First-aid rescue process tracking system and method

Abstract

The invention relates to the technical field of rescue data processing, and discloses an emergency rescue process tracking system and method, and the system comprises a collection module which is used for collecting dial information, user real-time information and historical pathological information, and judging whether to start rescue process tracking or not; the processing module comprises a processing unit, a judging unit and an adjusting unit, and when it is judged that rescue process tracking is started, the processing unit determines feature information and determines a recommendation scheme; the judgment unit collects rescue path information to judge whether the recommendation scheme is adjusted or not; when the adjustment is judged to be carried out, the adjustment unit determines an adjustment scheme based on a clustering result; the interaction module is used for realizing communication and interaction of users, users and rescuers based on Flutter; and the sharing module is used for sharing the rescue process tracking information to the emergency contact person, the user, the user and the rescuer. According to the invention, through intelligent triggering, recommendation, dynamic optimization, multi-terminal interaction and sharing, the response speed and the treatment quality of emergency rescue are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of rescue data processing, and in particular to a first aid rescue process tracking system and method. Background Art

[0002] As medical emergency response systems continue to evolve, intelligent rescue systems are playing a vital role in improving emergency response efficiency, optimizing information sharing, and reducing rescue delays. Modern intelligent emergency systems often rely on technologies such as mobile devices, GPS tracking, and artificial intelligence analysis to enhance the quality of patient care in emergency situations.

[0003] Currently, existing systems rely primarily on manual user input or preset conditions to trigger the rescue process, lacking automated judgment mechanisms. For example, calling an emergency number doesn't automatically trigger rescue progress tracking, resulting in the inability to collect and process patient information in certain situations (such as sudden illness or confusion). Using fixed plans while awaiting rescue makes it difficult to generate an optimal plan based on the patient's real-time physiological information (such as heart rate, blood oxygen level, and allergy history), thus impacting treatment effectiveness.

[0004] Therefore, it is necessary to design a first aid rescue process tracking system and method to solve the problems existing in the current technology. Summary of the Invention

[0005] In view of this, the present invention proposes an emergency rescue process tracking system and method, which aims to solve the problems that the current rescue process startup method is single and cannot intelligently judge whether tracking is needed, the real-time information processing is not accurate enough, and there is a lack of personalized recommendation solutions.

[0006] In one aspect, the present invention provides a first aid rescue process tracking system, comprising:

[0007] The collection module is used to collect dial code information, user real-time information and historical pathological information, and determine whether to start rescue process tracking based on the dial code information;

[0008] a processing module comprising a processing unit, a judgment unit, and an adjustment unit, wherein the processing module is connected to the acquisition module. When the acquisition module determines to start rescue process tracking, the processing unit processes the real-time information based on an information importance model to determine characteristic information, and determines a recommended solution based on the characteristic information; the judgment unit collects rescue path information, and determines whether to adjust the recommended solution based on the rescue path information; when it is determined to adjust, the adjustment unit processes the rescue path information and characteristic information based on K-Means clustering, and determines an adjustment solution based on the clustering result;

[0009] The interaction module uses Flutter to enable communication and interaction between users, users, and rescuers;

[0010] The sharing module is used to share rescue process tracking information with emergency contacts, users, users and rescuers. The rescue process tracking information includes the recommended plan, rescue path information, interaction records and adjustment plans.

[0011] Furthermore, when the acquisition module determines whether to start the rescue process tracking according to the dial code information, it includes:

[0012] The acquisition module compares the dial code information with the emergency phone list and determines whether to start rescue process tracking based on the comparison result;

[0013] When the dial code information is identical to any data in the emergency phone list, the collection module determines to start rescue process tracking.

[0014] Furthermore, the acquisition module acquires the user's real-time information and historical pathological information, and processes the real-time information based on the information importance model to determine characteristic information, including:

[0015] The processing unit obtains a pathology information dataset, and samples the pathology information dataset according to a preset ratio to obtain a training subset and a test subset;

[0016] The processing unit is used to obtain a pre-selected neural network model, and iteratively train the neural network model according to the training subset, evaluate the iteratively trained neural network model according to the test subset, and obtain the information importance model.

