensive information solution specifically designed for emergency medical services, and also a type of computer system used to collect, store, process, analyze, and share various types of data and information related to emergency medical care. The medical emergency center data information management system can receive and process dynamic information such as emergency calls, patient status, and ambulance location in real time, integrating data from multiple stages including pre-hospital emergency care, in-hospital emergency care, and command and dispatch; at the same time, it adheres to medical information exchange standards and emergency data specifications, ensuring the security of sensitive medical data and patient privacy.

[0003] However, existing medical emergency center data information management systems suffer from insufficient positioning accuracy. Relying on mobile phone base station positioning technology results in significant errors in complex urban areas or remote regions, potentially delaying rescue efforts. Furthermore, there is a risk of data leakage in emergency situations, with sensitive medical data potentially being leaked due to system vulnerabilities or poor internal management. Therefore, it is necessary to propose a high-precision medical emergency center data information management system and method to address these issues. Summary of the Invention

[0004] The purpose of this invention is to solve the above-mentioned problems by providing a high-precision medical emergency center data information management system and method to address the issues of large positioning errors and easy data leakage, thereby improving overall operational performance.

[0005] The technical solution of this invention is: a high-precision positioning data information management system for medical emergency centers, characterized in that: the system includes a multi-mode positioning terminal, an AI central platform, and an integrated emergency information sharing platform. The multi-mode positioning terminal collects raw positioning data (including latitude, longitude, altitude, and signal strength) through GPS, Bluetooth, or UWB sensors, processes the positioning data through a security gateway, and employs advanced encryption algorithms, such as symmetric encryption algorithms (e.g., AES) and asymmetric encryption algorithms (e.g., RSA). The processed data is distributed to the AI ​​central platform (different subsystems) according to priority. After AI processing, structured decision information is output to the integrated emergency information sharing platform, which enables cross-departmental collaboration to complete emergency tasks. The actual rescue results are then fed back to the AI ​​central platform for model optimization (reinforcement learning mechanism).

[0006] Furthermore, in the aforementioned high-precision medical emergency center data information management system, the structured decision information includes, but is not limited to, optimal ambulance dispatch, patient mortality risk prediction, and epidemic hotspot maps.

[0007] Furthermore, in the aforementioned high-precision medical emergency center data information management system, the AI ​​central platform includes a positioning optimization module, a security protection module, and a scheduling optimization module. The security protection module is a three-tiered protection mechanism, including a prevention unit, a detection unit, and corresponding units.

[0008] Furthermore, in the aforementioned high-precision medical emergency center data information management system, when the integrated emergency information sharing platform feeds back information to the multi-mode positioning terminal, it sends dynamic navigation paths and emergency knowledge pushes to the terminal, replans routes based on real-time traffic conditions (avoiding AI-predicted congestion points), and sends operation instructions to the medical staff's APP based on the patient's symptoms.

[0009] Furthermore, in the aforementioned high-precision medical emergency center data information management system, when the integrated emergency information sharing platform feeds information back to the security gateway, it updates the gateway access control policy and blacklist to automatically upgrade the data encryption level in the event of a sudden large-scale incident, thereby blocking connection requests from suspicious terminals.

[0010] Furthermore, in the aforementioned high-precision medical emergency center data information management system, the security gateway employs a dynamic traffic scrubbing algorithm (to combat DDoS attacks), the mathematical expression of which is:

[0011]

[0012] In the formula: d iLet be the i-th data packet; let be the set of legitimate traffic; let be the set of attack traffic; let be the data packet feature vector (packet length, frequency, source IP entropy); let be the n-th data packet; let be the σ-th data packet. n represents the mean and standard deviation of normal traffic characteristics; k is the dynamic threshold coefficient (which can be adaptively adjusted according to network load).

[0013] Furthermore, in the aforementioned high-precision medical emergency center data information management system, the security gateway employs a multimodal data desensitization algorithm (based on NLP + rule engine) to construct a sensitive field identification model. For text data T, the mathematical formula for calculating the sensitivity probability is: P sens (w i )=σ(α·BERT cls (w i )+β·R(w i ))

[0014] In the formula: w i R(w) is the i-th word element; i ): Regular expression matching score (e.g., ID card number regular expression); α and β are trainable weight parameters. Dynamic masking strategy:

[0015]

[0016] In addition, the above computational complexity control algorithm requires adaptive load balancing. The security gateway dynamically adjusts the processing pipeline based on CPU utilization U. The basic operating formula is as follows:

[0017]

[0018] Where: N max γ is the maximum number of parallel processing threads; γ is the decay coefficient.