[0017] Furthermore, when the processing unit processes the real-time information based on the information importance model to determine the characteristic information, it further includes:

[0018] The processing unit is configured to reduce the amplitude of the change in the gradient direction of the neural network model if the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, and continue iterative training until a preset number of iterations is reached;

[0019] The processing unit is used to stop iterative training if the evaluation value of the neural network model after the current iterative training is greater than or equal to the evaluation value of the neural network model after the previous iterative training.

[0020] Furthermore, when the processing unit determines a recommendation solution based on the feature information, the processing unit includes:

[0021] The similarity between the feature information and each historical feature information in the feature information-solution table is obtained, and the recommended solution is determined according to the historical solution corresponding to the maximum similarity value, wherein the feature information-solution table includes a plurality of historical feature information and a plurality of historical solutions, and each historical feature information corresponds to a historical solution.

[0022] Furthermore, when the judgment unit judges whether to adjust the recommended plan according to the rescue path information, it includes:

[0023] The judgment unit obtains a path duration according to the rescue path information, compares the path duration with a duration threshold, and determines whether to adjust the recommended plan according to the comparison result;

[0024] When the path duration is greater than a duration threshold, determining to adjust the recommended solution;

[0025] When the path duration is less than or equal to the duration threshold, it is determined that the recommended solution is not adjusted.

[0026] Furthermore, when the judgment unit determines to adjust the recommended solution, the adjustment unit processes the rescue path information and feature information based on K-Means clustering, including:

[0027] The adjustment unit normalizes the rescue path information and the feature information to obtain a cluster vector;

[0028] S1: The adjustment unit initializes K centroids in all adjustment schemes and assigns the clustering vector to the nearest centroid to form K clusters;

[0029] S2: Recalculate the centroid of each cluster;

[0030] S3: Repeat S1 and S2 until the center of mass no longer changes;

[0031] S4: When there is only one data in the cluster where the cluster vector is located, an early warning is issued to the rescuer and the adjustment plan is obtained; when there are two or more data in the cluster where the cluster vector is located, the historical adjustment plans corresponding to the remaining historical cluster vectors in the cluster are used as the adjustment plan;

[0032] The adjustment solution set includes a plurality of historical clustering vectors and historical adjustment solutions, and each of the historical clustering vectors corresponds to a historical adjustment solution.

[0033] Furthermore, when the adjustment unit processes the rescue path information and feature information based on K-Means clustering, it further includes:

[0034] The centroid calculation formula is as follows:

[0035]

[0036] Where Mk represents the centroid of the k-th cluster, |Nk| represents the number of feature sets in the k-th cluster, and Zi represents the feature set of the i-th historical clustering vector.

[0037] Furthermore, the emergency rescue process tracking system also includes:

[0038] A storage module is used to store the rescue process tracking information, historical pathology information and user real-time information.

[0039] Compared with the prior art, the beneficial effect of the present invention is that: through the intelligent rescue process tracking mechanism, it solves the problems of unintelligent rescue triggering, inflexible rescue paths, and inefficient information interaction in the existing emergency rescue system, thereby improving the efficiency of emergency rescue and the accuracy of information sharing. The acquisition module intelligently determines whether to start rescue process tracking based on the dial code information, avoiding the disadvantages of traditional reliance on manual user input, enabling the system to respond in emergency situations and improving the timeliness of emergency rescue. The processing module uses an information importance model to filter the user's real-time information (such as heart rate, blood oxygen, allergy history, etc.), and combines historical pathological information to generate the optimal recommendation plan to ensure that the rescue plan is more personalized and accurate. The judgment unit collects rescue path information in real time, dynamically adjusts the recommendation plan based on the ambulance's driving conditions and the patient's condition, and optimizes the rescue strategy through the adjustment unit using the K-Means clustering algorithm when necessary to achieve intelligent dynamic adjustment. The interaction module is built based on Flutter to ensure smooth multi-terminal information interaction between patients, users and rescue personnel, and supports multi-modal input such as voice and text to improve communication efficiency. The sharing module further strengthens the information synchronization mechanism, sharing rescue process information (including recommended plans, rescue routes, interaction records and adjustment plans) in real time with emergency contacts, patients and rescue teams, ensuring information transparency, reducing family anxiety, and optimizing the seamless connection between pre-hospital emergency care and in-hospital treatment.

[0040] On the other hand, the present application also provides a first aid and rescue process tracking method, which is applied to the first aid and rescue process tracking system, comprising:

[0041] Collect dial code information, and determine whether to start rescue process tracking based on the dial code information;

[0042] When it is determined that rescue process tracking is to be started, the user's real-time information and historical pathology information are collected, the real-time information is processed based on the information importance model to determine characteristic information, and a recommended solution is determined based on the characteristic information; rescue path information is collected, and based on the rescue path information, it is determined whether to adjust the recommended solution; if it is determined that adjustment is to be made, the rescue path information and characteristic information are processed based on K-Means clustering, and an adjustment solution is determined based on the clustering results;

[0043] Sharing rescue progress tracking information with emergency contacts, users, users, and rescuers, the rescue progress tracking information including the recommended plan, rescue path information, interaction records, and adjustment plans;

[0044] The rescue process tracking information, historical pathology information and user real-time information are stored.

[0045] It is understandable that the above-mentioned emergency rescue process tracking system and method have the same beneficial effects, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0047] Figure 1 A structural block diagram of the first aid and rescue process tracking system provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0048] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0049] In some embodiments of the present application, see Figure 1 As shown, a first aid rescue process tracking system includes:

[0050] The collection module is used to collect dial code information, user real-time information and historical pathology information, and determine whether to start rescue process tracking based on the dial code information.

[0051] The processing module includes a processing unit, a judgment unit, and an adjustment unit. The processing module is connected to the acquisition module. When the acquisition module determines to initiate rescue progress tracking, the processing unit processes real-time information based on an information importance model to determine feature information and, based on this feature information, determines a recommended solution. The judgment unit collects rescue route information and, based on this information, determines whether to adjust the recommended solution. If an adjustment is determined, the adjustment unit processes the rescue route information and feature information using K-Means clustering and determines an adjustment solution based on the clustering results.

[0052] The interaction module uses Flutter to enable communication and interaction between users, users, and rescuers.

[0053] The sharing module is used to share rescue process tracking information with emergency contacts, users, users and rescuers. The rescue process tracking information includes recommended plans, rescue path information, interaction records and adjustment plans.

[0054] Specifically, this embodiment achieves precise and efficient pre-hospital emergency process management through intelligent data collection, dynamic information processing, smart path adjustment, interactive optimization, and information sharing. The system comprises an acquisition module, a processing module, an interactive module, and a sharing module, all working together to ensure the real-time, intelligent, and efficient rescue process.

[0055] Specifically, when using the system, users can set certain parameters in advance. For example, they can set the primary phone, backup phone, or watch from which to make emergency calls. They can also set their emergency medical information, the hospital they prefer to go to after calling an ambulance, the conditions that automatically trigger the rescue process, the emergency contact number, and whether to share the rescue process with the emergency contact.

[0056] Specifically, the acquisition module is mainly responsible for collecting dial code information for collecting dial code information, user real-time information and historical pathological information. The dial code information is automatically determined whether to start rescue process tracking by monitoring the emergency calls (such as 120, 911, etc.) dialed by the user or the SOS emergency help signal of the smart device. Based on the phone monitoring API and emergency call detection mechanism provided by the operating system, it monitors whether the user has dialed the emergency call; combined with the emergency help trigger signal provided by smart devices (such as smart watches, wearable health devices and sweeping robots), the rescue tracking process is automatically started. For example, when the sweeping robot recognizes that a person has fallen to the ground and has not gotten up for more than a certain time threshold, it dials an emergency call or an SOS help signal. When the system detects that an emergency call or an SOS help signal has been dialed, the acquisition module starts immediately and transmits a signal to the processing module to trigger the subsequent data collection and analysis process to ensure the automatic triggering of the rescue process and improve the first aid response speed.

[0057] Specifically, in some embodiments of the present application, an auxiliary backup device may be added, such as a backup mobile phone or watch. When an emergency call is automatically initiated, if the main mobile phone is out of power, the backup mobile phone or watch may be automatically enabled to initiate an emergency call.