[0019] This invention also provides a method for managing data information in a medical emergency center with high positioning accuracy, comprising the following steps:

[0020] Step S1: After the patient / witness initiates a distress call via the emergency app or 120 phone, the multi-mode positioning terminal is activated and environmental data is collected in real time. When the patient is in a dense urban environment, GPS, Bluetooth beacon and UWB combined positioning is activated; if the patient is in a remote mountainous area, the system switches to Beidou satellite, inertial navigation and ZigBee mode, runs the GDOP algorithm to select the optimal base station combination, calls the 3D map matching service and displays the final coordinates.

[0021] Step S2: Establish a quantum encryption channel through the security gateway, complete two-way identity authentication and multi-mode positioning terminal data encryption transmission, implement dynamic desensitization, block abnormal traffic, and send the processed structured data to the AI ​​central platform.

[0022] Step S3: Utilize the AI ​​central platform to calculate the optimal route based on the processed structured data. By inputting coordinates, real-time traffic conditions, and hospital capacity, predict the dynamic ETA under AI automatic adjustment. After obtaining diagnostic suggestions and resource allocation plans, send dispatch instructions to the emergency information integration and sharing platform.

[0023] Step S4: After receiving the dispatch instruction, the integrated emergency information sharing platform shares cross-departmental data through the IHE XDS.b protocol, generates navigation routes and emergency plans, and synchronously and collaboratively activates the vehicle-mounted and target hospital systems. On the one hand, it unlocks the necessary vehicle-mounted medical equipment (defibrillator / ventilator), preloads the patient's basic information to the vehicle-mounted tablet, and opens a real-time video consultation channel. On the other hand, the corresponding hospital system automatically starts, identifies the patient's de-identified information (including but not limited to gender / estimated age / preliminary diagnosis), estimated arrival time (accurate to ±1 minute), integrates the required resource list, and thus completes the emergency mission. Finally, it automatically records the complete emergency operation chain and uploads the encrypted model non-original data parameters of each node to complete the central aggregation update iteration of federated learning.

[0024] By adopting the technical solution of this invention, the command and dispatch functions of analyzing, coordinating, and controlling emergency, sudden and disaster events are fully realized, optimizing the level of emergency work and improving the treatment rate of critically ill patients. Real-time collection, aggregation and transmission of location data, synchronous sharing of real-time patient condition analysis data, and simultaneous pre-hospital and in-hospital treatment and condition analysis can race against time to save patients' lives and health. Through scientific analysis methods, personnel, vehicles and equipment can be rationally allocated, and the limited emergency resources can be fully utilized by using a sound 120 emergency command and dispatch system.

[0025] Compared with existing technologies, the technical solution of this invention improves positioning accuracy by using multi-source fusion positioning technology, selects the corresponding optimal positioning mode for different areas, shortens emergency response time, and allows for faster arrival at the patient's side for rescue. Moreover, after collecting patient information, key data is encrypted and stored to ensure data confidentiality, traceability, and security during transmission and storage. Attached Figure Description

[0026] Figure 1 This is a system framework diagram of the present invention;

[0027] Figure 2 This is a flow chart of the positioning of the AI ​​central platform of the present invention;

[0028] Figure 3 This is a system framework diagram of the AI ​​central platform of the present invention;

[0029] Figure 4 This is a flowchart illustrating the operation of the security protection module of the present invention.

[0030] Figure 5 This is a flowchart illustrating the complete emergency rescue information flow of this invention. Detailed Implementation

[0031] The technical solutions of the present invention will be further described below with reference to the accompanying drawings to make them easier to understand and master. The technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. 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.