[0058] Specifically, the processing module includes a processing unit, a judgment unit, and an adjustment unit, which are responsible for data processing, solution recommendation, and dynamic optimization. Real-time user information refers to the current user's physiological data. The processing unit screens and analyzes the user's real-time physiological data (such as heart rate, blood oxygen, and blood pressure) and historical pathological information (such as chronic diseases, drug allergies, and previous medical history) based on an information importance model. User physiological information is collected in real time through smart devices (such as smart watches, mobile health monitoring apps, etc.) or manual input, and combined with the pathological information dataset. A weight analysis is performed using an information importance model to filter out the feature information most relevant to the current emergency situation (for example, when a heart patient experiences sudden chest pain, blood oxygen, heart rate, and other data are prioritized). Combined with the filtered feature information, the optimal rescue plan in the medical database is matched, a recommended plan is generated, and pushed to the user's device and the rescuer's device. The judgment unit collects the ambulance's current location, driving route, and road traffic conditions based on GPS tracking and real-time traffic monitoring APIs, and determines whether the recommended plan needs to be adjusted. The system collects the ambulance's real-time location and route, as well as available beds in the hospital's emergency department. If traffic congestion, insufficient emergency resources, or a more optimal route are detected, the recommended plan needs to be adjusted, and the adjustment unit is notified to perform the optimization. Using the K-Means clustering algorithm, the adjustment unit performs cluster analysis on the route information and feature information to determine the optimal treatment plan.

[0059] It can be understood that when judging whether to adjust the recommended plan based on the rescue path information, it includes determining the adjustment plan based on the rescue path information (road congestion, driving distance) and feature information (extracted based on real-time user information). At this time, the adjustment plan includes some first aid measures suggestions for the user before the rescuer arrives.

[0060] It is understood that the sharing module in the embodiment of the present application not only displays the rescue progress, such as the ambulance arrival time, on the mobile phone that initiated the emergency call, but also shares the rescue progress with the emergency contact. At the same time, the user and the user can be notified via SMS or message when the ambulance is about to arrive, thereby shortening the waiting time.

[0061] It is understandable that, based on this embodiment, the current road congestion situation and hospital emergency resources (such as beds, doctors on duty, and emergency equipment conditions) can be further collected to adjust the user's final emergency route according to the resource situation. For example, cerebral infarction thrombolysis is best treated within 6 hours after onset. After dialing the emergency number, the system can estimate the time to pick up the patient to the hospital based on the location of the ambulance, the patient, and the hospital. Combined with the patient's current condition and the hospital's treatment capabilities (whether it has thrombolysis capabilities), the most suitable hospital is recommended after comprehensive consideration and pushed to the user and rescuer terminal.

[0062] Specifically, the interaction module, developed based on the Flutter framework, supports cross-platform interaction (Android, iOS, Web, etc.), ensuring smooth communication between users, users (such as emergency contacts and patients), and rescuers. WebSocket is integrated to achieve low-latency real-time communication, ensuring synchronization of rescue progress information. Users, users, emergency contacts, and rescuers can view information such as ambulance location, estimated time of arrival, and rescue plan through the interactive interface. User refers to the patient, user refers to the patient or other person who called the emergency room, and rescuer refers to the medical staff. Text or voice input can be used to supplement the on-site situation, helping medical staff to more accurately assess the patient's condition. Rescue personnel can use this interface to provide rescue progress and medical advice to the patient's family. The sharing module is responsible for synchronizing rescue progress information with emergency contacts, patients, users (such as caregivers), and rescuers, ensuring transparency and coordinated rescue efforts. The collected recommended plans, rescue route information, interaction records and adjustment plans are stored in the cloud in real time and pushed to the equipment of relevant personnel; emergency contacts (such as patients' families) can view the rescue progress in real time through the mobile app and interact with medical staff; medical institutions can obtain complete rescue records to ensure that they have a complete patient medical history when they receive emergency treatment, thereby improving treatment efficiency.