[0032] like Figure 1 , Figure 2 and Figure 5 As shown, this invention provides a high-precision medical emergency center data information management system, including a multi-mode positioning terminal, an AI central platform, and an integrated emergency information sharing platform. Its modular design supports rapid integration with new technologies and is highly adaptable. The integrated emergency information sharing platform breaks down information silos, enabling three-terminal collaboration and reducing the average time for the entire process—from patient call, AI dispatch and triage, ambulance dispatch, and hospital preparation—from 10 minutes to 5 minutes.

[0033] According to the technical solution of the present invention, the multi-mode positioning terminal collects raw positioning data (including but not limited to latitude, longitude, altitude, and signal strength) through GPS, Bluetooth, or UWB sensors. The positioning data is processed by a security gateway, and advanced encryption algorithms are used, such as symmetric encryption algorithms (e.g., AES) and asymmetric encryption algorithms (e.g., RSA). The processed data is distributed to the AI ​​central platform (different subsystems) according to priority. After processing by the AI, structured decision information (including but not limited to optimal ambulance dispatch, patient mortality risk prediction, and epidemic hotspot maps) is output to the emergency information integrated sharing platform. The emergency information integrated sharing platform enables cross-departmental collaboration to complete emergency rescue tasks, and then the actual rescue results are sent back to the AI ​​central platform for model optimization (reinforcement learning mechanism).

[0034] Preferably, such as Figure 3 and Figure 4As shown, in the above structure: the AI ​​central platform includes a positioning optimization module, a security protection module, and a scheduling optimization module. The positioning optimization module optimizes the dynamic base station selection algorithm based on the GDOP matrix and integrates OpenStreeMap data to construct a terrain crossing cost model. The security protection module is a three-level protection mechanism for data security. The scheduling optimization module uses the DRL-DQN algorithm, allocates resources based on deep reinforcement learning, accesses GFT data, and generates an epidemic heat map for optimization and prediction. The epidemic heat map prediction module can provide early warning of clustered cases at least 2 hours in advance (this integrates an AI epidemic monitoring tool similar to Samdesk, but the processing speed in this case is faster and more efficient).

[0035] Specifically, the security protection module includes a prevention unit, a detection unit, and corresponding units. It trains a disease diagnosis model through federated learning to ensure that the data does not fall within a reasonable range. It then uses quantum encryption to transmit the patient's specific coordinates and performs full analysis of the operation chain. It detects abnormal operations through multimodal threat perception and finally uses blockchain auditing and evidence storage to prevent the operation records from being tampered with, thus having high security.

[0036] Preferably, in the above structure: when the integrated emergency information sharing platform feeds back information to the multi-mode positioning terminal, it sends dynamic navigation paths and emergency knowledge to the terminal, replans the route based on real-time traffic conditions (avoiding congestion points predicted by AI), and sends operation instructions to the medical staff's APP according to the patient's symptoms.

[0037] Preferably, in the above structure: when the emergency information integrated sharing platform feeds information back to the security gateway, it updates the gateway access control policy and blacklist to automatically upgrade the data encryption level in the event of a sudden large-scale incident, so as to block connection requests from suspicious terminals.

[0038] Specifically, the security gateway employs a dynamic traffic scrubbing algorithm (to combat DDoS attacks), the mathematical expression of which is:

[0039]

[0040] In the formula: d i Let be the i-th data packet; let be the set of legitimate traffic; let be the set of attack traffic; let be the data packet feature vector (packet length, frequency, source IP entropy); let be the n-th data packet; let be the σ-th data packet. n represents the mean and standard deviation of normal traffic characteristics; k is the dynamic threshold coefficient (which can be adaptively adjusted according to network load).

[0041] Specifically, the security gateway employs a multimodal data desensitization algorithm (based on NLP + rule engine) to construct a sensitive field identification model. For text data T, the mathematical formula for calculating the sensitivity probability is: P sens (w i )=σ(α·BERT cls (w i )+β·R(w i ))

[0042] In the formula: w i R(w) is the i-th word element; i ): Regular expression matching score (e.g., ID card number regular expression); α and β are trainable weight parameters.