[0063] It's understandable that dial code information intelligently triggers rescue progress tracking, preventing patients from missing the optimal treatment opportunity due to sudden conditions (such as coma or confusion). Based on an information importance model, real-time patient health data is screened, and the rescue plan is dynamically optimized using the K-Means clustering algorithm to achieve personalized and precise rescue plan recommendations. The interactive module is developed using the cross-platform Flutter to ensure seamless communication between patients, families, and rescue teams, reducing anxiety and misjudgments caused by information lags. The sharing module further optimizes the information synchronization mechanism, making the rescue process more transparent and improving the collaborative efficiency between medical teams and patients' families.

[0064] In some embodiments of the present application, when the acquisition module determines whether to start rescue process tracking based on the dial code information, it includes: the acquisition module compares the dial code information with the emergency phone list, and determines whether to start rescue process tracking based on the comparison result.

[0065] Specifically, when the dial code information is the same as any data in the emergency phone list, the collection module determines to start rescue process tracking.

[0066] It is understandable that through the dial code comparison mechanism, it can automatically determine whether to start the rescue process, avoiding rescue delays caused by factors such as patients' blurred consciousness and incorrect operations in emergency situations. Using a hash table or Trie tree structure to store the emergency phone number list reduces the time complexity of dial information matching to O(1) or O(log n), ensuring a quick response. The rescue process will not be mistakenly triggered by ordinary dialing behavior (such as calling family or friends), ensuring the intelligent operation of the system and reducing resource waste. The emergency phone number list can be dynamically updated through the cloud to adapt to the emergency systems of different countries and regions, making the system globally adaptable. Once an emergency dial is identified, the system can simultaneously collect the patient's location information and push it to the rescue center to achieve precise rescue and improve rescue efficiency.

[0067] In some embodiments of the present application, a processing unit collects real-time user information and historical pathology information, and processes the real-time information based on an information importance model to determine characteristic information. The processing unit obtains a pathology information dataset, samples the pathology information dataset according to a preset ratio to obtain a training subset and a test subset. The processing unit is configured to obtain a preselected neural network model, iteratively train the neural network model based on the training subset, evaluate the iteratively trained neural network model based on the test subset, and obtain an information importance model.

[0068] In some embodiments of the present application, when the processing unit processes the real-time information based on the information importance model to determine the feature information, the processing unit further includes: if the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, the processing unit is configured to reduce the amplitude of the change in the gradient direction of the neural network model and continue iterative training until a preset number of iterations is reached. If the evaluation value of the neural network model after the current iterative training is greater than or equal to the evaluation value of the neural network model after the previous iterative training, the processing unit is configured to stop iterative training.

[0069] In some embodiments of the present application, when the processing unit determines a recommended solution based on feature information, it includes: obtaining the similarity between the feature information and each historical feature information in the feature information-solution table, and determining a recommended solution based on the historical solution corresponding to the maximum similarity value, the feature information-solution table includes several historical feature information and several historical solutions, and each historical feature information corresponds to a historical solution.

[0070] Specifically, the pathology dataset consists of various pathologies and their key features at onset, acquired through big data. Pathology feature data (such as blood pressure, heart rate, and medical history) is input. Feature extraction is performed through multiple neural layers to identify key relevant features of the pathology. The importance of each pathology feature is assigned a score. The trained neural network model is then evaluated on a test subset to ensure its predictive power on new data.

[0071] It's understandable that deep learning extracts the most critical patient pathological information, making emergency plans more targeted and improving rescue success rates. A gradient adjustment mechanism enables the neural network model to adaptively optimize under varying data environments, improving the stability and generalization capabilities of the rescue system. An information importance model filters out less significant data that has a small impact on rescue decisions, accelerating system response. Test subset evaluation and gradient optimization prevent the model from overfitting to the training data, ensuring robust predictions in real-world rescue scenarios.

[0072] In some embodiments of the present application, when the judgment unit judges whether to adjust the recommended plan based on the rescue path information, it includes: the judgment unit obtains the path duration based on the rescue path information, compares the path duration with the duration threshold, and judges whether to adjust the recommended plan based on the comparison result.

[0073] Specifically, when the path duration is greater than the duration threshold, it is determined that the recommended solution should be adjusted. When the path duration is less than or equal to the duration threshold, it is determined that the recommended solution should not be adjusted.

[0074] In some embodiments of the present application, when the judgment unit determines to adjust the recommended plan, the adjustment unit processes the rescue path information and feature information based on K-Means clustering, including: the adjustment unit normalizes the rescue path information and feature information to obtain a clustering vector.

[0075] S1: The adjustment unit initializes K centroids in all adjustment schemes and assigns clustering vectors to the nearest centroids to form K clusters.

[0076] S2: Recalculate the centroid of each cluster.

[0077] S3: Repeat S1 and S2 until the center of mass no longer changes.

[0078] S4: When there is only one data in the cluster where the cluster vector is located, an early warning is issued to the rescuer and an adjustment plan is obtained. When there are two or more data in the cluster where the cluster vector is located, the historical adjustment plan corresponding to the remaining historical cluster vectors in the cluster is used as the adjustment plan.

[0079] The adjustment solution set includes a plurality of historical clustering vectors and historical adjustment solutions, and each historical clustering vector corresponds to a historical adjustment solution.

[0080] In some embodiments of the present application, when the adjustment unit processes the rescue path information and feature information based on K-Means clustering, it further includes:

[0081] The formula for calculating the center of mass is as follows:

[0082]

[0083] Where Mk represents the centroid of the k-th cluster, |Nk| represents the number of feature sets in the k-th cluster, and Zi represents the feature set of the i-th historical clustering vector.

[0084] It's understandable that intelligent assessment of ambulance travel times can optimize rescue strategies based on real-time traffic conditions, ensuring optimal rescue efficiency. Cluster analysis can automatically adjust rescue plans, avoiding the limitations of fixed protocols and improving the ability to respond to diverse patient situations. This solution not only relies on historical data but also incorporates real-time route information, achieving the dual guarantees of real-time monitoring and intelligent data optimization, thereby improving rescue success rates.

[0085] In some embodiments of the present application, the first aid rescue process tracking system further includes:

[0086] The storage module is used to store rescue process tracking information, historical pathology information and real-time user information.

[0087] Specifically, a combination of SQL databases (such as MySQL and PostgreSQL) and NoSQL databases (such as MongoDB) is used to implement structured and unstructured data storage: SQL database: stores structured data such as medical records, rescue records, and interaction logs. NoSQL database: stores real-time monitoring data, such as continuously changing heart rate and blood oxygen data. Rescue process tracking information includes records of the entire process from calling the emergency number to the arrival of the ambulance at the scene and then to the hospital. It includes information such as the ambulance's location, estimated arrival time, first aid measures, and interaction records between medical staff. Historical pathology information includes storage of health data such as the user's medical history, allergy history, chronic diseases, and recent medical records. This information can be used to match the optimal rescue plan and improve the targeted nature of rescue. User real-time information includes the collection of data such as the user's current vital signs (such as heart rate, blood oxygen, blood pressure), symptom descriptions (such as dizziness and chest pain), and other data.

[0088] As you can see, the storage module allows the system to fully record the rescue process, combining historical pathological information with real-time data to improve the scientific nature of rescue decisions. Efficient indexing and caching technologies enable medical staff to query patient medical histories in seconds, speeding up rescue response times. Encrypted storage combined with access control ensures that patient information is protected from unauthorized access, complying with medical data security standards. Stored historical data can also be used to train machine learning models, continuously optimizing future rescue plans and enhancing the intelligence of the emergency response system.

[0089] In the above embodiment, the intelligent rescue process tracking mechanism solves the problems of unintelligent rescue triggering, inflexible rescue paths, and inefficient information interaction in the existing emergency rescue system, thereby improving the efficiency of emergency rescue and the accuracy of information sharing. The acquisition module intelligently determines whether to start rescue process tracking based on the dial code information, avoiding the disadvantages of traditional reliance on manual user input, enabling the system to respond in emergency situations and improving the timeliness of emergency rescue. The processing module uses an information importance model to filter the user's real-time information (such as heart rate, blood oxygen, allergy history, etc.), and combines historical pathological information to generate the best recommendation plan to ensure that the rescue plan is more personalized and accurate. The judgment unit collects rescue path information in real time, dynamically adjusts the recommended plan based on the ambulance's driving conditions and the patient's condition, and optimizes the rescue strategy through the adjustment unit using the K-Means clustering algorithm when necessary to achieve intelligent dynamic adjustment. The interaction module is built based on Flutter to ensure smooth multi-terminal information interaction between patients, users and rescue personnel, and supports multi-modal input such as voice and text to improve communication efficiency. The sharing module further strengthens the information synchronization mechanism, sharing rescue process information (including recommended plans, rescue routes, interaction records and adjustment plans) in real time with emergency contacts, patients and rescue teams, ensuring information transparency, reducing family anxiety, and optimizing the seamless connection between pre-hospital emergency care and in-hospital treatment.