[0043] Dynamic occlusion strategy:

[0044]

[0045] The high-precision medical emergency center data information management method of the present invention includes the following steps: 1) After a patient / witness initiates a distress call through an emergency APP or 120 telephone, a multi-mode positioning terminal is activated and environmental data is collected in real time. When the patient is in a dense urban environment, GPS, Bluetooth beacon and UWB combined positioning is activated; if the patient is in a remote mountainous area, the system switches to Beidou satellite, inertial navigation and ZigBee mode, runs the GDOP algorithm to select the optimal base station combination, calls the 3D map matching service, and displays the final coordinates; 2) A quantum encryption channel is established through a security gateway. After completing two-way identity authentication and encrypted transmission of multi-mode positioning terminal data, dynamic desensitization is implemented, and abnormal traffic is blocked. The processed structured data is then transmitted to the AI ​​central platform; 3) The AI ​​central platform calculates the optimal path based on the processed structured data. By inputting coordinates, real-time traffic conditions and hospital reception capacity, dynamic ETA is predicted under AI automatic adjustment. After obtaining diagnostic suggestions and resource allocation plans, a dispatch instruction is sent to the emergency information integrated sharing platform; 4) After receiving the dispatch instruction, the emergency information integrated sharing platform uses IHE... The XDS.b protocol shares cross-departmental data, generates navigation routes and emergency plans, and synchronously and collaboratively activates the vehicle-mounted and target hospital systems. On one hand, it unlocks the necessary vehicle-mounted medical equipment (defibrillator / ventilator), preloads the patient's basic information to the vehicle-mounted tablet, and opens a real-time video consultation channel. On the other hand, the corresponding hospital system automatically starts, identifies the patient's de-identified information (including but not limited to gender / estimated age / preliminary diagnosis), the estimated arrival time (accurate to ±1 minute), and integrates the required resource list to complete the emergency mission. Finally, it automatically records the complete emergency operation chain and uploads the encrypted model non-original data parameters of each node to complete the central aggregation and update iteration of federated learning.

[0046] The multi-source fusion positioning technology and data AI encryption technology incorporated in this invention are key to its technical solution. Deep integration of multi-mode positioning improves emergency positioning accuracy, while AI assistance enhances data security. This not only reconstructs the emergency medical service model but also completes a closed-loop emergency medical system. For equipment mounted on ambulances, those skilled in the art can perform conventional setups based on existing technologies; this invention does not have special requirements regarding model selection or combination of these devices.

[0047] Thus, by adopting the technical solution of this invention, the command and dispatch functions of analysis, planning, organization, coordination, and timely control of emergency, sudden, and disaster events are fully realized. By integrating regional pre-hospital and in-hospital emergency resources with high-quality professional resources, the level of emergency work is optimized, which helps to improve the treatment rate of critically ill patients, reduce post-treatment risks, and thus improve public health medical services. It also enables timely data collection and response capabilities; real-time collection, aggregation, and transmission of location data, and synchronous sharing of real-time patient condition analysis data, and simultaneous pre-hospital and in-hospital treatment and condition analysis, race against time to save patients' lives and health. Through scientific analysis methods, personnel, vehicles, and equipment can be rationally allocated, and the use of a complete 120 emergency command and dispatch subsystem can make the most of limited emergency resources, reducing or avoiding medical disputes.

[0048] As described above, compared with existing technologies, the technical solution of this invention improves positioning accuracy through multi-source fusion positioning technology, selects the optimal positioning mode for different areas, shortens emergency response time, and allows for faster arrival at the patient's side for rescue. Furthermore, after collecting patient information, key data is encrypted and stored to ensure data confidentiality, traceability, and security during transmission and storage. Additionally, suitable encryption algorithms and key lengths can be selected for different data types and storage requirements to achieve optimal security.

[0049] The technical solution, working process, and implementation effects of the present invention have been described in detail above. It should be noted that the described examples are only typical examples of the present invention. In addition, the present invention may have many other specific implementation methods. All technical solutions formed by equivalent substitution or equivalent transformation fall within the scope of protection claimed by the present invention.

Claims

1. A high-precision medical emergency center data information management system, characterized in that: The system includes a multi-mode positioning terminal, an AI central platform, and an integrated emergency information sharing platform. The multi-mode positioning terminal collects raw positioning data through GPS, Bluetooth, or UWB sensors. The processed data is distributed to the AI ​​central platform according to priority via a security gateway. After AI processing, structured decision information is output to the integrated emergency information sharing platform. The integrated emergency information sharing platform enables cross-departmental collaboration to complete emergency rescue tasks and then sends the actual rescue results back to the AI ​​central platform for model optimization.