[0090] In another preferred embodiment based on the above embodiment, this embodiment provides a method for tracking an emergency rescue process, which is applied to the above emergency rescue process tracking system, including:

[0091] S100: Collect dial code information and determine whether to start rescue process tracking based on the dial code information.

[0092] S200: When it is determined that rescue progress tracking is enabled, real-time user information and historical pathology information are collected. Based on the information importance model, the real-time information is processed to determine characteristic information, and a recommended plan is determined based on this characteristic information. Rescue route information is collected, and based on this information, a determination is made as to whether the recommended plan should be adjusted. If an adjustment is determined, the rescue route information and characteristic information are processed using K-Means clustering, and an adjustment plan is determined based on the clustering results.

[0093] S300: Sharing rescue process tracking information with emergency contacts, users, users and rescuers. The rescue process tracking information includes recommended plans, rescue path information, interaction records and adjustment plans.

[0094] S400: Storing rescue process tracking information, historical pathology information, and user real-time information.

[0095] As can be understood, the intelligent rescue progress tracking mechanism solves existing emergency systems' problems of unintelligent rescue triggering, inflexible rescue routes, and inefficient information exchange, thereby improving emergency efficiency and the accuracy of information sharing. The collection module intelligently determines whether to enable rescue progress tracking based on dial code information, avoiding the drawbacks of traditional reliance on manual user input. This enables the system to respond to emergencies and improves the timeliness of emergency care. The processing module uses an information importance model to filter real-time user information (such as heart rate, blood oxygen level, and allergy history) and, combined with historical pathological information, generates optimal recommendations, ensuring more personalized and accurate rescue plans. The judgment unit collects rescue route information in real time and dynamically adjusts the recommended plan based on ambulance driving conditions and patient conditions. When necessary, the adjustment unit uses the K-Means clustering algorithm to optimize the rescue strategy, enabling intelligent dynamic adjustments. The interaction module, built on Flutter, ensures smooth multi-terminal information exchange between patients, users, and rescue personnel, and supports multimodal input such as voice and text to improve communication efficiency. The sharing module further strengthens the information synchronization mechanism, sharing rescue process information (including recommended plans, rescue routes, interaction records and adjustment plans) in real time with emergency contacts, patients and rescue teams, ensuring information transparency, reducing family anxiety, and optimizing the seamless connection between pre-hospital emergency care and in-hospital treatment.

[0096] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific implementations of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A first aid rescue process tracking system, characterized in that: include: The collection module is used to collect dial code information, user real-time information and historical pathological information, and determine whether to start rescue process tracking based on the dial code information; a processing module, comprising a processing unit, a judgment unit, and an adjustment unit; the processing module is connected to the acquisition module; when the acquisition module determines to start rescue process tracking, the processing unit processes the real-time information based on an information importance model to determine feature information, and determines a recommended solution based on the feature information; The judgment unit collects rescue path information and determines whether to adjust the recommended plan based on the rescue path information; when it is determined that the recommended plan is to be adjusted, the adjustment unit processes the rescue path information and feature information based on K-Means clustering and determines the adjustment plan based on the clustering result; The interaction module uses Flutter to enable communication and interaction between users, users, and rescuers; The sharing module is used to share rescue process tracking information with emergency contacts, users, users and rescuers. The rescue process tracking information includes the recommended plan, rescue path information, interaction records and adjustment plans.

2. The emergency rescue process tracking system according to claim 1, characterized in that: When the acquisition module determines whether to start the rescue process tracking according to the dial code information, it includes: The acquisition module compares the dial code information with the emergency phone list and determines whether to start rescue process tracking based on the comparison result; When the dial code information is identical to any data in the emergency phone list, the collection module determines to start rescue process tracking.