2. The high-precision medical emergency center data information management system according to claim 1, characterized in that: The structured decision information includes, but is not limited to, optimal ambulance dispatch, patient mortality risk prediction, and epidemic hotspot maps.

3. The high-precision medical emergency center data information management system according to claim 1, characterized in that: The AI ​​central platform includes a positioning optimization module, a security protection module, and a scheduling optimization module. The security protection module is a three-tiered protection mechanism, including a prevention unit, a detection unit, and corresponding units.

4. The high-precision medical emergency center data information management system according to claim 1, characterized in that: When the integrated emergency information sharing platform feeds information back to the multi-mode positioning terminal, it sends dynamic navigation routes and emergency knowledge to the terminal, replans the route based on real-time traffic conditions, and sends operation instructions to the medical staff's APP according to the patient's symptoms.

5. The high-precision medical emergency center data information management system according to claim 1 or 4, characterized in that: When the emergency information sharing platform feeds information back to the security gateway, it updates the gateway's access control policy and blacklist to automatically upgrade the data encryption level in the event of a large-scale emergency, thereby blocking connection requests from suspicious terminals.

6. The high-precision medical emergency center data information management system according to claim 1, characterized in that, The security gateway employs a dynamic traffic scrubbing algorithm, the mathematical expression of which is: In the formula: d i Let be the i-th data packet; let mathcal(L) be the set of legitimate traffic; let \mathcalA be the set of attack traffic; let \mathbf(d) be the data packet feature vector; let \mathbf(\mu)n; \σ n represents the mean and standard deviation of normal flow characteristics; k is the dynamic threshold coefficient.

7. The high-precision medical emergency center data information management system according to claim 6, characterized in that: The security gateway employs a multimodal data desensitization algorithm to construct a sensitive field identification model. For text data T, the mathematical formula for calculating the sensitivity probability is as follows: P sens (w i )=σ(α·BERT cls (oh i )+β·R(ω i )) In the formula: w i R(w) is the i-th word element; i ): Regular expression rule matching score; α and β are trainable weight parameters.

8. A method for managing data information in a medical emergency center with high positioning accuracy, characterized in that, Includes the following steps: Step S1: After the patient / witness initiates a distress call through the emergency app or 120 phone, the multi-mode positioning terminal is activated and environmental data is collected in real time. The GDOP algorithm is run to select the optimal combination of base stations, and the 3D map matching service is called to display the final coordinates. Step S2: Establish a quantum encryption channel through the security gateway, complete two-way identity authentication and multi-mode positioning terminal data encryption transmission, implement dynamic desensitization, block abnormal traffic, and send the processed structured data to the AI ​​central platform. Step S3: Utilize the AI ​​central platform to calculate the optimal route based on the processed structured data. By inputting coordinates, real-time traffic conditions, and hospital capacity, predict the dynamic ETA under AI automatic adjustment. After obtaining diagnostic suggestions and resource allocation plans, send dispatch instructions to the emergency information integration and sharing platform. Step S4: After receiving the dispatch instruction, the integrated emergency information sharing platform shares cross-departmental data through the IHE XDS.b protocol, generates navigation routes and emergency plans, and synchronously and collaboratively starts the vehicle-mounted and target hospital systems. On the one hand, it unlocks the necessary vehicle-mounted medical equipment, preloads the patient's basic information to the vehicle-mounted tablet, and opens a real-time video consultation channel. On the other hand, the corresponding hospital system automatically starts, identifies the patient's de-identified information, estimates the arrival time, and integrates the required resource list to complete the emergency task. Finally, it automatically records the complete emergency operation chain and uploads the encrypted model parameters of each node to complete the central aggregation and update iteration of federated learning.

9. The high-precision medical emergency center data information management method according to claim 8, characterized in that: In step S1, when the patient is in a dense urban environment, a combination of GPS, Bluetooth beacon and UWB positioning is activated; if the patient is in a remote mountainous area, the system switches to Beidou satellite, inertial navigation and ZigBee mode.

Images