3. The emergency rescue process tracking system according to claim 1, characterized in that: When the processing unit processes the real-time information based on the information importance model to determine the characteristic information, it includes: The processing unit obtains a pathology information dataset, and samples the pathology information dataset according to a preset ratio to obtain a training subset and a test subset; The processing unit is used to obtain a pre-selected neural network model, and iteratively train the neural network model according to the training subset, evaluate the iteratively trained neural network model according to the test subset, and obtain the information importance model.

4. The emergency rescue process tracking system according to claim 3, characterized in that: When the processing unit processes the real-time information based on the information importance model to determine the characteristic information, the processing unit further includes: The processing unit is configured to reduce the amplitude of the change in the gradient direction of the neural network model if the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, and continue iterative training until a preset number of iterations is reached; The processing unit is used to stop iterative training if the evaluation value of the neural network model after the current iterative training is greater than or equal to the evaluation value of the neural network model after the previous iterative training.

5. The emergency rescue process tracking system according to claim 4, characterized in that: When the processing unit determines a recommendation solution based on the feature information, it includes: The similarity between the feature information and each historical feature information in the feature information-solution table is obtained, and the recommended solution is determined according to the historical solution corresponding to the maximum similarity value, wherein the feature information-solution table includes a plurality of historical feature information and a plurality of historical solutions, and each historical feature information corresponds to a historical solution.

6. The emergency rescue process tracking system according to claim 1, characterized in that: When the judging unit judges whether to adjust the recommended plan according to the rescue path information, the method includes: The judgment unit obtains a path duration according to the rescue path information, compares the path duration with a duration threshold, and determines whether to adjust the recommended plan according to the comparison result; When the path duration is greater than a duration threshold, determining to adjust the recommended solution; When the path duration is less than or equal to the duration threshold, it is determined that the recommended solution is not adjusted.

7. The emergency rescue process tracking system according to claim 6, characterized in that: When the judgment unit determines to adjust the recommended solution, the adjustment unit processes the rescue path information and the feature information based on K-Means clustering, including: The adjustment unit normalizes the rescue path information and the feature information to obtain a cluster vector; S1: The adjustment unit initializes K centroids in all adjustment schemes and assigns the clustering vector to the nearest centroid to form K clusters; S2: Recalculate the centroid of each cluster; S3: Repeat S1 and S2 until the center of mass no longer changes; S4: When there is only one data in the cluster where the cluster vector is located, an early warning is issued to the rescuer and the adjustment plan is obtained; when there are two or more data in the cluster where the cluster vector is located, the historical adjustment plans corresponding to the remaining historical cluster vectors in the cluster are used as the adjustment plan; The adjustment solution set includes a plurality of historical clustering vectors and historical adjustment solutions, and each of the historical clustering vectors corresponds to a historical adjustment solution.

8. The emergency rescue process tracking system according to claim 7, characterized in that: When the adjustment unit processes the rescue path information and the feature information based on K-Means clustering, the adjustment unit further includes: The centroid calculation formula is as follows: Where Mk represents the centroid of the k-th cluster, |Nk| represents the number of feature sets in the k-th cluster, and Zi represents the feature set of the i-th historical clustering vector.

9. The emergency rescue process tracking system according to claim 1, characterized in that: Also includes: A storage module is used to store the rescue process tracking information, historical pathology information and user real-time information.

10. A method for tracking the progress of emergency rescue, applied to the system for tracking the progress of emergency rescue according to any one of claims 1 to 9, characterized in that: include: Collect dial code information, and determine whether to start rescue process tracking based on the dial code information; When it is determined that rescue process tracking is started, the user's real-time information and historical pathological information are collected, the real-time information is processed based on the information importance model to determine feature information, and a recommendation plan is determined based on the feature information; collecting rescue path information and determining whether to adjust the recommended plan based on the rescue path information; when it is determined that adjustment is required, processing the rescue path information and feature information based on K-Means clustering, and determining an adjustment plan based on the clustering results; Sharing rescue progress tracking information with emergency contacts, users, users, and rescuers, the rescue progress tracking information including the recommended plan, rescue path information, interaction records, and adjustment plans; The rescue process tracking information, historical pathology information and user real-time information are stored.

Images